{"id":886,"date":"2013-10-10T14:19:57","date_gmt":"2013-10-10T14:19:57","guid":{"rendered":"http:\/\/jacobimed.org\/NS\/?page_id=886"},"modified":"2013-10-10T14:19:57","modified_gmt":"2013-10-10T14:19:57","slug":"stats-and-figures","status":"publish","type":"page","link":"https:\/\/jacobimed.org\/old\/ambulatory\/mlove\/practical-practice\/information-mastery\/stats-and-figures\/","title":{"rendered":"Stats and Figures"},"content":{"rendered":"<p>&nbsp;<\/p>\n<div class=\"Section1\">\n<p class=\"MsoBodyText3\" style=\"text-align: center;\"><span style=\"font-size: 12pt;\">AMBULATORY BLOCK<br \/>\nWINTER\/SPRING 2005<\/span><\/p>\n<p class=\"MsoNormal\" style=\"text-align: center;\"><span style=\"font-family: &quot;Book Antiqua&quot;;\"><!--[if !supportEmptyParas]-->&nbsp;<!--[endif]--><\/span><\/p>\n<p class=\"MsoNormal\" style=\"text-align: center;\"><span style=\"font-family: &quot;Book Antiqua&quot;;\"><!--[if gte vml 1]><v:shapetype id=\"_x0000_t75\"\n coordsize=\"21600,21600\" o:spt=\"75\" o:preferrelative=\"t\" path=\"m@4@5l@4@11@9@11@9@5xe\"\n filled=\"f\" stroked=\"f\">\n <v:stroke joinstyle=\"miter\" \/>\n <v:formulas>\n  <v:f eqn=\"if lineDrawn pixelLineWidth 0\" \/>\n  <v:f eqn=\"sum @0 1 0\" \/>\n  <v:f eqn=\"sum 0 0 @1\" \/>\n  <v:f eqn=\"prod @2 1 2\" \/>\n  <v:f eqn=\"prod @3 21600 pixelWidth\" \/>\n  <v:f eqn=\"prod @3 21600 pixelHeight\" \/>\n  <v:f eqn=\"sum @0 0 1\" \/>\n  <v:f eqn=\"prod @6 1 2\" \/>\n  <v:f eqn=\"prod @7 21600 pixelWidth\" \/>\n  <v:f eqn=\"sum @8 21600 0\" \/>\n  <v:f eqn=\"prod @7 21600 pixelHeight\" \/>\n  <v:f eqn=\"sum @10 21600 0\" \/>\n <\/v:formulas>\n <v:path o:extrusionok=\"f\" gradientshapeok=\"t\" o:connecttype=\"rect\" \/>\n <o:lock v:ext=\"edit\" aspectratio=\"t\" \/>\n<\/v:shapetype><v:shape id=\"_x0000_i1025\" type=\"#_x0000_t75\" style='width:104.25pt;\n height:109.5pt'>\n <v:imagedata src=\".\/stats%26figures_files\/image001.wmz\" mce_src=\"\/admin\/page\/edit\/stats%26figures_files\/image001.wmz\" o:title=\"bd06416_\" \/>\n<\/v:shape><![endif]--><!--[if !vml]--><img loading=\"lazy\" decoding=\"async\" src=\"\/public\/images\/ambulatory_content\/image002_diabetes.gif\" border=\"0\" alt=\"\/public\/images\/ambulatory_content\/image002_diabetes.gif\" title=\"\/public\/images\/ambulatory_content\/image002_diabetes.gif\" width=\"139\" height=\"146\" \/><!--[endif]--><br \/>\n<!--[if !supportLineBreakNewLine]--><br \/>\n<!--[endif]--><\/span><\/p>\n<p class=\"MsoBodyText3\" style=\"text-align: center;\"><span style=\"font-size: 12pt;\">PRACTICAL PRACTICE OF<br \/>\nMEDICINE<\/span><\/p>\n<p class=\"MsoNormal\"><span style=\"text-decoration: underline;\"><span style=\"font-size: 26pt; font-family: Broadway; color: #cc99ff;\"><!--[if !supportEmptyParas]-->&nbsp;<!--[endif]--><\/span><\/span><\/p>\n<p class=\"MsoNormal\" style=\"text-align: center;\" align=\"center\"><span style=\"font-size: 36pt; font-family: Broadway; color: #cc66ff;\">STATS &amp; FIGURES<\/span><span style=\"font-size: 36pt; color: #cc66ff;\"> <\/span><\/p>\n<p class=\"MsoNormal\" style=\"text-align: center;\" align=\"center\"><span style=\"font-size: 14pt; color: #cc66ff;\"><!--[if !supportEmptyParas]-->&nbsp;<!--[endif]--><\/span><\/p>\n<p class=\"MsoNormal\" style=\"text-align: justify;\"><span style=\"font-size: 14pt;\"><!--[if !supportEmptyParas]-->&nbsp;<!--[endif]--><\/span><\/p>\n<p class=\"MsoNormal\" style=\"margin-left: 0.5in; text-align: justify; text-indent: -0.25in;\"><!--[if !supportLists]--><span style=\"font-size: 14pt;\">1.<span style=\"font-family: &quot;Times New Roman&quot;; font-style: normal; font-variant: normal; font-weight: normal; font-size: 7pt; line-height: normal; font-size-adjust: none; font-stretch: normal;\">&nbsp;&nbsp;&nbsp;&nbsp;<br \/>\n<\/span><\/span><!--[endif]--><span style=\"font-size: 14pt;\"><a href=\"http:\/\/uptodateonline.com\/application\/topic.asp?file=genr_med\/17654&amp;type=A&amp;selectedTitle=1%7E3\">UpToDate<br \/>\nGlossary of common biostatistical and epidemiological terms<\/a><\/span><\/p>\n<p class=\"MsoNormal\" style=\"margin-left: 0.25in; text-align: justify;\"><span style=\"font-size: 14pt;\"><!--[if !supportEmptyParas]-->&nbsp;<!--[endif]--><\/span><\/p>\n<p class=\"MsoNormal\" style=\"text-align: justify;\"><span style=\"font-size: 14pt;\"><!--[if !supportEmptyParas]-->&nbsp;<!--[endif]--><\/span><\/p>\n<table style=\"width: 100%;\" border=\"0\" cellspacing=\"0\" cellpadding=\"0\">\n<tbody>\n<tr>\n<td style=\"padding: 0.75pt;\">\n<table style=\"width: 100%;\" border=\"0\" cellpadding=\"0\">\n<tbody>\n<tr>\n<td style=\"padding: 0.75pt;\">\n<table border=\"0\" cellspacing=\"0\" cellpadding=\"0\">\n<tbody>\n<tr>\n<td style=\"padding: 0in;\">\n<p class=\"MsoNormal\"><!--[if gte vml 1]><v:shape id=\"_x0000_i1026\" type=\"#_x0000_t75\"\n       alt=\"\" style='width:99.75pt;height:19.5pt'>\n       <v:imagedata src=\".\/stats%26figures_files\/image003.gif\" mce_src=\"\/admin\/page\/edit\/stats%26figures_files\/image003.gif\" o:href=\"http:\/\/uptodateonline.com\/application\/images\/uptodateLogoSmall1.gif\" \/>\n      <\/v:shape><![endif]--><!--[if !vml]--><img loading=\"lazy\" decoding=\"async\" src=\"\/public\/images\/ambulatory_content\/image003.gif\" border=\"0\" alt=\"\/public\/images\/ambulatory_content\/image003.gif\" title=\"\/public\/images\/ambulatory_content\/image003.gif\" width=\"133\" height=\"26\" style=\"border: 0pt none;\" \/><!--[endif]--><span style=\"font-family: &quot;Arial Unicode MS&quot;;\"><\/span><\/p>\n<\/td>\n<\/tr>\n<tr>\n<td style=\"padding: 0in;\">\n<table style=\"width: 100%;\" border=\"0\" cellspacing=\"0\" cellpadding=\"0\">\n<tbody>\n<tr>\n<td style=\"padding: 0in; width: 0.1in;\" width=\"10\">\n<p class=\"MsoNormal\"><!--[if gte vml 1]><v:shape id=\"_x0000_i1027\"\n         type=\"#_x0000_t75\" alt=\"\" style='width:38.25pt;height:18pt'>\n         <v:imagedata src=\".\/stats%26figures_files\/image004.gif\" mce_src=\"\/admin\/page\/edit\/stats%26figures_files\/image004.gif\" o:href=\"http:\/\/uptodateonline.com\/application\/images\/uptodateLogoSmall2.gif\" \/>\n        <\/v:shape><![endif]--><!--[if !vml]--><img loading=\"lazy\" decoding=\"async\" src=\"\/public\/images\/ambulatory_content\/image004.gif\" border=\"0\" alt=\"\/public\/images\/ambulatory_content\/image004.gif\" title=\"\/public\/images\/ambulatory_content\/image004.gif\" width=\"51\" height=\"24\" style=\"border: 0pt none;\" \/><!--[endif]--><span style=\"font-family: &quot;Arial Unicode MS&quot;;\"><\/span><\/p>\n<\/td>\n<td style=\"padding: 0in;\">\n<p class=\"MsoNormal\" style=\"text-align: center;\" align=\"center\"><strong><span style=\"font-size: 7.5pt; font-family: Verdana;\">ONLINE 12.3<\/span><\/strong><span style=\"font-family: &quot;Arial Unicode MS&quot;;\"><\/span><\/p>\n<\/td>\n<\/tr>\n<\/tbody>\n<\/table>\n<p class=\"MsoNormal\"><span style=\"font-family: &quot;Arial Unicode MS&quot;;\"><\/span><\/p>\n<\/td>\n<\/tr>\n<\/tbody>\n<\/table>\n<p class=\"MsoNormal\"><span style=\"font-family: &quot;Arial Unicode MS&quot;;\"><\/span><\/p>\n<\/td>\n<\/tr>\n<\/tbody>\n<\/table>\n<p class=\"MsoNormal\"><span style=\"font-family: &quot;Arial Unicode MS&quot;;\"><\/span><\/p>\n<\/td>\n<td style=\"padding: 0.75pt;\" valign=\"bottom\">\n<p class=\"MsoNormal\" style=\"text-align: right;\" align=\"right\"><span style=\"font-size: 7.5pt; font-family: Verdana;\">&copy;2005 UpToDate<\/span><sup><span style=\"font-size: 10pt; font-family: Verdana;\">&reg;<\/span><\/sup><\/p>\n<p><span style=\"font-family: &quot;Arial Unicode MS&quot;;\"><\/span>\n  <\/td>\n<\/tr>\n<tr>\n<td style=\"padding: 1.5pt; background: black none repeat scroll 0% 0%;\">\n<table style=\"background: black none repeat scroll 0% 0%; width: 100%;\" border=\"0\" cellspacing=\"0\" cellpadding=\"0\" bgcolor=\"black\">\n<tbody>\n<tr>\n<td style=\"padding: 2.25pt; width: 8%;\" width=\"8%\">\n<p class=\"MsoNormal\" style=\"text-align: center;\" align=\"center\"><span style=\"font-family: Verdana;\"><br \/>\n<script type=\"text\/javascript\"><!--\nfunction openSurvey(){\n\n\n\nif (''=='True'){\n\n\tif(navigator.userAgent.indexOf('Mac') != -1){\n\n\twindow.open('..\/feedback\/surveyapp\/liveSurvey.asp?link=1','Survey','height=555,width=500,location=no,directories=no,status=yes,menubar=no,scrollbars=yes,resizable=yes');\n\n   \treturn true;\n\n\t}\n\n}\n\nelse{\n\n   window.open('..\/feedback\/surveyapp\/liveSurvey.asp?link=1','Survey','height=555,width=500,location=no,directories=no,status=yes,menubar=no,scrollbars=yes,resizable=yes');\n\n   return true;\n\n}\n\n}\n\n\n\nfunction openFeedback()\n\n{\n\n\twindow.open('..\/..\/..\/application\/feedback\/letters\/writeFeedback.asp','feedback','height=450,width=410,toolbar=no,location=no,directories=no,status=yes,menubar=no,scrollbars=yes,resizable=yes')\n\n\treturn false;\n\n}\n\/\/ --><\/script><br \/>\n<\/span><strong><span style=\"font-size: 10pt; font-family: Verdana;\"><a href=\"http:\/\/uptodateonline.com\/application\/search.asp\"><!-- Search button --><span style=\"color: white;\">New Search<\/span><\/a><\/span><\/strong><span style=\"font-family: &quot;Arial Unicode MS&quot;;\"><\/span><\/p>\n<\/td>\n<p><!--Peds Feedback Button --><!-- TOC button --><\/p>\n<td style=\"padding: 2.25pt; width: 14%;\" width=\"14%\">\n<p class=\"MsoNormal\" style=\"text-align: center;\" align=\"center\"><strong><span style=\"font-size: 10pt; font-family: Verdana;\"><a href=\"http:\/\/uptodateonline.com\/application\/toc.asp\"><span style=\"color: white;\">Table of Contents<\/span><\/a><\/span><\/strong><span style=\"font-family: &quot;Arial Unicode MS&quot;;\"><\/span><\/p>\n<\/td>\n<p><!-- My UpToDate button --><!-- Feedback button --><\/p>\n<td style=\"padding: 2.25pt; width: 10%;\" width=\"10%\">\n<p class=\"MsoNormal\" style=\"text-align: center;\" align=\"center\"><strong><span style=\"text-decoration: underline;\"><span style=\"font-size: 10pt; font-family: Verdana; color: white;\"><a href=\"http:\/\/uptodateonline.com\/application\/topic\/print.asp?file=genr_med\/feedback\/letters\/writeFeedback.asp\" onclick=\"return openFeedback();\"><span style=\"color: white;\">Feedback<\/span><\/a><\/span><\/span><\/strong><span style=\"font-family: &quot;Arial Unicode MS&quot;;\"><\/span><\/p>\n<\/td>\n<p><!