{"id":285,"date":"2015-09-28T17:52:46","date_gmt":"2015-09-28T23:52:46","guid":{"rendered":"https:\/\/www.ometrics.com\/blog\/?p=285"},"modified":"2019-05-28T12:17:50","modified_gmt":"2019-05-28T18:17:50","slug":"dont-be-tricked-with-false-positives-when-a-b-testing","status":"publish","type":"post","link":"https:\/\/www.ometrics.com\/blog\/dont-be-tricked-with-false-positives-when-a-b-testing\/","title":{"rendered":"Don\u2019t Be Tricked With False Positives When A-B Testing"},"content":{"rendered":"<p>Often when running conversion rate optimization A\/B\u00a0testing (split testing)\u00a0the tests\u00a0are\u00a0concluded too early even though the results are showing a statistically accurate result. To avoid this false positive a general understanding of the life of a test and what can affect it is required.<\/p>\n<p><!--more--><\/p>\n<h2>Why does my A\/B test\u00a0look great then start dropping in lift.<\/h2>\n<p>This often happens when you are adding a new test to a currently running control. For example you are testing two variations and you stop both and add a new one combining the two. When you start the test the number of visitors is low (denominator) therefore the fraction is a higher. <a href=\"https:\/\/www.ometrics.com\/blog\/wp-content\/uploads\/2015\/09\/early-results-table.jpg\"><img loading=\"lazy\" decoding=\"async\" class=\"aligncenter size-full wp-image-286\" src=\"https:\/\/www.ometrics.com\/blog\/wp-content\/uploads\/2015\/09\/early-results-table.jpg\" alt=\"a-b test conversion early results table\" width=\"392\" height=\"87\" srcset=\"https:\/\/www.ometrics.com\/blog\/wp-content\/uploads\/2015\/09\/early-results-table.jpg 392w, https:\/\/www.ometrics.com\/blog\/wp-content\/uploads\/2015\/09\/early-results-table-300x66.jpg 300w\" sizes=\"(max-width: 392px) 100vw, 392px\" \/><\/a> The conversion rate in the beginning of a good test is always high because the denominator is low. Once you give it time it dampens out and will become more accurate. As you can see the pink variation has a big spike then levels off toward the light orange (control) conversion rate. This is why we want to run a test for at least a week. <a href=\"https:\/\/www.ometrics.com\/blog\/wp-content\/uploads\/2015\/09\/3-varients-a-b-testa.jpg\"><img loading=\"lazy\" decoding=\"async\" class=\"aligncenter size-full wp-image-287\" src=\"https:\/\/www.ometrics.com\/blog\/wp-content\/uploads\/2015\/09\/3-varients-a-b-testa.jpg\" alt=\"conversion rate optimization spikes\" width=\"620\" height=\"240\" srcset=\"https:\/\/www.ometrics.com\/blog\/wp-content\/uploads\/2015\/09\/3-varients-a-b-testa.jpg 620w, https:\/\/www.ometrics.com\/blog\/wp-content\/uploads\/2015\/09\/3-varients-a-b-testa-300x116.jpg 300w\" sizes=\"(max-width: 620px) 100vw, 620px\" \/><\/a> The other reasons for running a test for at least a week is the type of traffic can fluctuate over time. The causes of this are due to the following:<\/p>\n<ul>\n<li><strong>User types<\/strong> &#8211; weekend users, weekday morning and afternoon users. For example a business user may convert differently on weekdays than weekends.<\/li>\n<li><strong>Traffic and ad fluctuations<\/strong> &#8211; ad placement changes over the week by Facebook, Google and Bing. Unfortunately we cannot control when an ad is shown and where as much as we would like. It is not unusual to have a spike of ad traffic from a source that may have different quality or user type. The test has to run long enough to capture all user types.<\/li>\n<li><strong>Device anomalies<\/strong> &#8211; Some tests need time to collect enough data to analyze desktop vs mobile variations. Mobile users are using\u00a0the phone on\u00a0different days and times of the day.