{"id":3492,"date":"2023-11-01T14:37:54","date_gmt":"2023-11-01T14:37:54","guid":{"rendered":"https:\/\/www.figpii.com\/blog\/?p=3492"},"modified":"2025-02-04T13:17:54","modified_gmt":"2025-02-04T13:17:54","slug":"type-1-and-type-2-errors-in-a-b-testing","status":"publish","type":"post","link":"https:\/\/www.figpii.com\/blog\/type-1-and-type-2-errors-in-a-b-testing\/","title":{"rendered":"What are Type 1 and Type 2 Errors in A\/B Testing?"},"content":{"rendered":"<p class=\"c3\"><span class=\"c1 c0\">Imagine you&#8217;re a marketer testing two different email subject lines to see which one gets more opens. It&#8217;s like choosing between two doors\u2014one leads to a room full of engaged customers, and the other, well, let&#8217;s just say it&#8217;s not where you want to be.<\/span><\/p><div id=\"ez-toc-container\" class=\"ez-toc-v2_0_74 ez-toc-wrap-left counter-hierarchy ez-toc-counter ez-toc-transparent ez-toc-container-direction\">\n<div class=\"ez-toc-title-container\">\n<p class=\"ez-toc-title\" style=\"cursor:inherit\">Table of Contents<\/p>\n<span class=\"ez-toc-title-toggle\"><a href=\"#\" class=\"ez-toc-pull-right ez-toc-btn ez-toc-btn-xs ez-toc-btn-default ez-toc-toggle\" aria-label=\"Toggle Table of Content\"><span class=\"ez-toc-js-icon-con\"><span class=\"\"><span class=\"eztoc-hide\" style=\"display:none;\">Toggle<\/span><span class=\"ez-toc-icon-toggle-span\"><svg style=\"fill: #999;color:#999\" xmlns=\"http:\/\/www.w3.org\/2000\/svg\" class=\"list-377408\" width=\"20px\" height=\"20px\" viewBox=\"0 0 24 24\" fill=\"none\"><path d=\"M6 6H4v2h2V6zm14 0H8v2h12V6zM4 11h2v2H4v-2zm16 0H8v2h12v-2zM4 16h2v2H4v-2zm16 0H8v2h12v-2z\" fill=\"currentColor\"><\/path><\/svg><svg style=\"fill: #999;color:#999\" class=\"arrow-unsorted-368013\" xmlns=\"http:\/\/www.w3.org\/2000\/svg\" width=\"10px\" height=\"10px\" viewBox=\"0 0 24 24\" version=\"1.2\" baseProfile=\"tiny\"><path d=\"M18.2 9.3l-6.2-6.3-6.2 6.3c-.2.2-.3.4-.3.7s.1.5.3.7c.2.2.4.3.7.3h11c.3 0 .5-.1.7-.3.2-.2.3-.5.3-.7s-.1-.5-.3-.7zM5.8 14.7l6.2 6.3 6.2-6.3c.2-.2.3-.5.3-.7s-.1-.5-.3-.7c-.2-.2-.4-.3-.7-.3h-11c-.3 0-.5.1-.7.3-.2.2-.3.5-.3.7s.1.5.3.7z\"\/><\/svg><\/span><\/span><\/span><\/a><\/span><\/div>\n<nav><ul class='ez-toc-list ez-toc-list-level-1 eztoc-toggle-hide-by-default' ><li class='ez-toc-page-1 ez-toc-heading-level-2'><a class=\"ez-toc-link ez-toc-heading-1\" href=\"https:\/\/www.figpii.com\/blog\/type-1-and-type-2-errors-in-a-b-testing\/#The_Anatomy_of_Errors_in_AB_Testing\" >The Anatomy of Errors in A\/B Testing<\/a><\/li><li class='ez-toc-page-1 ez-toc-heading-level-2'><a class=\"ez-toc-link ez-toc-heading-2\" href=\"https:\/\/www.figpii.com\/blog\/type-1-and-type-2-errors-in-a-b-testing\/#Understanding_Null_Hypotheses\" >Understanding Null Hypotheses<\/a><ul class='ez-toc-list-level-3' ><li class='ez-toc-heading-level-3'><a class=\"ez-toc-link ez-toc-heading-3\" href=\"https:\/\/www.figpii.com\/blog\/type-1-and-type-2-errors-in-a-b-testing\/#Relationship_between_the_Null_Hypothesis_and_Type_1_and_Type_2_Errors\" >Relationship between the Null Hypothesis and Type 1 and Type 2 Errors<\/a><\/li><\/ul><\/li><li class='ez-toc-page-1 