-- Help button --><\/p>\n<td style=\"padding: 2.25pt; width: 4%;\" width=\"4%\">\n<p class=\"MsoNormal\" style=\"text-align: center;\" align=\"center\"><strong><span style=\"font-size: 10pt; font-family: Verdana;\"><a href=\"http:\/\/uptodateonline.com\/application\/help.asp\"><span style=\"color: white;\">Help<\/span><\/a><\/span><\/strong><span style=\"font-family: &quot;Arial Unicode MS&quot;;\"><\/span><\/p>\n<\/td>\n<p><!-- Purchase Now button --><\/p>\n<\/tr>\n<\/tbody>\n<\/table>\n<p class=\"MsoNormal\"><span style=\"font-family: &quot;Arial Unicode MS&quot;;\"><\/span><\/p>\n<\/td>\n<\/tr>\n<\/tbody>\n<\/table>\n<p class=\"MsoNormal\"><span style=\"font-family: Verdana;\"><!--[if !supportEmptyParas]-->&nbsp;<!--[endif]--><\/span><\/p>\n<table style=\"background: black none repeat scroll 0% 0%; width: 100%;\" border=\"0\" cellspacing=\"0\" cellpadding=\"0\" bgcolor=\"black\">\n<tbody>\n<tr>\n<td style=\"padding: 0.75pt;\">\n<table style=\"background: white none repeat scroll 0% 0%; width: 100%;\" border=\"0\" cellspacing=\"0\" cellpadding=\"0\" bgcolor=\"white\">\n<tbody>\n<tr>\n<td style=\"padding: 3pt;\">\n<p class=\"MsoNormal\" style=\"text-align: center;\" align=\"center\"><span style=\"font-size: 10pt; font-family: Verdana;\">Official reprint from <strong><em><span style=\"color: #007760;\">UpToDate<sup>&reg;<\/sup><\/span><\/em><\/strong> <a href=\"http:\/\/www.uptodate.com\/\">www.uptodate.com<\/a><\/span><span style=\"font-family: &quot;Arial Unicode MS&quot;;\"><\/span><\/p>\n<\/td>\n<\/tr>\n<\/tbody>\n<\/table>\n<p class=\"MsoNormal\"><span style=\"font-family: &quot;Arial Unicode MS&quot;;\"><\/span><\/p>\n<\/td>\n<\/tr>\n<\/tbody>\n<\/table>\n<p class=\"MsoNormal\"><span style=\"font-size: 10pt; font-family: Verdana;\"><!--[if !supportEmptyParas]-->&nbsp;<!--[endif]--><\/span><\/p>\n<p class=\"MsoNormal\" style=\"text-align: center;\" align=\"center\"><strong><span style=\"font-size: 10pt; font-family: Verdana;\">Glossary of common biostatistical<br \/>\nand epidemiological terms<\/span><\/strong><span style=\"font-size: 10pt; font-family: Verdana;\"><\/span><\/p>\n<p class=\"MsoNormal\" style=\"margin-bottom: 12pt;\"><span style=\"font-size: 10pt; font-family: Verdana;\"><br \/>\n<a href=\"http:\/\/uptodateonline.com\/application\/author.asp?ID=251745\" target=\"side\" onclick=\"javascript:window.open('\/application\/author.asp?ID=251745', 'author', 'toolbar=no,menubar=no,resizable=yes,height=200,width=300');return(false);\">Peter<br \/>\nA L Bonis, MD<\/a><\/span><\/p>\n<p><em><span style=\"font-size: 10pt; font-family: Verdana;\">UpToDate performs a<br \/>\ncontinuous review of over 330 journals and other resources. Updates are added<br \/>\nas important new information is published. The literature review for version<br \/>\n12.3 is current through August 2004; this topic was last changed on July 28, 2004.<br \/>\nThe next version of UpToDate (13.1) will be released in February 2005. <\/span><\/em><span style=\"font-size: 10pt; font-family: Verdana;\"><\/span><\/p>\n<p><strong><span style=\"font-size: 10pt; font-family: Verdana;\">INTRODUCTION<\/span><\/strong><span style=\"font-size: 10pt; font-family: Verdana;\"> &mdash; This topic review will provide<br \/>\na catalog of common biostatistical and epidemiological terms encountered in the<br \/>\nmedical literature. A list of textbooks that are geared toward health<br \/>\nprofessionals interested in these topics is provided in the references [<a href=\"http:\/\/uptodateonline.com\/application\/abstract.asp?TR=genr_med\/17654&amp;viewAbs=1%7E2%7E3%7E4%7E5%7E6%7E7%7E8&amp;title=1-8\" target=\"side\">1-8<\/a>].<\/span><\/p>\n<p><strong><span style=\"font-size: 10pt; font-family: Verdana;\">STATISTICS THAT<br \/>\nDESCRIBE HOW DATA ARE DISTRIBUTED<\/span><\/strong><span style=\"font-size: 10pt; font-family: Verdana;\"><\/span><\/p>\n<p><strong><span style=\"font-size: 10pt; font-family: Verdana;\">Measures of central<br \/>\ntendency<\/span><\/strong><span style=\"font-size: 10pt; font-family: Verdana;\"> &mdash; Three<br \/>\nmeasures of central tendency are most frequently used to describe data:<\/span><\/p>\n<p class=\"MsoNormal\" style=\"margin-bottom: 12pt;\"><span style=\"font-size: 10pt; font-family: Verdana;\">&nbsp;&nbsp;<!--[if gte vml 1]><v:shape id=\"_x0000_i1029\"\n type=\"#_x0000_t75\" alt=\"bullet\" style='width:4.5pt;height:5.25pt'>\n <v:imagedata src=\".\/stats%26figures_files\/image005.gif\" mce_src=\"\/admin\/page\/edit\/stats%26figures_files\/image005.gif\" o:href=\"http:\/\/uptodateonline.com\/application\/images\/characters\/bull.gif\" \/>\n<\/v:shape><![endif]--><!--[if !vml]--><img loading=\"lazy\" decoding=\"async\" src=\"file:\/\/\/C:\/Documents%20and%20Settings\/LauraKoo\/Desktop\/ambulatory_backup\/mlove\/Practical%20Practice\/Information%20Mastery\/stats&amp;figures_files\/image005.gif\" border=\"0\" alt=\"bullet\" width=\"6\" height=\"7\" \/><!--[endif]-->&nbsp;Mean<br \/>\nequals the sum of observations divided by the number of observations.<\/p>\n<p>&nbsp;&nbsp;<!--[if gte vml 1]><v:shape id=\"_x0000_i1030\" type=\"#_x0000_t75\"\n alt=\"bullet\" style='width:4.5pt;height:5.25pt'>\n <v:imagedata src=\".\/stats%26figures_files\/image005.gif\" mce_src=\"\/admin\/page\/edit\/stats%26figures_files\/image005.gif\" o:href=\"http:\/\/uptodateonline.com\/application\/images\/characters\/bull.gif\" \/>\n<\/v:shape><![endif]--><!--[if !vml]--><img loading=\"lazy\" decoding=\"async\" src=\"file:\/\/\/C:\/Documents%20and%20Settings\/LauraKoo\/Desktop\/ambulatory_backup\/mlove\/Practical%20Practice\/Information%20Mastery\/stats&amp;figures_files\/image005.gif\" border=\"0\" alt=\"bullet\" width=\"6\" height=\"7\" \/><!--[endif]-->&nbsp;Median<br \/>\nequals the observation in the middle when all observations are ordered from<br \/>\nsmallest to largest; when there are an even number of observations the median<br \/>\nis defined as the mean of the middle two data points.<\/p>\n<p>&nbsp;&nbsp;<!--[if gte vml 1]><v:shape id=\"_x0000_i1031\" type=\"#_x0000_t75\"\n alt=\"bullet\" style='width:4.5pt;height:5.25pt'>\n <v:imagedata src=\".\/stats%26figures_files\/image005.gif\" mce_src=\"\/admin\/page\/edit\/stats%26figures_files\/image005.gif\" o:href=\"http:\/\/uptodateonline.com\/application\/images\/characters\/bull.gif\" \/>\n<\/v:shape><![endif]--><!--[if !vml]--><img loading=\"lazy\" decoding=\"async\" src=\"file:\/\/\/C:\/Documents%20and%20Settings\/LauraKoo\/Desktop\/ambulatory_backup\/mlove\/Practical%20Practice\/Information%20Mastery\/stats&amp;figures_files\/image005.gif\" border=\"0\" alt=\"bullet\" width=\"6\" height=\"7\" \/><!--[endif]-->&nbsp;Mode<br \/>\nequals the observation that occurs most frequently.<\/span><\/p>\n<p><strong><span style=\"font-size: 10pt; font-family: Verdana;\">Measures of dispersion<\/span><\/strong><span style=\"font-size: 10pt; font-family: Verdana;\"> &mdash; Dispersion (or variance) refers<br \/>\nto the degree to which data are scattered around a specific value (such as the<br \/>\nmean). The most commonly used measures of dispersion are:<\/span><\/p>\n<p class=\"MsoNormal\" style=\"margin-bottom: 12pt;\"><span style=\"font-size: 10pt; font-family: Verdana;\">&nbsp;&nbsp;<!--[if gte vml 1]><v:shape id=\"_x0000_i1032\"\n type=\"#_x0000_t75\" alt=\"bullet\" style='width:4.5pt;height:5.25pt'>\n <v:imagedata src=\".\/stats%26figures_files\/image005.gif\" mce_src=\"\/admin\/page\/edit\/stats%26figures_files\/image005.gif\" o:href=\"http:\/\/uptodateonline.com\/application\/images\/characters\/bull.gif\" \/>\n<\/v:shape><![endif]--><!--[if !vml]--><img loading=\"lazy\" decoding=\"async\" src=\"file:\/\/\/C:\/Documents%20and%20Settings\/LauraKoo\/Desktop\/ambulatory_backup\/mlove\/Practical%20Practice\/Information%20Mastery\/stats&amp;figures_files\/image005.gif\" border=\"0\" alt=\"bullet\" width=\"6\" height=\"7\" \/><!--[endif]-->&nbsp;Range<br \/>\n&mdash; The range equals the difference between the largest and smallest observation.<\/p>\n<p>&nbsp;&nbsp;<!--[if gte vml 1]><v:shape id=\"_x0000_i1033\" type=\"#_x0000_t75\"\n alt=\"bullet\" style='width:4.5pt;height:5.25pt'>\n <v:imagedata src=\".\/stats%26figures_files\/image005.gif\" mce_src=\"\/admin\/page\/edit\/stats%26figures_files\/image005.gif\" o:href=\"http:\/\/uptodateonline.com\/application\/images\/characters\/bull.gif\" \/>\n<\/v:shape><![endif]--><!--[if !vml]--><img loading=\"lazy\" decoding=\"async\" src=\"file:\/\/\/C:\/Documents%20and%20Settings\/LauraKoo\/Desktop\/ambulatory_backup\/mlove\/Practical%20Practice\/Information%20Mastery\/stats&amp;figures_files\/image005.gif\" border=\"0\" alt=\"bullet\" width=\"6\" height=\"7\" \/><!--[endif]-->&nbsp;Standard<br \/>\ndeviation &mdash; The standard deviation measures the variability of data around the<br \/>\nmean. It provides information on how much variability can be expected among<br \/>\nindividuals within a population. Sixty-eight and 95 percent of values in a<br \/>\nsample population fall within one and two standard deviations of the mean,<br \/>\nrespectively.<\/p>\n<p>&nbsp;&nbsp;<!--[if gte vml 1]><v:shape id=\"_x0000_i1034\" type=\"#_x0000_t75\"\n alt=\"bullet\" style='width:4.5pt;height:5.25pt'>\n <v:imagedata src=\".\/stats%26figures_files\/image005.gif\" mce_src=\"\/admin\/page\/edit\/stats%26figures_files\/image005.gif\" o:href=\"http:\/\/uptodateonline.com\/application\/images\/characters\/bull.gif\" \/>\n<\/v:shape><![endif]--><!--[if !vml]--><img loading=\"lazy\" decoding=\"async\" src=\"file:\/\/\/C:\/Documents%20and%20Settings\/LauraKoo\/Desktop\/ambulatory_backup\/mlove\/Practical%20Practice\/Information%20Mastery\/stats&amp;figures_files\/image005.gif\" border=\"0\" alt=\"bullet\" width=\"6\" height=\"7\" \/><!