<\/li>\n<\/ul>\n<p>Because of these reasons a test should run at least a week even if the test is statistically showing a positive lift.<\/p>\n<h2>How can I speed up conversion rate optimization testing?<\/h2>\n<p>If you are trying to understand how much your element under test\u00a0affects conversions there are no short cuts. However if you want to quickly test with a result of \u201chas a lift\u201d or \u201cdoes not have a lift\u201d then you can prematurely end some tests as long as your final test is run to conclusion. Can you tell which variation below could be stopped early? <a href=\"https:\/\/www.ometrics.com\/blog\/wp-content\/uploads\/2015\/09\/3-varients-a-b-test-2a.jpg\"><img loading=\"lazy\" decoding=\"async\" class=\"aligncenter size-full wp-image-288\" src=\"https:\/\/www.ometrics.com\/blog\/wp-content\/uploads\/2015\/09\/3-varients-a-b-test-2a.jpg\" alt=\"landing page optimization variants vs control\" width=\"620\" height=\"253\" srcset=\"https:\/\/www.ometrics.com\/blog\/wp-content\/uploads\/2015\/09\/3-varients-a-b-test-2a.jpg 620w, https:\/\/www.ometrics.com\/blog\/wp-content\/uploads\/2015\/09\/3-varients-a-b-test-2a-300x122.jpg 300w\" sizes=\"(max-width: 620px) 100vw, 620px\" \/><\/a> When orange is the control.<\/p>\n<p style=\"padding-left: 30px;\"><strong>The blue variation<\/strong> looks great in the beginning but in the end it is equal to the control. If this test was stopped on the third day the blue variation would not provide any significant lift and possible a negative result although your initial results said otherwise.<\/p>\n<p style=\"padding-left: 30px;\"><strong>The pink variation<\/strong> is above the control all the time, this can indicate a solid positive test. If the test was concluded early the estimated lift would not be accurate but at least there would be a positive lift.<\/p>\n<p style=\"padding-left: 30px;\"><strong>The dark yellow variation<\/strong> was negative after the second day and stayed negative. This test could be stopped early. Usually a good test shows positive results or a consistent daily increase against the control.<\/p>\n<p>Every page has a deviation\u00a0in conversions overtime depending on the traffic type. If you do an A\/A test and track the conversions over time you will see the difference between the two A\/A results will decrease. The amount of time it take for both A\/A versions to have the same conversion rate is an indication of a minimum test time. It is also your noise floor or the lowest conversion lift you can accurate state. For example if the deviation\u00a0is always .5% all of your tests must have a lift greater than .5% to be accurate.<\/p>\n<h2>Conversion optimization A-B testing\u00a0guidelines<\/h2>\n<ol>\n<li>Always run a test to statistical confidence of 90% or greater. Note that different A-B testing systems use different algorithms such as chi squared, z-score and derivatives of these. This means there is a variance when comparing data between different testing systems but if you are testing to above 90% you are ok.<\/li>\n<li>Always run a test for at least seven days even if you have a statistical winner earlier. This will account for advertising, user personas and user device variants. Of course this also depends on the amount of traffic and conversions you are getting. It is not unusual to run a test on a page that has a low volume of couple thousand visitors for a month.<\/li>\n<li>Look for test variants cumulative conversion rate compared to the control and see if the lines cross or are consistently above or below.