ez-toc-heading-level-2'><a class=\"ez-toc-link ez-toc-heading-4\" href=\"https:\/\/www.figpii.com\/blog\/type-1-and-type-2-errors-in-a-b-testing\/#Deep_Dive_into_Type_1_Errors\" >Deep Dive into Type 1 Errors<\/a><ul class='ez-toc-list-level-3' ><li class='ez-toc-heading-level-3'><a class=\"ez-toc-link ez-toc-heading-5\" href=\"https:\/\/www.figpii.com\/blog\/type-1-and-type-2-errors-in-a-b-testing\/#Scenario_for_Type_1_Error\" >Scenario for Type 1 Error<\/a><\/li><li class='ez-toc-page-1 ez-toc-heading-level-3'><a class=\"ez-toc-link ez-toc-heading-6\" href=\"https:\/\/www.figpii.com\/blog\/type-1-and-type-2-errors-in-a-b-testing\/#Causes_of_Type_1_Errors_False_Positives\" >Causes of Type 1 Errors (False Positives)<\/a><\/li><li class='ez-toc-page-1 ez-toc-heading-level-3'><a class=\"ez-toc-link ez-toc-heading-7\" href=\"https:\/\/www.figpii.com\/blog\/type-1-and-type-2-errors-in-a-b-testing\/#Consequences_of_Committing_a_Type_1_Error\" >Consequences of Committing a Type 1 Error<\/a><\/li><li class='ez-toc-page-1 ez-toc-heading-level-3'><a class=\"ez-toc-link ez-toc-heading-8\" href=\"https:\/\/www.figpii.com\/blog\/type-1-and-type-2-errors-in-a-b-testing\/#How_to_Minimize_Type_1_Errors\" >How to Minimize Type 1 Errors<\/a><\/li><\/ul><\/li><li class='ez-toc-page-1 ez-toc-heading-level-2'><a class=\"ez-toc-link ez-toc-heading-9\" href=\"https:\/\/www.figpii.com\/blog\/type-1-and-type-2-errors-in-a-b-testing\/#Type_2_Errors\" >Type 2 Errors<\/a><ul class='ez-toc-list-level-3' ><li class='ez-toc-heading-level-3'><a class=\"ez-toc-link ez-toc-heading-10\" href=\"https:\/\/www.figpii.com\/blog\/type-1-and-type-2-errors-in-a-b-testing\/#Scenario_for_Type_2_Error\" >Scenario for Type 2 Error<\/a><\/li><li class='ez-toc-page-1 ez-toc-heading-level-3'><a class=\"ez-toc-link ez-toc-heading-11\" href=\"https:\/\/www.figpii.com\/blog\/type-1-and-type-2-errors-in-a-b-testing\/#Causes_of_Type_2_Errors_False_Negatives\" >Causes of Type 2 Errors (False Negatives)<\/a><\/li><li class='ez-toc-page-1 ez-toc-heading-level-3'><a class=\"ez-toc-link ez-toc-heading-12\" href=\"https:\/\/www.figpii.com\/blog\/type-1-and-type-2-errors-in-a-b-testing\/#Consequences_of_Committing_a_Type_1_Error-2\" >Consequences of Committing a Type 1 Error<\/a><\/li><li class='ez-toc-page-1 ez-toc-heading-level-3'><a class=\"ez-toc-link ez-toc-heading-13\" href=\"https:\/\/www.figpii.com\/blog\/type-1-and-type-2-errors-in-a-b-testing\/#How_to_minimize_type_2_errors\" >How to minimize type 2 errors<\/a><\/li><\/ul><\/li><li class='ez-toc-page-1 ez-toc-heading-level-2'><a class=\"ez-toc-link ez-toc-heading-14\" href=\"https:\/\/www.figpii.com\/blog\/type-1-and-type-2-errors-in-a-b-testing\/#Frequently_Ask_Questions\" >Frequently Ask Questions<\/a><ul class='ez-toc-list-level-3' ><li class='ez-toc-heading-level-3'><a class=\"ez-toc-link ez-toc-heading-15\" href=\"https:\/\/www.figpii.com\/blog\/type-1-and-type-2-errors-in-a-b-testing\/#How_do_Type_1_and_Type_2_errors_differ_from_each_other\" >How do Type 1 and Type 2 errors differ from each other?