--[endif]-->&nbsp;Standard<br \/>\nerror of the mean &mdash; Standard deviation of the mean (for a sample population)<br \/>\nshould be distinguished from the standard error of the mean, which describes<br \/>\nhow much variability can be expected when measuring the mean from several<br \/>\ndifferent samples.<\/p>\n<p>&nbsp;&nbsp;<!--[if gte vml 1]><v:shape id=\"_x0000_i1035\" type=\"#_x0000_t75\"\n alt=\"bullet\" style='width:4.5pt;height:5.25pt'>\n <v:imagedata src=\".\/stats%26figures_files\/image005.gif\" mce_src=\"\/admin\/page\/edit\/stats%26figures_files\/image005.gif\" o:href=\"http:\/\/uptodateonline.com\/application\/images\/characters\/bull.gif\" \/>\n<\/v:shape><![endif]--><!--[if !vml]--><img loading=\"lazy\" decoding=\"async\" src=\"file:\/\/\/C:\/Documents%20and%20Settings\/LauraKoo\/Desktop\/ambulatory_backup\/mlove\/Practical%20Practice\/Information%20Mastery\/stats&amp;figures_files\/image005.gif\" border=\"0\" alt=\"bullet\" width=\"6\" height=\"7\" \/><!--[endif]-->&nbsp;Percentile<br \/>\n&mdash; The percentile equals the percentage of a distribution that is below a<br \/>\nspecific value. As an example, a child is in 90th percentile for weight if only<br \/>\n10 percent of children the same age weigh more than she does.<\/p>\n<p>&nbsp;&nbsp;<!--[if gte vml 1]><v:shape id=\"_x0000_i1036\" type=\"#_x0000_t75\"\n alt=\"bullet\" style='width:4.5pt;height:5.25pt'>\n <v:imagedata src=\".\/stats%26figures_files\/image005.gif\" mce_src=\"\/admin\/page\/edit\/stats%26figures_files\/image005.gif\" o:href=\"http:\/\/uptodateonline.com\/application\/images\/characters\/bull.gif\" \/>\n<\/v:shape><![endif]--><!--[if !vml]--><img loading=\"lazy\" decoding=\"async\" src=\"file:\/\/\/C:\/Documents%20and%20Settings\/LauraKoo\/Desktop\/ambulatory_backup\/mlove\/Practical%20Practice\/Information%20Mastery\/stats&amp;figures_files\/image005.gif\" border=\"0\" alt=\"bullet\" width=\"6\" height=\"7\" \/><!--[endif]-->&nbsp;Interquartile<br \/>\nrange &mdash; The interquartile range refers to the upper and lower values defining<br \/>\nthe central 50 percent of observations. The boundaries are equal to the<br \/>\nobservations representing the 25th and 75th percentiles. The interquartile<br \/>\nrange is depicted in a box and whiskers plot (<a href=\"http:\/\/uptodateonline.com\/application\/image.asp?file=prim_pix\/box_and_.gif\" target=\"side\">show figure 1<\/a>).<\/span><\/p>\n<p><strong><span style=\"font-size: 10pt; font-family: Verdana;\">TERMS USED TO DESCRIBE<br \/>\nTHE FREQUENCY OF AN EVENT<\/span><\/strong><span style=\"font-size: 10pt; font-family: Verdana;\"> &mdash; Incidence and prevalence are the two main terms used to describe<br \/>\nthe frequency of an event.<\/span><\/p>\n<p><strong><span style=\"font-size: 10pt; font-family: Verdana;\">Incidence<\/span><\/strong><span style=\"font-size: 10pt; font-family: Verdana;\"> &mdash; Incidence represents the number<br \/>\nof new events that have occurred in a specific time interval divided by the<br \/>\npopulation at risk at the beginning of the time interval. The result gives the<br \/>\nlikelihood of developing an event in that time interval.<\/span><\/p>\n<p><strong><span style=\"font-size: 10pt; font-family: Verdana;\">Prevalence<\/span><\/strong><span style=\"font-size: 10pt; font-family: Verdana;\"> &mdash; Prevalence refers to the number<br \/>\nof individuals with a given disease at a given point in time divided by the<br \/>\npopulation at risk at that point in time.<\/span><\/p>\n<p><strong><span style=\"font-size: 10pt; font-family: Verdana;\">TERMS USED TO DESCRIBE<br \/>\nTHE MAGNITUDE OF AN EFFECT<\/span><\/strong><span style=\"font-size: 10pt; font-family: Verdana;\"> &mdash; The types of descriptors used to define the relationship among<br \/>\nvariables of interest in a data set and the effect of one variable on another<br \/>\ndepend upon the type of data. Important examples are the relative risk and odds<br \/>\nratio, which are commonly encountered expressions describing the relationship<br \/>\nbetween nominal characteristics (ie, variables that are grouped as unique<br \/>\ncategories) (<a href=\"http:\/\/uptodateonline.com\/application\/image.asp?file=prim_pix\/relative.gif\" target=\"side\">show figure 2<\/a>).<\/span><\/p>\n<p><strong><span style=\"font-size: 10pt; font-family: Verdana;\">Relative risk and<br \/>\ncohort studies<\/span><\/strong><span style=\"font-size: 10pt; font-family: Verdana;\"> &mdash;<br \/>\nThe relative risk (or risk ratio) equals the incidence in exposed individuals<br \/>\ndivided by the incidence in unexposed individuals. The relative risk can be<br \/>\ncalculated from studies in which the proportion of patients exposed and<br \/>\nunexposed to a risk is known. An example is a cohort study, in which a group of<br \/>\npatients who have variable exposure to a risk factor of interest are followed<br \/>\nover time for an outcome. The Nurses&#8217; Health Study is an example of a cohort<br \/>\nstudy. A large number of nurses are followed over time for an outcome such as<br \/>\ncolon cancer. Those with and without colon cancer are then evaluated for their<br \/>\ndietary fiber intake to determine if it is a risk factor (or a protective<br \/>\nfactor) for colon cancer.<\/span><\/p>\n<p><strong><span style=\"font-size: 10pt; font-family: Verdana;\">Odds ratio and<br \/>\ncase-control studies<\/span><\/strong><span style=\"font-size: 10pt; font-family: Verdana;\"><br \/>\n&mdash; The odds ratio equals the odds that an individual with a specific condition<br \/>\nhas been exposed to a risk factor divided by the odds that a control has been<br \/>\nexposed. The odds ratio is used in case-control studies. In this type of study,<br \/>\npatients with a disease are identified and compared with matched controls for<br \/>\nexposure to a risk factor. This design does not permit measurement of the<br \/>\nproportion of the population who were exposed to the risk factor and then<br \/>\ndeveloped or did not develop the disease; thus, the relative risk or the<br \/>\nincidence of disease cannot be calculated. However, in case-control studies,<br \/>\nthe odds ratio provides a reasonable estimate of the relative risk (<a href=\"http:\/\/uptodateonline.com\/application\/image.asp?file=prim_pix\/relative.gif\" target=\"side\">show figure 2<\/a>).<\/span><\/p>\n<p><span style=\"font-size: 10pt; font-family: Verdana;\">If one were to perform a<br \/>\ncase-control study to assess the role of dietary fiber in colon cancer as noted<br \/>\nabove for the cohort study, a group of patients with colon cancer would be<br \/>\ncompared with matched controls without colon cancer; the fiber intake in the<br \/>\ntwo groups would then be compared. The case-control study is most useful for<br \/>\nuncommon diseases in which a very large cohort would be required to accumulate<br \/>\nenough cases for analysis.<\/span><\/p>\n<p><span style=\"font-size: 10pt; font-family: Verdana;\">The relative risk and<br \/>\nodds ratio are interpreted relative to the number one. An odds ratio of 0.6,<br \/>\nfor example, suggests that patients exposed to a variable of interest were 40<br \/>\npercent less likely to develop a specific outcome compared to the control<br \/>\ngroup. Similarly, an odds ratio of 1.5 suggests that the risk was increased by<br \/>\n50 percent.<\/span><\/p>\n<p><strong><span style=\"font-size: 10pt; font-family: Verdana;\">Absolute risk<\/span><\/strong><span style=\"font-size: 10pt; font-family: Verdana;\"> &mdash; The relative risk and odds<br \/>\nratio provide an understanding of the magnitude of risk compared with a<br \/>\nstandard. However, it is more often desirable to know information about the<br \/>\nabsolute risk. As an example, a 40 percent increase in mortality due to a<br \/>\nparticular exposure does not provide direct insight into the likelihood that<br \/>\nexposure in an individual patient will lead to mortality.<\/span><\/p>\n<p><span style=\"font-size: 10pt; font-family: Verdana;\">The &#8220;attributable<br \/>\nrisk&#8221; (also called the risk difference) is a measure of absolute risk. It<br \/>\nreflects the additional incidence of disease related to an exposure taking into<br \/>\naccount the background rate of the disease. The attributable risk is calculated<br \/>\nby subtracting the incidence of a disease in nonexposed persons from the<br \/>\nincidence of disease in exposed persons.<\/span><\/p>\n<p><span style=\"font-size: 10pt; font-family: Verdana;\">A related term, the<br \/>\n&#8220;population attributable risk&#8221; is used to describe the contribution<br \/>\nthat an exposure has on the incidence of a specific disease in a population. It<br \/>\nis calculated by multiplying the attributable risk by the prevalence of exposure<br \/>\nto a risk factor in a population. The population attributable risk is<br \/>\nparticularly important when considering public health measures and the<br \/>\nallocation of resources intended to reduce the incidence of a disease.<\/span><\/p>\n<p><strong><span style=\"font-size: 10pt; font-family: Verdana;\">Number needed to treat<\/span><\/strong><span style=\"font-size: 10pt; font-family: Verdana;\"> &mdash; The benefit of an intervention<br \/>\ncan be expressed by the &#8220;number needed to treat&#8221; (NNT). NNT is the<br \/>\nreciprocal of the absolute risk reduction (the absolute adverse event rate for<br \/>\nplacebo minus the absolute adverse event rate for treated patients). Its<br \/>\ninterpretation can be illustrated by the following sentence: &#8220;This study<br \/>\nsuggests that I would have to treat five patients with a drug to prevent one<br \/>\ndeath.&#8221;<\/span><\/p>\n<p><span style=\"font-size: 10pt; font-family: Verdana;\">As an example, consider a<br \/>\nplacebo-controlled trial involving 100 patients. Thirty patients died during<br \/>\nthe study period (10 receiving active drug and 20 receiving placebo) giving a<br \/>\nmortality rate of 20 percent with active drug versus 40 percent with placebo (<a href=\"http:\/\/uptodateonline.com\/application\/image.asp?file=prim_pix\/number_n.gif\" target=\"side\">show figure 3<\/a>). The difference between these two rates, the<br \/>\n&#8220;risk difference&#8221;, is used to calculate NNT.