<br \/>\n<strong>&gt; Above control<\/strong> \u2013 most likely a solid lift<br \/>\n<strong>&gt; Criss-crossing the control <\/strong>\u2013 the test has not run its course yet and is not statistically accurate<br \/>\n<strong>&gt; Below the control and not going positive<\/strong>\u00a0\u2013 most likely a negative lift, this type of variant can be stopped\u00a0early to speed up testing.<\/li>\n<li>Check the data by device. Often devices can cancel each other\u2019s results out. A desktop may have positive result but mobile may not, making the total conversion lift not as great as could be. This also tips you off that mobile only tests are needed.<\/li>\n<li>Be conscious of other factors during your testing period\u00a0such as holidays, ad campaign changes, lifts in traffic due to other corporate initiatives.<\/li>\n<li>Doing an A\/A test can help determine length of test and minimum conversion lift.<\/li>\n<li>If you are not sure it does not hurt to continue running the test unless the results are negligible.<\/li>\n<\/ol>\n<p>&nbsp;<\/p>\n","protected":false},"excerpt":{"rendered":"<p>Often when running conversion rate optimization A\/B\u00a0testing (split testing)\u00a0the tests\u00a0are\u00a0concluded too early even though the results are showing a statistically accurate result. To avoid this false positive a general understanding of the life of a test and what can affect it is required.<\/p>\n","protected":false},"author":1,"featured_media":0,"comment_status":"open","ping_status":"open","sticky":false,"template":"","format":"standard","meta":{"_et_pb_use_builder":"","_et_pb_old_content":"","_et_gb_content_width":"","footnotes":""},"categories":[7,18,23],"tags":[41,12,682423,28,35],"class_list":["post-285","post","type-post","status-publish","format-standard","hentry","category-a-b-testing","category-conversion-rate-optimization","category-landing-page-optimization","tag-a-b-testing-2","tag-ab-testing","tag-blog","tag-conversion-rate-optimization-2","tag-landing-page-optimization-2"],"yoast_head":"<!-- This site is optimized with the Yoast SEO plugin v26.9 - https:\/\/yoast.com\/product\/yoast-seo-wordpress\/ -->\n<title>Don\u2019t be tricked with false positives when A-B testing | Ometrics<\/title>\n<meta name=\"description\" content=\"When running conversion rate optimization A-B testing the tests are concluded to early here is how to avoid this false positives.\" \/>\n<meta name=\"robots\" content=\"index, follow, max-snippet:-1, max-image-preview:large, max-video-preview:-1\" \/>\n<link rel=\"canonical\" href=\"https:\/\/www.ometrics.com\/blog\/dont-be-tricked-with-false-positives-when-a-b-testing\/\" \/>\n<meta property=\"og:locale\" content=\"en_US\" \/>\n<meta property=\"og:type\" content=\"article\" \/>\n<meta property=\"og:title\" content=\"Don\u2019t be tricked with false positives when A-B testing | Ometrics\" \/>\n<meta property=\"og:description\" content=\"When running conversion rate optimization A-B testing the tests are concluded to early here is how to avoid this false positives.\" \/>\n<meta property=\"og:url\" content=\"https:\/\/www.ometrics.com\/blog\/dont-be-tricked-with-false-positives-when-a-b-testing\/\" \/>\n<meta property=\"og:site_name\" content=\"Ometrics\" \/>\n<meta property=\"article:publisher\" content=\"https:\/\/www.facebook.com\/Ometrics\/\" \/>\n<meta property=\"article:author\" content=\"http:\/\/www.facebook.com\/ometrics\" \/>\n<meta property=\"article:published_time\" content=\"2015-09-28T23:52:46+00:00\" \/>\n<meta property=\"article:modified_time\" content=\"2019-05-28T18:17:50+00:00\" \/>\n<meta property=\"og:image\" content=\"https:\/\/www.ometrics.com\/blog\/wp-content\/uploads\/2015\/09\/early-results-table.jpg\" \/>\n<meta name=\"author\" content=\"Greg Ahern\" \/>\n<meta name=\"twitter:label1\" content=\"Written by\" \/>\n\t<meta name=\"twitter:data1\" content=\"Greg