<\/a><\/li><li class='ez-toc-page-1 ez-toc-heading-level-3'><a class=\"ez-toc-link ez-toc-heading-16\" href=\"https:\/\/www.figpii.com\/blog\/type-1-and-type-2-errors-in-a-b-testing\/#What_is_the_significance_level_and_how_does_it_relate_to_Type_1_errors\" >What is the significance level, and how does it relate to Type 1 errors?<\/a><\/li><li class='ez-toc-page-1 ez-toc-heading-level-3'><a class=\"ez-toc-link ez-toc-heading-17\" href=\"https:\/\/www.figpii.com\/blog\/type-1-and-type-2-errors-in-a-b-testing\/#What_is_statistical_power_and_how_does_it_relate_to_Type_2_errors\" >What is statistical power, and how does it relate to Type 2 errors?<\/a><\/li><\/ul><\/li><\/ul><\/nav><\/div>\n\n<p class=\"c3\"><span class=\"c1 c0\">Making the wrong choice could mean missing out on valuable conversions or, worse, wasting resources on a strategy that doesn&#8217;t work.<\/span><\/p>\n<p class=\"c3\"><span class=\"c0\">This is where Type 1 and Type 2 errors come into play. They&#8217;re the pitfalls that can trip you up in your\u00a0<\/span><span class=\"c13 c0\"><a class=\"c15\" href=\"https:\/\/www.figpii.com\/blog\/how-to-setup-and-run-an-a-b-test-a-step-by-step-guide\/\">A\/B testing<\/a><\/span><span class=\"c1 c0\">\u00a0journey, leading you to the wrong door. \u00a0In statistical terms, these errors are known as false positives and false negatives.<\/span><\/p>\n<p class=\"c3\"><span class=\"c1 c0\">In this article, you&#8217;ll learn what these errors are, why they can make or break your A\/B testing strategy, and how to minimize their occurrences.<\/span><\/p>\n<h2 id=\"h.2en3wbx4h6db\" class=\"c7\"><span class=\"ez-toc-section\" id=\"The_Anatomy_of_Errors_in_AB_Testing\"><\/span><span class=\"c10 c0\">The Anatomy of Errors in A\/B Testing<\/span><span class=\"ez-toc-section-end\"><\/span><\/h2>\n<p class=\"c3\"><span class=\"c1 c0\">Errors in A\/B testing are an inherent part of the process, mainly due to the statistical nature of these tests. When conducting an <a href=\"https:\/\/www.figpii.com\/blog\/ab-testing-guide\/\">A\/B test<\/a>, one is essentially drawing conclusions based on a sample of data, which may not represent the entire customer base. This inherent limitation in sampling makes the occurrence of Type 1 and Type 2 errors unavoidable.<\/span><\/p>\n<h2 id=\"h.snv8qr8xooux\" class=\"c7\"><span class=\"ez-toc-section\" id=\"Understanding_Null_Hypotheses\"><\/span><span class=\"c10 c0\">Understanding Null Hypotheses<\/span><span class=\"ez-toc-section-end\"><\/span><\/h2>\n<p class=\"c3\"><span class=\"c1 c0\">Before we get into what type 1 and type 2 errors are, it\u2019s important to understand what the null hypothesis is.<\/span><\/p>\n<p class=\"c3\"><span class=\"c0\">The null hypothesis, symbolized as\u00a0<\/span><span class=\"c2 c0\">H<\/span><span class=\"c0 c6\">0<\/span><span class=\"c1 c0\">, is a fundamental concept in statistical testing. It serves as the default or initial assumption that there is no effect or difference between the groups being compared.<\/span><\/p>\n<p class=\"c3\"><span class=\"c0\">In simpler terms,\u00a0<\/span><span class=\"c2 c0\">H<\/span><span class=\"c0 c6\">0\u00a0<\/span><span class=\"c1 c0\">posits that any observed differences in performances of variations are due to random chance rather than an underlying cause or effect.