<\/span><\/p>\n<p class=\"MsoNormal\" style=\"margin-bottom: 12pt;\"><span style=\"font-size: 10pt; font-family: Verdana;\">&nbsp;&nbsp;<!--[if gte vml 1]><v:shape id=\"_x0000_i1037\"\n type=\"#_x0000_t75\" alt=\"bullet\" style='width:4.5pt;height:5.25pt'>\n <v:imagedata src=\".\/stats%26figures_files\/image005.gif\" mce_src=\"\/admin\/page\/edit\/stats%26figures_files\/image005.gif\" o:href=\"http:\/\/uptodateonline.com\/application\/images\/characters\/bull.gif\" \/>\n<\/v:shape><![endif]--><!--[if !vml]--><img loading=\"lazy\" decoding=\"async\" src=\"file:\/\/\/C:\/Documents%20and%20Settings\/LauraKoo\/Desktop\/ambulatory_backup\/mlove\/Practical%20Practice\/Information%20Mastery\/stats&amp;figures_files\/image005.gif\" border=\"0\" alt=\"bullet\" width=\"6\" height=\"7\" \/><!--[endif]-->&nbsp;40<br \/>\npercent minus 20 percent = 20 percent = 0.2<\/p>\n<p>&nbsp;&nbsp;<!--[if gte vml 1]><v:shape id=\"_x0000_i1038\" type=\"#_x0000_t75\"\n alt=\"bullet\" style='width:4.5pt;height:5.25pt'>\n <v:imagedata src=\".\/stats%26figures_files\/image005.gif\" mce_src=\"\/admin\/page\/edit\/stats%26figures_files\/image005.gif\" o:href=\"http:\/\/uptodateonline.com\/application\/images\/characters\/bull.gif\" \/>\n<\/v:shape><![endif]--><!--[if !vml]--><img loading=\"lazy\" decoding=\"async\" src=\"file:\/\/\/C:\/Documents%20and%20Settings\/LauraKoo\/Desktop\/ambulatory_backup\/mlove\/Practical%20Practice\/Information%20Mastery\/stats&amp;figures_files\/image005.gif\" border=\"0\" alt=\"bullet\" width=\"6\" height=\"7\" \/><!--[endif]-->&nbsp;1<br \/>\ndivided by 0.2 = 5<\/span><\/p>\n<p><span style=\"font-size: 10pt; font-family: Verdana;\">Thus, this study suggests<br \/>\nthat only five patients need to be treated with the drug (compared with<br \/>\nplacebo) to prevent one death.<\/span><\/p>\n<p><span style=\"font-size: 10pt; font-family: Verdana;\">Because it is intuitive,<br \/>\nthe NNT has become an increasingly popular expression of absolute benefit or<br \/>\nrisk, potentially allowing for comparison of the relative benefit (or harm) of<br \/>\ndifferent interventions. However, the NNT can be misleading:<\/span><\/p>\n<p class=\"MsoNormal\" style=\"margin-bottom: 12pt;\"><span style=\"font-size: 10pt; font-family: Verdana;\">&nbsp;&nbsp;<!--[if gte vml 1]><v:shape id=\"_x0000_i1039\"\n type=\"#_x0000_t75\" alt=\"bullet\" style='width:4.5pt;height:5.25pt'>\n <v:imagedata src=\".\/stats%26figures_files\/image005.gif\" mce_src=\"\/admin\/page\/edit\/stats%26figures_files\/image005.gif\" o:href=\"http:\/\/uptodateonline.com\/application\/images\/characters\/bull.gif\" \/>\n<\/v:shape><![endif]--><!--[if !vml]--><img loading=\"lazy\" decoding=\"async\" src=\"file:\/\/\/C:\/Documents%20and%20Settings\/LauraKoo\/Desktop\/ambulatory_backup\/mlove\/Practical%20Practice\/Information%20Mastery\/stats&amp;figures_files\/image005.gif\" border=\"0\" alt=\"bullet\" width=\"6\" height=\"7\" \/><!--[endif]-->&nbsp;It<br \/>\nimplies that the option is to treat or not to treat rather than to treat or<br \/>\nswitch to another more effective treatment [<a href=\"http:\/\/uptodateonline.com\/application\/abstract.asp?TR=genr_med\/17654&amp;viewAbs=9&amp;title=9\" target=\"side\">9<\/a>].<\/p>\n<p>&nbsp;&nbsp;<!--[if gte vml 1]><v:shape id=\"_x0000_i1040\" type=\"#_x0000_t75\"\n alt=\"bullet\" style='width:4.5pt;height:5.25pt'>\n <v:imagedata src=\".\/stats%26figures_files\/image005.gif\" mce_src=\"\/admin\/page\/edit\/stats%26figures_files\/image005.gif\" o:href=\"http:\/\/uptodateonline.com\/application\/images\/characters\/bull.gif\" \/>\n<\/v:shape><![endif]--><!--[if !vml]--><img loading=\"lazy\" decoding=\"async\" src=\"file:\/\/\/C:\/Documents%20and%20Settings\/LauraKoo\/Desktop\/ambulatory_backup\/mlove\/Practical%20Practice\/Information%20Mastery\/stats&amp;figures_files\/image005.gif\" border=\"0\" alt=\"bullet\" width=\"6\" height=\"7\" \/><!--[endif]-->&nbsp;There<br \/>\nare variations on how NNT is determined; NNTs from different studies cannot be<br \/>\ncompared unless the methods used to determine them are identical [<a href=\"http:\/\/uptodateonline.com\/application\/abstract.asp?TR=genr_med\/17654&amp;viewAbs=10&amp;title=10\" target=\"side\">10<\/a>]. This may be a particular consideration when NNTs are<br \/>\ncalculated for treatment of chronic diseases in which outcomes (such as<br \/>\nmortality) do not cluster in time.<\/p>\n<p>&nbsp;&nbsp;<!--[if gte vml 1]><v:shape id=\"_x0000_i1041\" type=\"#_x0000_t75\"\n alt=\"bullet\" style='width:4.5pt;height:5.25pt'>\n <v:imagedata src=\".\/stats%26figures_files\/image005.gif\" mce_src=\"\/admin\/page\/edit\/stats%26figures_files\/image005.gif\" o:href=\"http:\/\/uptodateonline.com\/application\/images\/characters\/bull.gif\" \/>\n<\/v:shape><![endif]--><!--[if !vml]--><img loading=\"lazy\" decoding=\"async\" src=\"file:\/\/\/C:\/Documents%20and%20Settings\/LauraKoo\/Desktop\/ambulatory_backup\/mlove\/Practical%20Practice\/Information%20Mastery\/stats&amp;figures_files\/image005.gif\" border=\"0\" alt=\"bullet\" width=\"6\" height=\"7\" \/><!--[endif]-->&nbsp;Calculation<br \/>\nof the NNT depends upon the control rate (ie, the rate of events in the control<br \/>\narm), which can be variable (particularly in small controlled trials, which are<br \/>\nmore vulnerable to random effects). As a result, the NNT may not accurately<br \/>\nreflect the benefit of an intervention if events occurred in the control arm<br \/>\nmore or less than would be expected based upon the biology of the disease. This<br \/>\neffect can be particularly problematic when comparing the NNTs among placebo<br \/>\ncontrolled trials (<a href=\"http:\/\/uptodateonline.com\/application\/image.asp?file=prim_pix\/number_n.gif\" target=\"side\">show figure 3<\/a>) [<a href=\"http:\/\/uptodateonline.com\/application\/abstract.asp?TR=genr_med\/17654&amp;viewAbs=11&amp;title=11\" target=\"side\">11<\/a>].<\/span><\/p>\n<p><strong><span style=\"font-size: 10pt; font-family: Verdana;\">TERMS USED TO DESCRIBE<br \/>\nTHE QUALITY OF MEASUREMENTS<\/span><\/strong><span style=\"font-size: 10pt; font-family: Verdana;\"> &mdash; The most commonly used measures to describe the quality of an<br \/>\nobservation are reliability and validity.<\/span><\/p>\n<p><strong><span style=\"font-size: 10pt; font-family: Verdana;\">Reliability<\/span><\/strong><span style=\"font-size: 10pt; font-family: Verdana;\"> &mdash; Reliability refers to the<br \/>\nextent to which repeated measurements of a relatively stable phenomenon fall<br \/>\nclosely to each other. Several different types of reliability can be measured.<br \/>\nExamples include inter- and intraobserver reliability and test-retest<br \/>\nreliability.<\/span><\/p>\n<p><strong><span style=\"font-size: 10pt; font-family: Verdana;\">Validity<\/span><\/strong><span style=\"font-size: 10pt; font-family: Verdana;\"> &mdash; Validity refers to the extent<br \/>\nto which an observation reflects the &#8220;truth&#8221; of the phenomenon being<br \/>\nmeasured. Several types can be measured such as content (the extent to which<br \/>\nthe measure reflects the dimensions of a particular problem), construct (the<br \/>\nextent to which a measure is affirmed by an external established indicator),<br \/>\nand criterion validity (the extent to which a measure can predict an observable<br \/>\nphenomenon). These types of validity are often applied to questionnaires, in<br \/>\nwhich the truth is not physically verifiable.<\/span><\/p>\n<p><strong><span style=\"font-size: 10pt; font-family: Verdana;\">MEASURES OF DIAGNOSTIC<br \/>\nTEST ACCURACY<\/span><\/strong><span style=\"font-size: 10pt; font-family: Verdana;\"> &mdash;<br \/>\nThe most common terms used to describe the accuracy of a diagnostic test are<br \/>\nsensitivity and specificity (<a href=\"http:\/\/uptodateonline.com\/application\/image.asp?file=gast_pix\/sensit1.gif\" target=\"side\">show figure 4<\/a>).<\/span><\/p>\n<p><strong><span style=\"font-size: 10pt; font-family: Verdana;\">Sensitivity<\/span><\/strong><span style=\"font-size: 10pt; font-family: Verdana;\"> &mdash; The number of patients with a<br \/>\npositive test who have a disease divided by all patients who have the disease.<br \/>\nA test with high sensitivity will not miss many patients who have the disease<br \/>\n(ie, few false negative results).<\/span><\/p>\n<p><strong><span style=\"font-size: 10pt; font-family: Verdana;\">Specificity<\/span><\/strong><span style=\"font-size: 10pt; font-family: Verdana;\"> &mdash; The number of patients who have<br \/>\na negative test and do not have the disease divided by the number of patients<br \/>\nwho do not have the disease. A test with high specificity will infrequently<br \/>\nidentify patients as having a disease when they do not (ie, few false positive<br \/>\nresults).<\/span><\/p>\n<p><span style=\"font-size: 10pt; font-family: Verdana;\">Sensitivity and<br \/>\nspecificity are properties of tests that should be considered when tests are<br \/>\nobtained. In addition, sensitivity and specificity are interdependent. Thus,<br \/>\nfor a given test, an increase in sensitivity is accompanied by a decrease in<br \/>\nspecificity and vice versa. This can be illustrated by the following example.<br \/>\nConsider two populations of patients: one has chronic hepatitis as defined by a<br \/>\ngold standard, and the other does not. The diagnostic test being used to<br \/>\nevaluate for chronic hepatitis is the serum alanine aminotransferase (ALT)<br \/>\nconcentration. The sensitivity and specificity of the ALT depends upon the<br \/>\nvalue chosen as a cutoff (<a href=\"http:\/\/uptodateonline.com\/application\/image.asp?file=prim_pix\/interdep.gif\" target=\"side\">show figure 5<\/a>).