Ahern\" \/>\n\t<meta name=\"twitter:label2\" content=\"Est. reading time\" \/>\n\t<meta name=\"twitter:data2\" content=\"5 minutes\" \/>\n<script type=\"application\/ld+json\" class=\"yoast-schema-graph\">{\"@context\":\"https:\/\/schema.org\",\"@graph\":[{\"@type\":\"Article\",\"@id\":\"https:\/\/www.ometrics.com\/blog\/dont-be-tricked-with-false-positives-when-a-b-testing\/#article\",\"isPartOf\":{\"@id\":\"https:\/\/www.ometrics.com\/blog\/dont-be-tricked-with-false-positives-when-a-b-testing\/\"},\"author\":{\"name\":\"Greg Ahern\",\"@id\":\"https:\/\/www.ometrics.com\/blog\/#\/schema\/person\/2e626ba442cbcf4e1db7e9fe737dcbc8\"},\"headline\":\"Don\u2019t Be Tricked With False Positives When A-B Testing\",\"datePublished\":\"2015-09-28T23:52:46+00:00\",\"dateModified\":\"2019-05-28T18:17:50+00:00\",\"mainEntityOfPage\":{\"@id\":\"https:\/\/www.ometrics.com\/blog\/dont-be-tricked-with-false-positives-when-a-b-testing\/\"},\"wordCount\":959,\"commentCount\":0,\"publisher\":{\"@id\":\"https:\/\/www.ometrics.com\/blog\/#organization\"},\"image\":{\"@id\":\"https:\/\/www.ometrics.com\/blog\/dont-be-tricked-with-false-positives-when-a-b-testing\/#primaryimage\"},\"thumbnailUrl\":\"https:\/\/www.ometrics.com\/blog\/wp-content\/uploads\/2015\/09\/early-results-table.jpg\",\"keywords\":[\"A-B Testing\",\"A\/B testing\",\"blog\",\"conversion rate optimization\",\"landing page optimization\"],\"articleSection\":[\"A\/B Testing\",\"Conversion Rate Optimization\",\"Landing Page Optimization\"],\"inLanguage\":\"en-US\"},{\"@type\":\"WebPage\",\"@id\":\"https:\/\/www.ometrics.com\/blog\/dont-be-tricked-with-false-positives-when-a-b-testing\/\",\"url\":\"https:\/\/www.ometrics.com\/blog\/dont-be-tricked-with-false-positives-when-a-b-testing\/\",\"name\":\"Don\u2019t be tricked with false positives when A-B testing | Ometrics\",\"isPartOf\":{\"@id\":\"https:\/\/www.ometrics.com\/blog\/#website\"},\"primaryImageOfPage\":{\"@id\":\"https:\/\/www.ometrics.com\/blog\/dont-be-tricked-with-false-positives-when-a-b-testing\/#primaryimage\"},\"image\":{\"@id\":\"https:\/\/www.ometrics.com\/blog\/dont-be-tricked-with-false-positives-when-a-b-testing\/#primaryimage\"},\"thumbnailUrl\":\"https:\/\/www.ometrics.com\/blog\/wp-content\/uploads\/2015\/09\/early-results-table.jpg\",\"datePublished\":\"2015-09-28T23:52:46+00:00\",\"dateModified\":\"2019-05-28T18:17:50+00:00\",\"description\":\"When running conversion rate optimization A-B testing the tests are concluded to early here is how to avoid this false positives.\",\"breadcrumb\":{\"@id\":\"https:\/\/www.ometrics.com\/blog\/dont-be-tricked-with-false-positives-when-a-b-testing\/#breadcrumb\"},\"inLanguage\":\"en-US\",\"potentialAction\":[{\"@type\":\"ReadAction\",\"target\":[\"https:\/\/www.ometrics.com\/blog\/dont-be-tricked-with-false-positives-when-a-b-testing\/\"]}]},{\"@type\":\"ImageObject\",\"inLanguage\":\"en-US\",\"@id\":\"https:\/\/www.ometrics.com\/blog\/dont-be-tricked-with-false-positives-when-a-b-testing\/#primaryimage\",\"url\":\"https:\/\/www.ometrics.com\/blog\/wp-content\/uploads\/2015\/09\/early-results-table.jpg\",\"contentUrl\":\"https:\/\/www.ometrics.com\/blog\/wp-content\/uploads\/2015\/09\/early-results-table.jpg\",\"width\":392,\"height\":87,\"caption\":\"a-b test conversion early results table\"},{\"@type\":\"BreadcrumbList\",\"@id\":\"https:\/\/www.ometrics.com\/blog\/dont-be-tricked-with-false-positives-when-a-b-testing\/#breadcrumb\",\"itemListElement\":[{\"@type\":\"ListItem\",\"position\":1,\"name\":\"Home\",\"item\":\"https:\/\/www.ometrics.com\/blog\/\"},{\"@type\":\"ListItem\",\"position\":2,\"name\":\"Don\u2019t Be Tricked With False Positives When A-B