<\/span><\/p>\n<p class=\"c3\"><span class=\"c0\">In A\/B testing, the null hypothesis often states that there is no significant difference between the control group (A) and the variant group (B) concerning the metric under investigation, such as\u00a0<\/span><span class=\"c13 c0\"><a class=\"c15\" href=\"https:\/\/www.figpii.com\/blog\/how-to-calculate-conversion-rate\/\">conversion rate<\/a><\/span><span class=\"c0\">\u00a0or user engagement. The objective is often to reject the null hypothesis in favor of the alternative hypothesis based on <a href=\"https:\/\/www.figpii.com\/blog\/misconceptions-about-statistical-significance\/\">statistical significance<\/a>.<\/span><\/p>\n<h3 id=\"h.46hre5rm9cdj\" class=\"c12\"><span class=\"ez-toc-section\" id=\"Relationship_between_the_Null_Hypothesis_and_Type_1_and_Type_2_Errors\"><\/span><span class=\"c16 c0\">Relationship between the Null Hypothesis and Type 1 and Type 2 Errors<\/span><span class=\"ez-toc-section-end\"><\/span><\/h3>\n<p class=\"c3\"><span class=\"c0\">The null hypothesis,\u00a0<\/span><span class=\"c2 c0\">H<\/span><span class=\"c0 c6\">0,<\/span><span class=\"c0\">\u00a0<\/span><span class=\"c0\">is intrinsically connected to Type 1 and Type 2 errors. A Type 1 error occurs when\u00a0<\/span><span class=\"c2 c0\">H<\/span><span class=\"c0 c6\">0<\/span><span class=\"c1 c0\">\u00a0is incorrectly rejected, leading to the false conclusion that there is a significant difference between the groups when, in fact, there is none.<\/span><\/p>\n<p class=\"c3\"><span class=\"c0\">On the other hand, a Type 2 error arises when\u00a0<\/span><span class=\"c0 c2\">H<\/span><span class=\"c0 c6\">0<\/span><span class=\"c1 c0\">\u00a0is incorrectly retained, thereby failing to identify a real difference or effect. Both types of errors compromise the integrity of the hypothesis-testing process and can result in flawed business decisions.<\/span><\/p>\n<h2 id=\"h.eg1ydkl17dzm\" class=\"c7\"><span class=\"ez-toc-section\" id=\"Deep_Dive_into_Type_1_Errors\"><\/span><span class=\"c0\">Deep Dive into Type 1 Errors<\/span><span class=\"ez-toc-section-end\"><\/span><\/h2>\n<p class=\"c3\"><span class=\"c0\">As stated earlier, a Type 1 error, often denoted by the symbol\u00a0<\/span><span class=\"c9\">\u03b1<\/span><span class=\"c0\">, occurs when the null hypothesis is incorrectly rejected. The level of\u00a0<\/span><span class=\"c9\">\u03b1<\/span><span class=\"c1 c0\">\u00a0is often set prior to the test and represents the probability of committing a Type 1 error.<\/span><\/p>\n<p><img loading=\"lazy\" decoding=\"async\" class=\"alignnone size-large wp-image-3638\" src=\"https:\/\/www.figpii.com\/blog\/wp-content\/uploads\/2023\/11\/3-1024x706.png\" alt=\"Probability of a type 1 error\" width=\"770\" height=\"531\" srcset=\"https:\/\/www.figpii.com\/blog\/wp-content\/uploads\/2023\/11\/3-1024x706.png 1024w, https:\/\/www.figpii.com\/blog\/wp-content\/uploads\/2023\/11\/3-300x207.png 300w, https:\/\/www.figpii.com\/blog\/wp-content\/uploads\/2023\/11\/3-768x529.png 