<\/span><\/p>\n<p><span style=\"font-size: 10pt; font-family: Verdana;\">The interdependence of<br \/>\nsensitivity and specificity can be depicted graphically using a receiver<br \/>\noperating characteristic curve (ROC). The ROC curve plots sensitivity on the Y<br \/>\naxis, and 1-specificity (which is the false positive rate) on the X axis. The<br \/>\narea under the ROC curves gives an estimate of the accuracy of a test. An ideal<br \/>\ntest would have a cutoff value that perfectly discriminated those with disease,<br \/>\nand would have an area under the ROC curve of 1.00 (<a href=\"http:\/\/uptodateonline.com\/application\/image.asp?file=prim_pix\/roc_curv.gif\" target=\"side\">show figure 6<\/a>). The ROC curve can be adapted to multivariate<br \/>\nanalysis (such as logistic regression) in which it provides an estimate of the<br \/>\naccuracy of the statistical model (ie, how well it predicts an outcome).<\/span><\/p>\n<p><strong><span style=\"font-size: 10pt; font-family: Verdana;\">Predictive values<\/span><\/strong><span style=\"font-size: 10pt; font-family: Verdana;\"> &mdash; In addition to sensitivity and<br \/>\nspecificity, the predictive values of a diagnostic test must be considered when<br \/>\ninterpreting the results of a test. The positive predictive value of a test<br \/>\nrepresents the likelihood that a patient with a positive test has the disease.<br \/>\nConversely, the negative predictive value represents the likelihood that a<br \/>\npatient who has a negative test is free of the disease (<a href=\"http:\/\/uptodateonline.com\/application\/image.asp?file=gast_pix\/sensit1.gif\" target=\"side\">show figure 4<\/a>).<\/span><\/p>\n<p><span style=\"font-size: 10pt; font-family: Verdana;\">The predictive values<br \/>\n(and the proportion of positive and negative evaluations that can be expected)<br \/>\ndepend upon the prevalence of a disease within a population. Thus, for given<br \/>\nvalues of sensitivity and specificity, a patient with a positive test is more<br \/>\nlikely to truly have the disease if the patient belongs to a population with a<br \/>\nhigh prevalence of the disease (<a href=\"http:\/\/uptodateonline.com\/application\/image.asp?file=prim_pix\/preval8.gif\" target=\"side\">show figure 7<\/a>). This observation has significant implications<br \/>\nfor screening tests, in which false positive results may lead to expensive and<br \/>\nsometimes dangerous testing, and false negative tests may be associated with<br \/>\nmorbidity or mortality. As an example, a positive stool test for occult blood<br \/>\nis much more likely to predict colon cancer in a seventy year-old compared with<br \/>\na twenty year-old. Thus, routine screening of stools in young patients would<br \/>\nlead to a high rate of subsequent false positive examinations and is not<br \/>\nrecommended. The predictive values of a test should be considered when selecting<br \/>\namong diagnostic tests for an individual patient in whom demographic or other<br \/>\nclinical risk factors influence the likelihood that the disease is present (ie,<br \/>\nthe &#8220;prior probability&#8221; of the disease).<\/span><\/p>\n<p><strong><span style=\"font-size: 10pt; font-family: Verdana;\">Likelihood ratio<\/span><\/strong><span style=\"font-size: 10pt; font-family: Verdana;\"> &mdash; As discussed above, a<br \/>\nlimitation to predictive values as expressions of test characteristics is their<br \/>\ndependence upon disease prevalence. To overcome this limitation, the likelihood<br \/>\nratio has been increasingly used as an expression of the performance of<br \/>\ndiagnostic tests [<a href=\"http:\/\/uptodateonline.com\/application\/abstract.asp?TR=genr_med\/17654&amp;viewAbs=12&amp;title=12\" target=\"side\">12<\/a>]. The likelihood ratio represents a measure of the odds of<br \/>\nhaving a disease relative to the prior probability of the disease. The estimate<br \/>\nis independent of the disease prevalence. A positive likelihood ratio is<br \/>\ncalculated by dividing sensitivity by 1 minus specificity<br \/>\n(sensitivity\/(1-specificity)). Similarly, a negative likelihood ratio is<br \/>\ncalculated by dividing 1 minus sensitivity by specificity ((1-sensitivity)\/specificity).<br \/>\nPositive and negative likelihood ratios of 9 and 0.25, for example, can be<br \/>\ninterpreted as meaning that a positive result is seen 9 times as frequently<br \/>\nwhile a negative test is seen 0.25 times as frequently in those with a specific<br \/>\ncondition than those without it.<\/span><\/p>\n<p><strong><span style=\"font-size: 10pt; font-family: Verdana;\">Accuracy<\/span><\/strong><span style=\"font-size: 10pt; font-family: Verdana;\"> &mdash; The performance of a diagnostic<br \/>\ntest is sometimes expressed as accuracy, which refers to the number of true<br \/>\npositives and true negatives divided by the total number of observations (<a href=\"http:\/\/uptodateonline.com\/application\/image.asp?file=prim_pix\/defini4.gif\" target=\"side\">show figure 8<\/a>). However, accuracy by itself is not a good<br \/>\nindicator of test performance since it obscures important information related<br \/>\nto its component parts.<\/span><\/p>\n<p><strong><span style=\"font-size: 10pt; font-family: Verdana;\">EXPRESSIONS USED WHEN<br \/>\nMAKING INFERENCES ABOUT DATA<\/span><\/strong><span style=\"font-size: 10pt; font-family: Verdana;\"><\/span><\/p>\n<p><strong><span style=\"font-size: 10pt; font-family: Verdana;\">Confidence interval<\/span><\/strong><span style=\"font-size: 10pt; font-family: Verdana;\"> &mdash; A point estimate (ie, a single<br \/>\nvalue) from a sample population may not reflect the &#8220;true&#8221; value from<br \/>\nthe entire population. As a result, it is often helpful to provide a range that<br \/>\nis likely to include the true value. A confidence interval is a commonly used<br \/>\nestimate. The boundaries of a confidence interval give values within which<br \/>\nthere is a high probability (95 percent by convention) that the true population<br \/>\nvalue can be found. The calculation of a confidence interval considers the<br \/>\nstandard deviation of the data and the number of observations. Thus, a<br \/>\nconfidence interval narrows as the number of observations increases, or its<br \/>\nvariance (dispersion) decreases.<\/span><\/p>\n<p><strong><span style=\"font-size: 10pt; font-family: Verdana;\">Errors<\/span><\/strong><span style=\"font-size: 10pt; font-family: Verdana;\"> &mdash; Two potential errors are<br \/>\ncommonly recognized when testing a hypothesis:<\/span><\/p>\n<p class=\"MsoNormal\" style=\"margin-bottom: 12pt;\"><span style=\"font-size: 10pt; font-family: Verdana;\">&nbsp;&nbsp;<!--[if gte vml 1]><v:shape id=\"_x0000_i1042\"\n type=\"#_x0000_t75\" alt=\"bullet\" style='width:4.5pt;height:5.25pt'>\n <v:imagedata src=\".\/stats%26figures_files\/image005.gif\" mce_src=\"\/admin\/page\/edit\/stats%26figures_files\/image005.gif\" o:href=\"http:\/\/uptodateonline.com\/application\/images\/characters\/bull.gif\" \/>\n<\/v:shape><![endif]--><!--[if !vml]--><img loading=\"lazy\" decoding=\"async\" src=\"file:\/\/\/C:\/Documents%20and%20Settings\/LauraKoo\/Desktop\/ambulatory_backup\/mlove\/Practical%20Practice\/Information%20Mastery\/stats&amp;figures_files\/image005.gif\" border=\"0\" alt=\"bullet\" width=\"6\" height=\"7\" \/><!--[endif]-->&nbsp;A<br \/>\ntype I error (also known as alpha) is the probability of incorrectly concluding<br \/>\nthat there is a statistically significant difference in a dataset. Alpha is the<br \/>\nnumber after a p-value. Thus, a statistically significant difference reported<br \/>\nas p&lt;0.05 means that there is less than a 5 percent chance that the<br \/>\ndifference could have occurred by chance.<\/p>\n<p>&nbsp;&nbsp;<!--[if gte vml 1]><v:shape id=\"_x0000_i1043\" type=\"#_x0000_t75\"\n alt=\"bullet\" style='width:4.5pt;height:5.25pt'>\n <v:imagedata src=\".\/stats%26figures_files\/image005.gif\" mce_src=\"\/admin\/page\/edit\/stats%26figures_files\/image005.gif\" o:href=\"http:\/\/uptodateonline.com\/application\/images\/characters\/bull.gif\" \/>\n<\/v:shape><![endif]--><!--[if !vml]--><img loading=\"lazy\" decoding=\"async\" src=\"file:\/\/\/C:\/Documents%20and%20Settings\/LauraKoo\/Desktop\/ambulatory_backup\/mlove\/Practical%20Practice\/Information%20Mastery\/stats&amp;figures_files\/image005.gif\" border=\"0\" alt=\"bullet\" width=\"6\" height=\"7\" \/><!--[endif]-->&nbsp;A<br \/>\ntype II error (also known as beta) is the probability of incorrectly concluding<br \/>\nthat there was no statistically significant difference in a dataset. This error<br \/>\noften reflects insufficient power of the study.<\/span><\/p>\n<p><strong><span style=\"font-size: 10pt; font-family: Verdana;\">Power<\/span><\/strong><span style=\"font-size: 10pt; font-family: Verdana;\"> &mdash; The term &#8220;power&#8221;<br \/>\n(calculated as 1 &#8211; beta) refers to the ability of a study to detect a true<br \/>\ndifference. Negative findings in a study may reflect that the study was<br \/>\nunderpowered to detect a difference. A &#8220;power calculation&#8221; should be<br \/>\nperformed prior to conducting a study to be sure that there are a sufficient<br \/>\nnumber of observations to detect a desired degree of difference. The larger the<br \/>\ndifference, the fewer the number of observations that will be required. As an example,<br \/>\nit takes fewer patients to detect a 50 percent difference in blood pressure<br \/>\nfrom a new antihypertensive medication compared with placebo than a 5 percent<br \/>\ndifference.<\/span><\/p>\n<p><strong><span style=\"font-size: 10pt; font-family: Verdana;\">TERMS USED IN<br \/>\nMULTIVARIATE ANALYSIS<\/span><\/strong><span style=\"font-size: 10pt; font-family: Verdana;\"><br \/>\n&mdash; The effect of more than one variable often needs to be considered when<br \/>\npredicting an outcome. As an example, the effect of smoking status and age<br \/>\nneeds to be simultaneously considered when assessing the risk of lung cancer.