Testing\"}]},{\"@type\":\"WebSite\",\"@id\":\"https:\/\/www.ometrics.com\/blog\/#website\",\"url\":\"https:\/\/www.ometrics.com\/blog\/\",\"name\":\"Ometrics\",\"description\":\"AI Chatbots, Conversion Rate Optimization Resources, Exit Popups, A-B Testing\",\"publisher\":{\"@id\":\"https:\/\/www.ometrics.com\/blog\/#organization\"},\"potentialAction\":[{\"@type\":\"SearchAction\",\"target\":{\"@type\":\"EntryPoint\",\"urlTemplate\":\"https:\/\/www.ometrics.com\/blog\/?s={search_term_string}\"},\"query-input\":{\"@type\":\"PropertyValueSpecification\",\"valueRequired\":true,\"valueName\":\"search_term_string\"}}],\"inLanguage\":\"en-US\"},{\"@type\":\"Organization\",\"@id\":\"https:\/\/www.ometrics.com\/blog\/#organization\",\"name\":\"Ometrics\",\"url\":\"https:\/\/www.ometrics.com\/blog\/\",\"logo\":{\"@type\":\"ImageObject\",\"inLanguage\":\"en-US\",\"@id\":\"https:\/\/www.ometrics.com\/blog\/#\/schema\/logo\/image\/\",\"url\":\"https:\/\/www.ometrics.com\/blog\/wp-content\/uploads\/2019\/06\/ometrics-logo-white-r-210x45.png\",\"contentUrl\":\"https:\/\/www.ometrics.com\/blog\/wp-content\/uploads\/2019\/06\/ometrics-logo-white-r-210x45.png\",\"width\":210,\"height\":45,\"caption\":\"Ometrics\"},\"image\":{\"@id\":\"https:\/\/www.ometrics.com\/blog\/#\/schema\/logo\/image\/\"},\"sameAs\":[\"https:\/\/www.facebook.com\/Ometrics\/\",\"https:\/\/x.com\/ometrics\",\"https:\/\/www.instagram.com\/ometricsllc\/\",\"https:\/\/www.linkedin.com\/company\/ometrics\",\"https:\/\/www.youtube.com\/channel\/UCqOKmRfWQ7v7cgXAuSABFIw\"]},{\"@type\":\"Person\",\"@id\":\"https:\/\/www.ometrics.com\/blog\/#\/schema\/person\/2e626ba442cbcf4e1db7e9fe737dcbc8\",\"name\":\"Greg Ahern\",\"image\":{\"@type\":\"ImageObject\",\"inLanguage\":\"en-US\",\"@id\":\"https:\/\/www.ometrics.com\/blog\/#\/schema\/person\/image\/\",\"url\":\"https:\/\/secure.gravatar.com\/avatar\/f1e660b474ae1134f6648fb4f62489cf0672e17474fa4eeadcb2bca8b9a9e25e?s=96&d=mm&r=g\",\"contentUrl\":\"https:\/\/secure.gravatar.com\/avatar\/f1e660b474ae1134f6648fb4f62489cf0672e17474fa4eeadcb2bca8b9a9e25e?s=96&d=mm&r=g\",\"caption\":\"Greg Ahern\"},\"description\":\"Greg Ahern Founder and CEO of Ometrics\u00ae and Ochatbot\u00ae is a fanatic about artificial intelligence, machine learning, AI chatbots, conversational ecommerce, lead generation and conversion rate optimization. Greg has been a successful Internet entrepreneur since 1994. He speaks at conferences and webinars and has built a number of internet businesses. You can follow Greg on Twitter @gregahern, Linkedin, and join his CRO Hacks Groups on Slack. https:\/\/www.ometrics.com\/cro-growth-hacks\/\",\"sameAs\":[\"https:\/\/www.ometrics.com\",\"http:\/\/www.facebook.com\/ometrics\",\"https:\/\/x.com\/gregahern\"],\"url\":\"https:\/\/www.ometrics.com\/blog\/author\/domoreblogs\/\"}]}<\/script>\n<!-- \/ Yoast SEO plugin. -->","yoast_head_json":{"title":"Don\u2019t be tricked with false positives when A-B testing | Ometrics","description":"When running conversion rate optimization A-B testing the tests are concluded to early here is how to avoid this false positives.","robots":{"index":"index","follow":"follow","max-snippet":"max-snippet:-1","max-image-preview":"max-image-preview:large","max-video-preview":"max-video-preview:-1"},"canonical":"https:\/\/www.ometrics.com\/blog\/dont-be-tricked-with-false-positives-when-a-b-testing\/","og_locale":"en_US","og_type":"article","og_title":"Don\u2019t be tricked with false positives when A-B testing | Ometrics","og_description":"When running conversion rate optimization A-B testing the tests are concluded to early here is how to avoid this false