768w, https:\/\/www.figpii.com\/blog\/wp-content\/uploads\/2023\/11\/3-1536x1058.png 1536w, https:\/\/www.figpii.com\/blog\/wp-content\/uploads\/2023\/11\/3.png 1595w\" sizes=\"auto, (max-width: 770px) 100vw, 770px\" \/><\/p>\n<h3 id=\"h.joaegyvat5bo\" class=\"c12\"><span class=\"ez-toc-section\" id=\"Scenario_for_Type_1_Error\"><\/span><span class=\"c0\">Scenario for Type 1 Error<\/span><span class=\"ez-toc-section-end\"><\/span><\/h3>\n<p class=\"c3\"><span class=\"c1 c0\">You run an A\/B test comparing the two subject lines. At the end of the test, the data suggests that the &#8220;New Subject&#8221; has a significantly higher open rate. Thrilled, you decide to roll it out to your entire email list.<\/span><\/p>\n<p class=\"c3\"><span class=\"c9\">Type 1 Error<\/span><span class=\"c1 c0\">: In reality, the &#8220;New Subject&#8221; line doesn&#8217;t have a higher open rate; the test results were a fluke. You&#8217;ve rejected the true null hypothesis (&#8220;New Subject&#8221; is not better than &#8220;Old Subject&#8221;).<\/span><\/p>\n<h3 id=\"h.s139c09zry6l\" class=\"c12\"><span class=\"ez-toc-section\" id=\"Causes_of_Type_1_Errors_False_Positives\"><\/span>Causes of Type 1 Errors (False Positives)<span class=\"ez-toc-section-end\"><\/span><\/h3>\n<ol class=\"c5 lst-kix_8j22w3jweboh-0 start\" start=\"1\">\n<li class=\"c3 c11 li-bullet-0\">Expecting a larger effect than what is true can lead to overinterpreting normal variations as significant differences.<\/li>\n<li class=\"c3 c11 li-bullet-0\">Conducting multiple comparisons without adjusting for significance increases the likelihood of incorrectly rejecting the null hypothesis at least once.<\/li>\n<li class=\"c3 c11 li-bullet-0\">Searching through data for patterns without a specific hypothesis can result in identifying false positives purely by chance.<\/li>\n<li class=\"c3 c11 li-bullet-0\">Choosing a higher alpha level (e.g., 0.10 instead of 0.05) increases the probability of rejecting the null hypothesis erroneously.<\/li>\n<li class=\"c3 c11 li-bullet-0\">Lack of proper randomization or control groups can introduce bias, leading to incorrect conclusions.<\/li>\n<\/ol>\n<h3 id=\"h.s139c09zry6l\" class=\"c12\"><span class=\"ez-toc-section\" id=\"Consequences_of_Committing_a_Type_1_Error\"><\/span><span class=\"c16 c0\">Consequences of Committing a Type 1 Error<\/span><span class=\"ez-toc-section-end\"><\/span><\/h3>\n<ol class=\"c5 lst-kix_8j22w3jweboh-0 start\" start=\"1\">\n<li class=\"c3 c11 li-bullet-0\"><span class=\"c1 c0\">Implementing a change based on a false positive can lead to a waste of time, money, and manpower on a strategy that&#8217;s not effective.<\/span><\/li>\n<li class=\"c3 c11 li-bullet-0\"><span class=\"c1 c0\">While focusing on a strategy that doesn&#8217;t work, you might miss the chance to implement one that does, leading to lost revenue.<\/span><\/li>\n<li class=\"c3 c11 li-bullet-0\"><span class=\"c1 c0\">If the change negatively impacts user experience, it can harm your brand&#8217;s reputation and customer loyalty.