<\/span><\/p>\n<p><span style=\"font-size: 10pt; font-family: Verdana;\">Statistical methods that<br \/>\ncan simultaneously account for multiple variables are known as<br \/>\n&#8220;multivariate&#8221; (or multivariable) analysis. Two of the most commonly<br \/>\nencountered are multiple regression and logistic regression.<\/span><\/p>\n<p><strong><span style=\"font-size: 10pt; font-family: Verdana;\">Multiple regression<\/span><\/strong><span style=\"font-size: 10pt; font-family: Verdana;\"> &mdash; Multiple regression is used for<br \/>\nperforming multivariate analysis when the outcome is a continuous variable,<br \/>\nsuch as blood pressure. Thus, for example, a patient&#8217;s systolic blood pressure<br \/>\ncan be predicted from a multivariate model by adding together the appropriately<br \/>\nweighted variables (such as age, gender, diastolic blood pressure, weight, etc).<\/span><\/p>\n<p><strong><span style=\"font-size: 10pt; font-family: Verdana;\">Logistic regression<\/span><\/strong><span style=\"font-size: 10pt; font-family: Verdana;\"> &mdash; Logistic regression is similar<br \/>\nto multiple regression except the outcome is dichotomous (eg, alive or dead, or<br \/>\na complication occurs or does not occur).<\/span><\/p>\n<p><strong><span style=\"font-size: 10pt; font-family: Verdana;\">SURVIVAL ANALYSIS<\/span><\/strong><span style=\"font-size: 10pt; font-family: Verdana;\"> &mdash; Many examples of medical<br \/>\nresearch deal with an event that may or may not occur in a given period of time<br \/>\n(such as death, stroke, myocardial infarction). During the study, several<br \/>\noutcomes are possible in addition to the outcome of interest (eg, patients<br \/>\nmight die of other causes or drop out from the analysis). Furthermore, the<br \/>\nduration of follow-up can vary among individuals in the study. A patient who is<br \/>\nobserved for five years should count more in the statistical analysis than one<br \/>\nobserved for five months.<\/span><\/p>\n<p><span style=\"font-size: 10pt; font-family: Verdana;\">Several methods are<br \/>\navailable to account for these considerations. The most commonly used in<br \/>\nmedical research are Kaplan-Meier and Cox proportional hazards analyses.<\/span><\/p>\n<p><strong><span style=\"font-size: 10pt; font-family: Verdana;\">Kaplan-Meier analysis<\/span><\/strong><span style=\"font-size: 10pt; font-family: Verdana;\"> &mdash; Kaplan-Meier analysis measures<br \/>\nthe ratio of surviving patients (or those free from an outcome) divided by the<br \/>\ntotal number of patients at risk for the outcome. Every time a patient has an<br \/>\noutcome, the ratio is recalculated. Using these calculations, a curve can be<br \/>\ngenerated that graphically depicts the probability of survival (<a href=\"http:\/\/uptodateonline.com\/application\/image.asp?file=prim_pix\/kaplan1.gif\" target=\"side\">show figure 9<\/a>).<\/span><\/p>\n<p><span style=\"font-size: 10pt; font-family: Verdana;\">In many studies, the<br \/>\nbenefit of a drug or intervention on an outcome is compared with a control<br \/>\npopulation, permitting the construction of two or more Kaplan-Meier curves.<br \/>\nCurves that are close together or cross are unlikely to reflect a statistically<br \/>\nsignificant difference. Several formal statistical tests can be used to assess<br \/>\na significant difference. Examples include the log-rank test and the Breslow<br \/>\ntest.<\/span><\/p>\n<p><strong><span style=\"font-size: 10pt; font-family: Verdana;\">Cox proportional<br \/>\nhazards analysis<\/span><\/strong><span style=\"font-size: 10pt; font-family: Verdana;\"><br \/>\n&mdash; Cox proportional hazards analysis is similar to logistic regression because<br \/>\nit can account for many variables that are relevant for predicting a<br \/>\ndichotomous outcome. However, unlike logistic regression, Cox proportional<br \/>\nhazards analysis permits time to be included as a variable, and for patients to<br \/>\nbe counted only for the period of time in which they were observed.<\/span><\/p>\n<p><span style=\"font-size: 10pt; font-family: Verdana;\">The term &#8220;hazard<br \/>\nratio&#8221; is sometimes used when referring to variables included in the<br \/>\nanalysis. A hazard ratio is analogous to an odds ratio. Thus, a hazard ratio of<br \/>\nten means that group of patients exposed to a specific risk factor has ten<br \/>\ntimes the chance of developing the outcome compared with unexposed controls.<\/span><\/p>\n<p class=\"MsoNormal\"><span style=\"font-size: 10pt; font-family: Verdana;\"><!--[if !supportEmptyParas]-->&nbsp;<!--[endif]--><\/span><\/p>\n<p style=\"text-align: center;\" align=\"center\"><span style=\"font-size: 10pt; font-family: Verdana;\">Use of <em>UpToDate<\/em> is subject to the <a href=\"http:\/\/uptodateonline.com\/application\/security\/login\/license.asp\">Subscription<br \/>\nand License Agreement.<\/a><\/span><\/p>\n<p class=\"MsoNormal\" style=\"text-align: center;\" align=\"center\"><strong><span style=\"font-size: 10pt; font-family: Verdana;\">REFERENCES<\/span><\/strong><span style=\"font-size: 10pt; font-family: Verdana;\"><\/span><\/p>\n<table style=\"width: 100%;\" border=\"0\" cellpadding=\"0\">\n<tbody>\n<tr>\n<td style=\"padding: 0.75pt; background: #eeeeee none repeat scroll 0% 0%;\">\n<p class=\"MsoNormal\"><span style=\"font-size: 10pt; font-family: Verdana;\">1.<br \/>\n  &nbsp;Dawson-Saunders, B, Trapp, RG. Basic Clinical Biostatistics, 2nd ed,<br \/>\n  Appleton Lange, Connecticut 1994.<\/span><span style=\"font-family: &quot;Arial Unicode MS&quot;;\"><\/span><\/p>\n<\/td>\n<\/tr>\n<tr>\n<td style=\"padding: 0.75pt; background: white none repeat scroll 0% 0%;\">\n<p class=\"MsoNormal\"><span style=\"font-size: 10pt; font-family: Verdana;\">2.<br \/>\n  &nbsp;Shott, S. Statistics for Health Professionals, WB Saunders,<br \/>\n  Philadelphia 1990.<\/span><span style=\"font-family: &quot;Arial Unicode MS&quot;;\"><\/span><\/p>\n<\/td>\n<\/tr>\n<tr>\n<td style=\"padding: 0.75pt; background: #eeeeee none repeat scroll 0% 0%;\">\n<p class=\"MsoNormal\"><span style=\"font-size: 10pt; font-family: Verdana;\">3.<br \/>\n  &nbsp;Hulley, SB, Cummings, SR. Designing Clinical Research. Williams<br \/>\n  Wilkins, Baltimore 1988.<\/span><span style=\"font-family: &quot;Arial Unicode MS&quot;;\"><\/span><\/p>\n<\/td>\n<\/tr>\n<tr>\n<td style=\"padding: 0.75pt; background: white none repeat scroll 0% 0%;\">\n<p class=\"MsoNormal\"><span style=\"font-size: 10pt; font-family: Verdana;\">4.<br \/>\n  &nbsp;Henneckens, CH, Buring, JE. Epidemiology in Medicine, Little Brown,<br \/>\n  Boston 1987.<\/span><span style=\"font-family: &quot;Arial Unicode MS&quot;;\"><\/span><\/p>\n<\/td>\n<\/tr>\n<tr>\n<td style=\"padding: 0.75pt; background: #eeeeee none repeat scroll 0% 0%;\">\n<p class=\"MsoNormal\"><span style=\"font-size: 10pt; font-family: Verdana;\">5.<br \/>\n  &nbsp;Fletcher, RH, Fletcher, SW, Wagner, EH. Clinical Epidemiology: The<br \/>\n  Essentials, 2nd ed, Williams Wilkins, Baltimore 1988.<\/span><span style=\"font-family: &quot;Arial Unicode MS&quot;;\"><\/span><\/p>\n<\/td>\n<\/tr>\n<tr>\n<td style=\"padding: 0.75pt; background: white none repeat scroll 0% 0%;\">\n<p class=\"MsoNormal\"><span style=\"font-size: 10pt; font-family: Verdana;\">6.<br \/>\n  &nbsp;Kleinbaum, DG. Logistic Regression, A Self-Learning Text, Springer-Verlag,<br \/>\n  New York 1994.<\/span><span style=\"font-family: &quot;Arial Unicode MS&quot;;\"><\/span><\/p>\n<\/td>\n<\/tr>\n<tr>\n<td style=\"padding: 0.75pt; background: #eeeeee none repeat scroll 0% 0%;\">\n<p class=\"MsoNormal\"><span style=\"font-size: 10pt; font-family: Verdana;\">7.<br \/>\n  &nbsp;Kleinbaum, DG. Survival analysis. A Self-Learning Text,<br \/>\n  Springer-Verlag, New York 1996.<\/span><span style=\"font-family: &quot;Arial Unicode MS&quot;;\"><\/span><\/p>\n<\/td>\n<\/tr>\n<tr>\n<td style=\"padding: 0.75pt; background: white none repeat scroll 0% 0%;\">\n<p class=\"MsoNormal\"><span style=\"font-size: 10pt; font-family: Verdana;\">8.<br \/>\n  &nbsp;Hopkins, WG. A new view of statistics. Internet Society for Sport<br \/>\n  Science 2000 (http:\/\/www.sportsci.org\/resource\/stats\/index.html).<\/span><span style=\"font-family: &quot;Arial Unicode MS&quot;;\"><\/span><\/p>\n<\/td>\n<\/tr>\n<tr>\n<td style=\"padding: 0.75pt; background: #eeeeee none repeat scroll 0% 0%;\">\n<p class=\"MsoNormal\"><span style=\"font-size: 10pt; font-family: Verdana;\"><a href=\"http:\/\/uptodateonline.com\/application\/abstract.asp?TR=genr_med\/17654&amp;viewAbs=9&amp;title=9\" target=\"side\">9.<\/a> &nbsp;Moriarty, PM. Relative risk reduction versus number<br \/>\n  needed to treat as measures of lipid-lowering trial results (editorial). Am J<br \/>\n  Cardiol 1998; 82:505.<\/span><span style=\"font-family: &quot;Arial Unicode MS&quot;;\"><\/span><\/p>\n<\/td>\n<\/tr>\n<tr>\n<td style=\"padding: 0.75pt; background: white none repeat scroll 0% 0%;\">\n<p class=\"MsoNormal\"><span style=\"font-size: 10pt; font-family: Verdana;\"><a href=\"http:\/\/uptodateonline.com\/application\/abstract.asp?TR=genr_med\/17654&amp;viewAbs=10&amp;title=10\" target=\"side\">10.<\/a> &nbsp;Lubsden, J, Hoes, A, Grobbee, D. Implications of<br \/>\n  trial results: The potentially misleading notions of number needed to treat<br \/>\n  and average duration of life gained. Lancet 2000; 356:1757.<\/span><span style=\"font-family: &quot;Arial Unicode MS&quot;;\"><\/span><\/p>\n<\/td>\n<\/tr>\n<tr>\n<td style=\"padding: 0.75pt; background: #eeeeee none repeat scroll 0% 0%;\">\n<p class=\"MsoNormal\"><span style=\"font-size: 10pt; font-family: Verdana;\"><a href=\"http:\/\/uptodateonline.com\/application\/abstract.asp?TR=genr_med\/17654&amp;viewAbs=11&amp;title=11\" target=\"side\">11.<\/a> &nbsp;de Craen, AJ, Vickers, AJ, Tijssen, JGP, Kleijnen,<br \/>\n  J. Number needed to treat and placebo controlled trials [see comments].<br \/>\n  Lancet 1998; 351:310.