positives.","og_url":"https:\/\/www.ometrics.com\/blog\/dont-be-tricked-with-false-positives-when-a-b-testing\/","og_site_name":"Ometrics","article_publisher":"https:\/\/www.facebook.com\/Ometrics\/","article_author":"http:\/\/www.facebook.com\/ometrics","article_published_time":"2015-09-28T23:52:46+00:00","article_modified_time":"2019-05-28T18:17:50+00:00","og_image":[{"url":"https:\/\/www.ometrics.com\/blog\/wp-content\/uploads\/2015\/09\/early-results-table.jpg","type":"","width":"","height":""}],"author":"Greg Ahern","twitter_misc":{"Written by":"Greg Ahern","Est. reading time":"5 minutes"},"schema":{"@context":"https:\/\/schema.org","@graph":[{"@type":"Article","@id":"https:\/\/www.ometrics.com\/blog\/dont-be-tricked-with-false-positives-when-a-b-testing\/#article","isPartOf":{"@id":"https:\/\/www.ometrics.com\/blog\/dont-be-tricked-with-false-positives-when-a-b-testing\/"},"author":{"name":"Greg Ahern","@id":"https:\/\/www.ometrics.com\/blog\/#\/schema\/person\/2e626ba442cbcf4e1db7e9fe737dcbc8"},"headline":"Don\u2019t Be Tricked With False Positives When A-B Testing","datePublished":"2015-09-28T23:52:46+00:00","dateModified":"2019-05-28T18:17:50+00:00","mainEntityOfPage":{"@id":"https:\/\/www.ometrics.com\/blog\/dont-be-tricked-with-false-positives-when-a-b-testing\/"},"wordCount":959,"commentCount":0,"publisher":{"@id":"https:\/\/www.ometrics.com\/blog\/#organization"},"image":{"@id":"https:\/\/www.ometrics.com\/blog\/dont-be-tricked-with-false-positives-when-a-b-testing\/#primaryimage"},"thumbnailUrl":"https:\/\/www.ometrics.com\/blog\/wp-content\/uploads\/2015\/09\/early-results-table.jpg","keywords":["A-B Testing","A\/B testing","blog","conversion rate optimization","landing page optimization"],"articleSection":["A\/B Testing","Conversion Rate Optimization","Landing Page Optimization"],"inLanguage":"en-US"},{"@type":"WebPage","@id":"https:\/\/www.ometrics.com\/blog\/dont-be-tricked-with-false-positives-when-a-b-testing\/","url":"https:\/\/www.ometrics.com\/blog\/dont-be-tricked-with-false-positives-when-a-b-testing\/","name":"Don\u2019t be tricked with false positives when A-B testing | Ometrics","isPartOf":{"@id":"https:\/\/www.ometrics.com\/blog\/#website"},"primaryImageOfPage":{"@id":"https:\/\/www.ometrics.com\/blog\/dont-be-tricked-with-false-positives-when-a-b-testing\/#primaryimage"},"image":{"@id":"https:\/\/www.ometrics.com\/blog\/dont-be-tricked-with-false-positives-when-a-b-testing\/#primaryimage"},"thumbnailUrl":"https:\/\/www.ometrics.com\/blog\/wp-content\/uploads\/2015\/09\/early-results-table.jpg","datePublished":"2015-09-28T23:52:46+00:00","dateModified":"2019-05-28T18:17:50+00:00","description":"When running conversion rate optimization A-B testing the tests are concluded to early here is how to avoid this false positives.","breadcrumb":{"@id":"https:\/\/www.ometrics.com\/blog\/dont-be-tricked-with-false-positives-when-a-b-testing\/#breadcrumb"},"inLanguage":"en-US","potentialAction":[{"@type":"ReadAction","target":["https:\/\/www.ometrics.com\/blog\/dont-be-tricked-with-false-positives-when-a-b-testing\/"]}]},{"@type":"ImageObject","inLanguage":"en-US","@id":"https:\/\/www.ometrics.com\/blog\/dont-be-tricked-with-false-positives-when-a-b-testing\/#primaryimage","url":"https:\/\/www.ometrics.com\/blog\/wp-content\/uploads\/2015\/09\/early-results-table.jpg","contentUrl":"https:\/\/www.ometrics.com\/blog\/wp-content\/uploads\/2015\/09\/early-results-table.jpg","width":392,"height":87,"caption":"a-b test conversion early results table"},{"@type":"BreadcrumbList","@id":"https:\/\/www.ometrics.com\/blog\/dont-be-tricked-with-false-positives-when-a-b-testing\/#breadcrumb","itemListElement":[{"@type":"ListItem","position":1,"name":"Home","item":"https:\/\/www.ometrics.com\/blog\/"},{"@type":"ListItem","position":2,"name":"Don\u2019t Be Tricked With False Positives When A-B