<\/span><span style=\"font-family: &quot;Arial Unicode MS&quot;;\"><\/span><\/p>\n<\/td>\n<\/tr>\n<tr>\n<td style=\"padding: 0.75pt; background: white none repeat scroll 0% 0%;\">\n<p class=\"MsoNormal\"><span style=\"font-size: 10pt; font-family: Verdana;\"><a href=\"http:\/\/uptodateonline.com\/application\/abstract.asp?TR=genr_med\/17654&amp;viewAbs=12&amp;title=12\" target=\"side\">12.<\/a> &nbsp;Weissler, AM. A perspective on standardizing the<br \/>\n  predictive power of noninvasive cardiovascular tests by likelihood ratio<br \/>\n  computation: 1. Mathematical principles. Mayo Clin Proc 1999; 74:1061.<\/span><span style=\"font-family: &quot;Arial Unicode MS&quot;;\"><\/span><\/p>\n<\/td>\n<\/tr>\n<\/tbody>\n<\/table>\n<p class=\"MsoNormal\"><span style=\"font-size: 7.5pt; font-family: Verdana; display: none;\"><!--[if !supportEmptyParas]-->&nbsp;<!--[endif]--><\/span><\/p>\n<table style=\"width: 100%;\" border=\"0\" cellspacing=\"1\" cellpadding=\"0\">\n<tbody>\n<tr style=\"height: 7.5pt;\">\n<td style=\"padding: 0in; height: 7.5pt;\">\n<p class=\"MsoNormal\"><!--[if !supportEmptyParas]-->&nbsp;<!--[endif]--><span style=\"font-size: 8pt; font-family: &quot;Arial Unicode MS&quot;;\"><\/span><\/p>\n<\/td>\n<\/tr>\n<tr>\n<td style=\"padding: 0in;\">\n<p class=\"MsoNormal\" style=\"text-align: center;\" align=\"center\"><strong><span style=\"font-size: 10pt; font-family: Verdana;\">GRAPHICS<\/span><\/strong><strong><span style=\"font-size: 10pt; font-family: Verdana;\"><\/span><\/strong><\/p>\n<\/td>\n<\/tr>\n<tr>\n<td style=\"padding: 0.75pt;\">\n<div>\n<table border=\"0\" cellspacing=\"3\" cellpadding=\"0\">\n<tbody>\n<tr>\n<td style=\"padding: 2.25pt; background: #eeeeee none repeat scroll 0% 0%;\"><span style=\"font-size: 7.5pt; font-family: Verdana;\"><br style=\"page-break-before: always;\" \/><br \/>\n    <\/span><\/p>\n<p class=\"MsoNormal\"><span style=\"font-family: Verdana;\"><!--[if gte vml 1]><v:shape\n     id=\"_x0000_i1044\" type=\"#_x0000_t75\" alt=\"\" style='width:389.25pt;\n     height:231pt'>\n     <v:imagedata src=\".\/stats%26figures_files\/image006.gif\" mce_src=\"\/admin\/page\/edit\/stats%26figures_files\/image006.gif\" o:href=\"http:\/\/uptodateonline.com\/data\/images\/prim_pix\/box_and_.gif\" \/>\n    <\/v:shape><![endif]--><!--[if !vml]--><img loading=\"lazy\" decoding=\"async\" src=\"\/public\/images\/ambulatory_content\/image006.gif\" border=\"0\" alt=\"\/public\/images\/ambulatory_content\/image006.gif\" title=\"\/public\/images\/ambulatory_content\/image006.gif\" width=\"519\" height=\"308\" style=\"border: 0pt none;\" \/><!--[endif]--><\/span><span style=\"font-family: &quot;Arial Unicode MS&quot;;\"><\/span><\/p>\n<\/td>\n<\/tr>\n<\/tbody>\n<\/table>\n<\/div>\n<p class=\"MsoNormal\" style=\"text-align: center;\" align=\"center\"><span style=\"font-family: &quot;Arial Unicode MS&quot;;\"><\/span><\/p>\n<\/td>\n<\/tr>\n<tr>\n<td style=\"padding: 0.75pt;\">\n<div>\n<table border=\"0\" cellspacing=\"3\" cellpadding=\"0\">\n<tbody>\n<tr>\n<td style=\"padding: 2.25pt; background: #eeeeee none repeat scroll 0% 0%;\"><span style=\"font-size: 7.5pt; font-family: Verdana;\"><br style=\"page-break-before: always;\" \/><br \/>\n    <\/span><\/p>\n<p class=\"MsoNormal\"><span style=\"font-family: Verdana;\"><!--[if gte vml 1]><v:shape\n     id=\"_x0000_i1045\" type=\"#_x0000_t75\" alt=\"\" style='width:404.25pt;\n     height:309pt'>\n     <v:imagedata src=\".\/stats%26figures_files\/image007.gif\" mce_src=\"\/admin\/page\/edit\/stats%26figures_files\/image007.gif\" o:href=\"http:\/\/uptodateonline.com\/data\/images\/prim_pix\/relative.gif\" \/>\n    <\/v:shape><![endif]--><!--[if !vml]--><img loading=\"lazy\" decoding=\"async\" src=\"\/public\/images\/ambulatory_content\/image007.gif\" border=\"0\" alt=\"\/public\/images\/ambulatory_content\/image007.gif\" title=\"\/public\/images\/ambulatory_content\/image007.gif\" width=\"539\" height=\"412\" style=\"border: 0pt none;\" \/><!--[endif]--><\/span><span style=\"font-family: &quot;Arial Unicode MS&quot;;\"><\/span><\/p>\n<\/td>\n<\/tr>\n<\/tbody>\n<\/table>\n<\/div>\n<p class=\"MsoNormal\" style=\"text-align: center;\" align=\"center\"><span style=\"font-family: &quot;Arial Unicode MS&quot;;\"><\/span><\/p>\n<\/td>\n<\/tr>\n<tr>\n<td style=\"padding: 0.75pt;\">\n<div>\n<table border=\"0\" cellspacing=\"3\" cellpadding=\"0\">\n<tbody>\n<tr>\n<td style=\"padding: 2.25pt; background: #eeeeee none repeat scroll 0% 0%;\"><span style=\"font-size: 7.5pt; font-family: Verdana;\"><br style=\"page-break-before: always;\" \/><br \/>\n    <\/span><\/p>\n<p class=\"MsoNormal\"><span style=\"font-family: Verdana;\"><!--[if gte vml 1]><v:shape\n     id=\"_x0000_i1046\" type=\"#_x0000_t75\" alt=\"\" style='width:398.25pt;\n     height:259.5pt'>\n     <v:imagedata src=\".\/stats%26figures_files\/image008.gif\" mce_src=\"\/admin\/page\/edit\/stats%26figures_files\/image008.gif\" o:href=\"http:\/\/uptodateonline.com\/data\/images\/prim_pix\/number_n.gif\" \/>\n    <\/v:shape><![endif]--><!--[if !vml]--><img loading=\"lazy\" decoding=\"async\" src=\"\/public\/images\/ambulatory_content\/image008.gif\" border=\"0\" alt=\"\/public\/images\/ambulatory_content\/image008.gif\" title=\"\/public\/images\/ambulatory_content\/image008.gif\" width=\"531\" height=\"346\" style=\"border: 0pt none;\" \/><!--[endif]--><\/span><span style=\"font-family: &quot;Arial Unicode MS&quot;;\"><\/span><\/p>\n<\/td>\n<\/tr>\n<\/tbody>\n<\/table>\n<\/div>\n<p class=\"MsoNormal\" style=\"text-align: center;\" align=\"center\"><span style=\"font-family: &quot;Arial Unicode MS&quot;;\"><\/span><\/p>\n<\/td>\n<\/tr>\n<tr>\n<td style=\"padding: 0.75pt;\">\n<div>\n<table border=\"0\" cellspacing=\"3\" cellpadding=\"0\">\n<tbody>\n<tr>\n<td style=\"padding: 2.25pt; background: #eeeeee none repeat scroll 0% 0%;\"><span style=\"font-size: 7.5pt; font-family: Verdana;\"><br style=\"page-break-before: always;\" \/><br \/>\n    <\/span><\/p>\n<p class=\"MsoNormal\"><span style=\"font-family: Verdana;\"><!--[if gte vml 1]><v:shape\n     id=\"_x0000_i1047\" type=\"#_x0000_t75\" alt=\"\" style='width:323.25pt;\n     height:190.5pt'>\n     <v:imagedata src=\".\/stats%26figures_files\/image009.gif\" mce_src=\"\/admin\/page\/edit\/stats%26figures_files\/image009.gif\" o:href=\"http:\/\/uptodateonline.com\/data\/images\/gast_pix\/sensit1.gif\" \/>\n    <\/v:shape><![endif]--><!--[if !vml]--><img loading=\"lazy\" decoding=\"async\" src=\"\/public\/images\/ambulatory_content\/image009.gif\" border=\"0\" alt=\"\/public\/images\/ambulatory_content\/image009.gif\" title=\"\/public\/images\/ambulatory_content\/image009.gif\" width=\"431\" height=\"254\" style=\"border: 0pt none;\" \/><!--[endif]--><\/span><span style=\"font-family: &quot;Arial Unicode MS&quot;;\"><\/span><\/p>\n<\/td>\n<\/tr>\n<\/tbody>\n<\/table>\n<\/div>\n<p class=\"MsoNormal\" style=\"text-align: center;\" align=\"center\"><span style=\"font-family: &quot;Arial Unicode MS&quot;;\"><\/span><\/p>\n<\/td>\n<\/tr>\n<tr>\n<td style=\"padding: 0.75pt;\">\n<div>\n<table border=\"0\" cellspacing=\"3\" cellpadding=\"0\">\n<tbody>\n<tr>\n<td style=\"padding: 2.25pt; background: #eeeeee none repeat scroll 0% 0%;\"><span style=\"font-size: 7.5pt; font-family: Verdana;\"><br style=\"page-break-before: always;\" \/><br \/>\n    <\/span><\/p>\n<p class=\"MsoNormal\"><span style=\"font-family: Verdana;\"><!--[if gte vml 1]><v:shape\n     id=\"_x0000_i1048\" type=\"#_x0000_t75\" alt=\"\" style='width:384.75pt;\n     height:303pt'>\n     <v:imagedata src=\".\/stats%26figures_files\/image010.gif\" mce_src=\"\/admin\/page\/edit\/stats%26figures_files\/image010.gif\" o:href=\"http:\/\/uptodateonline.com\/data\/images\/prim_pix\/interdep.gif\" \/>\n    <\/v:shape><![endif]--><!--[if !vml]--><img loading=\"lazy\" decoding=\"async\" src=\"\/public\/images\/ambulatory_content\/image010.gif\" border=\"0\" alt=\"\/public\/images\/ambulatory_content\/image010.gif\" title=\"\/public\/images\/ambulatory_content\/image010.gif\" width=\"513\" height=\"404\" style=\"border: 0pt none;\" \/><!--[endif]--><\/span><span style=\"font-family: &quot;Arial Unicode MS&quot;;\"><\/span><\/p>\n<\/td>\n<\/tr>\n<\/tbody>\n<\/table>\n<\/div>\n<p class=\"MsoNormal\" style=\"text-align: center;\" align=\"center\"><span style=\"font-family: &quot;Arial Unicode MS&quot;;\"><\/span><\/p>\n<\/td>\n<\/tr>\n<tr>\n<td style=\"padding: 0.75pt;\">\n<div>\n<table border=\"0\" cellspacing=\"3\" cellpadding=\"0\">\n<tbody>\n<tr>\n<td style=\"padding: 2.25pt; background: #eeeeee none repeat scroll 0% 0%;\"><span style=\"font-size: 7.5pt; font-family: Verdana;\"><br style=\"page-break-before: always;\" \/><br \/>\n    <\/span><\/p>\n<p class=\"MsoNormal\"><span style=\"font-family: Verdana;\"><!--[if gte vml 1]><v:shape\n     id=\"_x0000_i1049\" type=\"#_x0000_t75\" alt=\"\" style='width:389.25pt;\n     height:369.75pt'>\n     <v:imagedata src=\".\/stats%26figures_files\/image011.gif\" mce_src=\"\/admin\/page\/edit\/stats%26figures_files\/image011.gif\" o:href=\"http:\/\/uptodateonline.com\/data\/images\/prim_pix\/roc_curv.gif\" \/>\n    <\/v:shape><![endif]--><!--[if !vml]--><img loading=\"lazy\" decoding=\"async\" src=\"\/public\/images\/ambulatory_content\/image011.gif\" border=\"0\" alt=\"\/public\/images\/ambulatory_content\/image011.gif\" title=\"\/public\/images\/ambulatory_content\/image011.gif\" width=\"519\" height=\"493\" style=\"border: 0pt none;\" \/><!--[endif]--><\/span><span style=\"font-family: &quot;Arial Unicode MS&quot;;\"><\/span><\/p>\n<\/td>\n<\/tr>\n<\/tbody>\n<\/table>\n<\/div>\n<p class=\"MsoNormal\" style=\"text-align: center;\" align=\"center\"><span style=\"font-family: &quot;Arial Unicode MS&quot;;\"><\/span><\/p>\n<\/td>\n<\/tr>\n<tr>\n<td style=\"padding: 0.75pt;\">\n<div>\n<table border=\"0\" cellspacing=\"3\" cellpadding=\"0\">\n<tbody>\n<tr>\n<td style=\"padding: 2.25pt; background: #eeeeee none repeat scroll 0% 0%;\"><span style=\"font-size: 7.5pt; font-family: Verdana;\"><br style=\"page-break-before: always;\" \/><br \/>\n    <\/span><\/p>\n<p class=\"MsoNormal\"><span style=\"font-family: Verdana;\"><!