Testing"}]},{"@type":"WebSite","@id":"https:\/\/www.ometrics.com\/blog\/#website","url":"https:\/\/www.ometrics.com\/blog\/","name":"Ometrics","description":"AI Chatbots, Conversion Rate Optimization Resources, Exit Popups, A-B Testing","publisher":{"@id":"https:\/\/www.ometrics.com\/blog\/#organization"},"potentialAction":[{"@type":"SearchAction","target":{"@type":"EntryPoint","urlTemplate":"https:\/\/www.ometrics.com\/blog\/?s={search_term_string}"},"query-input":{"@type":"PropertyValueSpecification","valueRequired":true,"valueName":"search_term_string"}}],"inLanguage":"en-US"},{"@type":"Organization","@id":"https:\/\/www.ometrics.com\/blog\/#organization","name":"Ometrics","url":"https:\/\/www.ometrics.com\/blog\/","logo":{"@type":"ImageObject","inLanguage":"en-US","@id":"https:\/\/www.ometrics.com\/blog\/#\/schema\/logo\/image\/","url":"https:\/\/www.ometrics.com\/blog\/wp-content\/uploads\/2019\/06\/ometrics-logo-white-r-210x45.png","contentUrl":"https:\/\/www.ometrics.com\/blog\/wp-content\/uploads\/2019\/06\/ometrics-logo-white-r-210x45.png","width":210,"height":45,"caption":"Ometrics"},"image":{"@id":"https:\/\/www.ometrics.com\/blog\/#\/schema\/logo\/image\/"},"sameAs":["https:\/\/www.facebook.com\/Ometrics\/","https:\/\/x.com\/ometrics","https:\/\/www.instagram.com\/ometricsllc\/","https:\/\/www.linkedin.com\/company\/ometrics","https:\/\/www.youtube.com\/channel\/UCqOKmRfWQ7v7cgXAuSABFIw"]},{"@type":"Person","@id":"https:\/\/www.ometrics.com\/blog\/#\/schema\/person\/2e626ba442cbcf4e1db7e9fe737dcbc8","name":"Greg Ahern","image":{"@type":"ImageObject","inLanguage":"en-US","@id":"https:\/\/www.ometrics.com\/blog\/#\/schema\/person\/image\/","url":"https:\/\/secure.gravatar.com\/avatar\/f1e660b474ae1134f6648fb4f62489cf0672e17474fa4eeadcb2bca8b9a9e25e?s=96&d=mm&r=g","contentUrl":"https:\/\/secure.gravatar.com\/avatar\/f1e660b474ae1134f6648fb4f62489cf0672e17474fa4eeadcb2bca8b9a9e25e?s=96&d=mm&r=g","caption":"Greg Ahern"},"description":"Greg Ahern Founder and CEO of Ometrics\u00ae and Ochatbot\u00ae is a fanatic about artificial intelligence, machine learning, AI chatbots, conversational ecommerce, lead generation and conversion rate optimization. Greg has been a successful Internet entrepreneur since 1994. He speaks at conferences and webinars and has built a number of internet businesses. You can follow Greg on Twitter @gregahern, Linkedin, and join his CRO Hacks Groups on Slack. https:\/\/www.ometrics.com\/cro-growth-hacks\/","sameAs":["https:\/\/www.ometrics.com","http:\/\/www.facebook.com\/ometrics","https:\/\/x.com\/gregahern"],"url":"https:\/\/www.ometrics.com\/blog\/author\/domoreblogs\/"}]}},"_links":{"self":[{"href":"https:\/\/www.ometrics.com\/blog\/wp-json\/wp\/v2\/posts\/285","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/www.ometrics.com\/blog\/wp-json\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/www.ometrics.com\/blog\/wp-json\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/www.ometrics.com\/blog\/wp-json\/wp\/v2\/users\/1"}],"replies":[{"embeddable":true,"href":"https:\/\/www.ometrics.com\/blog\/wp-json\/wp\/v2\/comments?post=285"}],"version-history":[{"count":1,"href":"https:\/\/www.ometrics.com\/blog\/wp-json\/wp\/v2\/posts\/285\/revisions"}],"predecessor-version":[{"id":1830,"href":"https:\/\/www.ometrics.com\/blog\/wp-json\/wp\/v2\/posts\/285\/revisions\/1830"}],"wp:attachment":[{"href":"https:\/\/www.ometrics.com\/blog\/wp-json\/wp\/v2\/media?parent=285"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/www.ometrics.com\/blog\/wp-json\/wp\/v2\/categories?post=285"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/www.ometrics.com\/blog\/wp-json\/wp\/v2\/tags?post=285"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}