--[if gte vml 1]><v:shape\n     id=\"_x0000_i1050\" type=\"#_x0000_t75\" alt=\"\" style='width:363pt;height:330pt'>\n     <v:imagedata src=\".\/stats%26figures_files\/image012.gif\" mce_src=\"\/admin\/page\/edit\/stats%26figures_files\/image012.gif\" o:href=\"http:\/\/uptodateonline.com\/data\/images\/prim_pix\/preval8.gif\" \/>\n    <\/v:shape><![endif]--><!--[if !vml]--><img loading=\"lazy\" decoding=\"async\" src=\"\/public\/images\/ambulatory_content\/image012.gif\" border=\"0\" alt=\"\/public\/images\/ambulatory_content\/image012.gif\" title=\"\/public\/images\/ambulatory_content\/image012.gif\" width=\"484\" height=\"440\" style=\"border: 0pt none;\" \/><!--[endif]--><\/span><span style=\"font-family: &quot;Arial Unicode MS&quot;;\"><\/span><\/p>\n<\/td>\n<\/tr>\n<\/tbody>\n<\/table>\n<\/div>\n<p class=\"MsoNormal\" style=\"text-align: center;\" align=\"center\"><span style=\"font-family: &quot;Arial Unicode MS&quot;;\"><\/span><\/p>\n<\/td>\n<\/tr>\n<tr>\n<td style=\"padding: 0.75pt;\">\n<div>\n<table border=\"0\" cellspacing=\"3\" cellpadding=\"0\">\n<tbody>\n<tr>\n<td style=\"padding: 2.25pt; background: #eeeeee none repeat scroll 0% 0%;\"><span style=\"font-size: 7.5pt; font-family: Verdana;\"><br style=\"page-break-before: always;\" \/><br \/>\n    <\/span><\/p>\n<p class=\"MsoNormal\"><span style=\"font-family: Verdana;\"><!--[if gte vml 1]><v:shape\n     id=\"_x0000_i1051\" type=\"#_x0000_t75\" alt=\"\" style='width:315pt;height:181.5pt'>\n     <v:imagedata src=\".\/stats%26figures_files\/image013.gif\" mce_src=\"\/admin\/page\/edit\/stats%26figures_files\/image013.gif\" o:href=\"http:\/\/uptodateonline.com\/data\/images\/prim_pix\/defini4.gif\" \/>\n    <\/v:shape><![endif]--><!--[if !vml]--><img loading=\"lazy\" decoding=\"async\" src=\"\/public\/images\/ambulatory_content\/image013.gif\" border=\"0\" alt=\"\/public\/images\/ambulatory_content\/image013.gif\" title=\"\/public\/images\/ambulatory_content\/image013.gif\" width=\"420\" height=\"242\" style=\"border: 0pt none;\" \/><!--[endif]--><\/span><span style=\"font-family: &quot;Arial Unicode MS&quot;;\"><\/span><\/p>\n<\/td>\n<\/tr>\n<\/tbody>\n<\/table>\n<\/div>\n<p class=\"MsoNormal\" style=\"text-align: center;\" align=\"center\"><span style=\"font-family: &quot;Arial Unicode MS&quot;;\"><\/span><\/p>\n<\/td>\n<\/tr>\n<tr>\n<td style=\"padding: 0.75pt;\">\n<div>\n<table border=\"0\" cellspacing=\"3\" cellpadding=\"0\">\n<tbody>\n<tr>\n<td style=\"padding: 2.25pt; background: #eeeeee none repeat scroll 0% 0%;\"><span style=\"font-size: 7.5pt; font-family: Verdana;\"><br style=\"page-break-before: always;\" \/><br \/>\n    <\/span><\/p>\n<p class=\"MsoNormal\"><span style=\"font-family: Verdana;\"><!--[if gte vml 1]><v:shape\n     id=\"_x0000_i1052\" type=\"#_x0000_t75\" alt=\"\" style='width:401.25pt;\n     height:297.75pt'>\n     <v:imagedata src=\".\/stats%26figures_files\/image014.gif\" mce_src=\"\/admin\/page\/edit\/stats%26figures_files\/image014.gif\" o:href=\"http:\/\/uptodateonline.com\/data\/images\/prim_pix\/kaplan1.gif\" \/>\n    <\/v:shape><![endif]--><!--[if !vml]--><img loading=\"lazy\" decoding=\"async\" src=\"\/public\/images\/ambulatory_content\/image014.gif\" border=\"0\" alt=\"\/public\/images\/ambulatory_content\/image014.gif\" title=\"\/public\/images\/ambulatory_content\/image014.gif\" width=\"535\" height=\"397\" style=\"border: 0pt none;\" \/><!--[endif]--><\/span><span style=\"font-family: &quot;Arial Unicode MS&quot;;\"><\/span><\/p>\n<\/td>\n<\/tr>\n<\/tbody>\n<\/table>\n<\/div>\n<p class=\"MsoNormal\" style=\"text-align: center;\" align=\"center\"><span style=\"font-family: &quot;Arial Unicode MS&quot;;\"><\/span><\/p>\n<\/td>\n<\/tr>\n<tr>\n<td style=\"padding: 0.75pt;\">\n<p class=\"MsoNormal\"><!--[if !supportEmptyParas]-->&nbsp;<!--[endif]--><span style=\"font-family: &quot;Arial Unicode MS&quot;;\"><\/span><\/p>\n<\/td>\n<\/tr>\n<tr>\n<td style=\"padding: 1.5pt; background: black none repeat scroll 0% 0%;\">\n<table style=\"background: black none repeat scroll 0% 0%; width: 100%;\" border=\"0\" cellspacing=\"0\" cellpadding=\"0\" bgcolor=\"black\">\n<tbody>\n<tr>\n<td style=\"padding: 2.25pt; width: 8%;\" width=\"8%\">\n<p class=\"MsoNormal\" style=\"text-align: center;\" align=\"center\"><span style=\"font-size: 7.5pt; font-family: Verdana;\"><br \/>\n<script type=\"text\/javascript\"><!--\nfunction openSurvey(){\n\n\n\nif (''=='True'){\n\n\tif(navigator.userAgent.indexOf('Mac') != -1){\n\n\twindow.open('..\/feedback\/surveyapp\/liveSurvey.asp?link=1','Survey','height=555,width=500,location=no,directories=no,status=yes,menubar=no,scrollbars=yes,resizable=yes');\n\n   \treturn true;\n\n\t}\n\n}\n\nelse{\n\n   window.open('..\/feedback\/surveyapp\/liveSurvey.asp?link=1','Survey','height=555,width=500,location=no,directories=no,status=yes,menubar=no,scrollbars=yes,resizable=yes');\n\n   return true;\n\n}\n\n}\n\n\n\nfunction openFeedback()\n\n{\n\n\twindow.open('..\/..\/..\/application\/feedback\/letters\/writeFeedback.asp','feedback','height=450,width=410,toolbar=no,location=no,directories=no,status=yes,menubar=no,scrollbars=yes,resizable=yes')\n\n\treturn false;\n\n}\n\/\/ --><\/script><br \/>\n<\/span><strong><span style=\"font-size: 10pt; font-family: Verdana;\"><a href=\"http:\/\/uptodateonline.com\/application\/search.asp\"><!-- Search button --><span style=\"color: white;\">New Search<\/span><\/a><\/span><\/strong><span style=\"font-family: &quot;Arial Unicode MS&quot;;\"><\/span><\/p>\n<\/td>\n<p><!--Peds Feedback Button --><!-- TOC button --><\/p>\n<td style=\"padding: 2.25pt; width: 14%;\" width=\"14%\">\n<p class=\"MsoNormal\" style=\"text-align: center;\" align=\"center\"><strong><span style=\"font-size: 10pt; font-family: Verdana;\"><a href=\"http:\/\/uptodateonline.com\/application\/toc.asp\"><span style=\"color: white;\">Table of Contents<\/span><\/a><\/span><\/strong><span style=\"font-family: &quot;Arial Unicode MS&quot;;\"><\/span><\/p>\n<\/td>\n<p><!-- My UpToDate button --><!-- Feedback button --><\/p>\n<td style=\"padding: 2.25pt; width: 10%;\" width=\"10%\">\n<p class=\"MsoNormal\" style=\"text-align: center;\" align=\"center\"><strong><span style=\"text-decoration: underline;\"><span style=\"font-size: 10pt; font-family: Verdana; color: white;\"><a href=\"http:\/\/uptodateonline.com\/application\/topic\/print.asp?file=genr_med\/feedback\/letters\/writeFeedback.asp\" onclick=\"return openFeedback();\"><span style=\"color: white;\">Feedback<\/span><\/a><\/span><\/span><\/strong><span style=\"font-family: &quot;Arial Unicode MS&quot;;\"><\/span><\/p>\n<\/td>\n<p><!-- Help button --><\/p>\n<td style=\"padding: 2.25pt; width: 4%;\" width=\"4%\">\n<p class=\"MsoNormal\" style=\"text-align: center;\" align=\"center\"><strong><span style=\"font-size: 10pt; font-family: Verdana;\"><a href=\"http:\/\/uptodateonline.com\/application\/help.asp\"><span style=\"color: white;\">Help<\/span><\/a><\/span><\/strong><span style=\"font-family: &quot;Arial Unicode MS&quot;;\"><\/span><\/p>\n<\/td>\n<p><!-- Purchase Now button --><\/p>\n<\/tr>\n<\/tbody>\n<\/table>\n<p class=\"MsoNormal\"><span style=\"font-family: &quot;Arial Unicode MS&quot;;\"><\/span><\/p>\n<\/td>\n<\/tr>\n<\/tbody>\n<\/table>\n<p class=\"MsoNormal\" style=\"text-align: center;\" align=\"center\"><span style=\"font-size: 10pt; font-family: Verdana;\">&copy;2005 UpToDate<sup>&reg;<\/sup><br \/>\n&bull; <a href=\"http:\/\/www.uptodate.com\/\"><span style=\"color: black;\">www.uptodate.com<\/span><\/a><br \/>\n&bull; <a href=\"mailto:customerservice@uptodate.com\"><span style=\"color: black;\">customerservice@uptodate.com<\/span><\/a><br \/>\n<\/span><span style=\"font-family: Verdana;\"><\/span><\/p>\n<p class=\"MsoNormal\" style=\"text-align: justify;\"><span style=\"font-size: 14pt;\"><!--[if !supportEmptyParas]-->&nbsp;<!--[endif]--><\/span><\/p>\n<p class=\"MsoNormal\" style=\"text-align: center;\" align=\"center\"><span style=\"font-size: 26pt; color: #cc66ff;\"><!--[if !supportEmptyParas]-->&nbsp;<!--[endif]--><\/span><\/p>\n<\/div>\n","protected":false},"excerpt":{"rendered":"<p>&nbsp; AMBULATORY BLOCK WINTER\/SPRING 2005 &nbsp; PRACTICAL PRACTICE OF MEDICINE &nbsp; STATS &amp; FIGURES &nbsp; &nbsp; 1.&nbsp;&nbsp;&nbsp;&nbsp; UpToDate Glossary of common biostatistical and epidemiological terms &nbsp; &nbsp; ONLINE 12.3 &copy;2005 UpToDate&reg; New Search Table of Contents Feedback Help &nbsp; Official reprint from UpToDate&reg; www.uptodate.com &nbsp; Glossary of common biostatistical and epidemiological terms Peter A L&#8230;.<\/p>\n","protected":false},"author":1,"featured_media":0,"parent":882,"menu_order":0,"comment_status":"open","ping_status":"open","template":"","meta":{"_bbp_topic_count":0,"_bbp_reply_count":0,"_bbp_total_topic_count":0,"_bbp_total_reply_count":0,"_bbp_voice_count":0,"_bbp_anonymous_reply_count":0,"_bbp_topic_count_hidden":0,"_bbp_reply_count_hidden":0,"_bbp_forum_subforum_count":0,"footnotes":""},"class_list":["post-886","page","type-page","status-publish","hentry"],"_links":{"self":[{"href":"https:\/\/jacobimed.org\/old\/wp-json\/wp\/v2\/pages\/886","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/jacobimed.org\/old\/wp-json\/wp\/v2\/pages"}],"about":[{"href":"https:\/\/jacobimed.org\/old\/wp-json\/wp\/v2\/types\/page"}],"author":[{"embeddable":true,"href":"https:\/\/jacobimed.org\/old\/wp-json\/wp\/v2\/users\/1"}],"replies":[{"embeddable":true,"href":"https:\/\/jacobimed.org\/old\/wp-json\/wp\/v2\/comments?post=886"}],"version-history":[{"count":1,"href":"https:\/\/jacobimed.org\/old\/wp-json\/wp\/v2\/pages\/886\/revisions"}],"predecessor-version":[{"id":890,"href":"https:\/\/jacobimed.org\/old\/wp-json\/wp\/v2\/pages\/886\/revisions\/890"}],"up":[{"embeddable":true,"href":"https:\/\/jacobimed.org\/old\/wp-json\/wp\/v2\/pages\/882"}],"wp:attachment":[{"href":"https:\/\/jacobimed.org\/old\/wp-json\/wp\/v2\/media?parent=886"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}