<\/span><\/li>\n<li class=\"c3 c11 li-bullet-0\"><span class=\"c1 c0\">A Type 1 error can cast doubt on the reliability of your A\/B testing process, making stakeholders less likely to trust future test results.<\/span><\/li>\n<li class=\"c3 c11 li-bullet-0\"><span class=\"c0\">Implementing ineffective changes can put you at a disadvantage, especially when your competitors make more data-driven, effective decisions.<\/span><\/li>\n<\/ol>\n<h3 id=\"h.qclqi1me9v5t\" class=\"c12\"><span class=\"ez-toc-section\" id=\"How_to_Minimize_Type_1_Errors\"><\/span><span class=\"c16 c0\">How to Minimize Type 1 Errors<\/span><span class=\"ez-toc-section-end\"><\/span><\/h3>\n<ol class=\"c5 lst-kix_s5aip9lh7hfb-0 start\" start=\"1\">\n<li class=\"c3 c11 li-bullet-0\"><span class=\"c0\">Adjust the\u00a0<\/span><span class=\"c13 c0\">Significance Level<\/span><span class=\"c1 c0\">: One common approach is to set a lower \u03b1 level, such as 0.01 instead of the conventional 0.05, to reduce the chances of incorrectly rejecting the null hypothesis.<\/span><\/li>\n<li class=\"c3 c11 li-bullet-0\"><span class=\"c0\">Increase Sample Size: A larger\u00a0<\/span><span class=\"c0 c13\"><a class=\"c15\" href=\"https:\/\/www.figpii.com\/blog\/what-is-a-sample-size-in-a-b-testing\/\">sample size<\/a><\/span><span class=\"c1 c0\">\u00a0can provide more accurate results, reducing the likelihood of a Type 1 error.<\/span><\/li>\n<li class=\"c3 c11 li-bullet-0\"><span class=\"c1 c0\">Sequential Testing: This involves periodically checking the data and stopping the test once sufficient evidence has been gathered, reducing the chances of a Type 1 error.<\/span><\/li>\n<li class=\"c3 c11 li-bullet-0\"><span class=\"c0\">Peer Review: Before making any significant changes based on the test results, having the data and methodology peer-reviewed can serve as an additional safeguard against Type 1 errors.<\/span><\/li>\n<\/ol>\n<h2 id=\"h.fr342t3l1rb\" class=\"c7\"><span class=\"ez-toc-section\" id=\"Type_2_Errors\"><\/span><span class=\"c10 c0\">Type 2 Errors<\/span><span class=\"ez-toc-section-end\"><\/span><\/h2>\n<p class=\"c3\"><span class=\"c0\">A Type 2 error, commonly represented by the symbol\u00a0<\/span><span class=\"c9\">\u03b2<\/span><span class=\"c0\">, occurs when the null hypothesis,\u00a0<\/span><span class=\"c2 c0\">H<\/span><span class=\"c0 c6\">0,<\/span><span class=\"c1 c0\"> is incorrectly accepted or failed to be rejected. The probability of committing a Type 2 error is\u00a0<\/span><strong><span class=\"c9\">\u03b2<\/span><\/strong><span class=\"c0\">, and it is inversely related to the test&#8217;s power, which is\u00a0<\/span><strong><span class=\"c9\">1\u2212\u03b2<\/span><\/strong><span class=\"c0 c1\">.<\/span><\/p>\n<p><img loading=\"lazy\" decoding=\"async\" class=\"alignnone wp-image-3640 size-large\" src=\"https:\/\/www.figpii.com\/blog\/wp-content\/uploads\/2023\/11\/4-1024x706.png\" alt=\"Probability of a type II error\" width=\"770\" height=\"531\" srcset=\"https:\/\/www.figpii.com\/blog\/wp-content\/uploads\/2023\/11\/4-1024x706.png 1024w, https:\/\/www.figpii.com\/blog\/wp-content\/uploads\/2023\/11\/4-300x207.png 300w, https:\/\/www.figpii.com\/blog\/wp-content\/uploads\/2023\/11\/4-768x529.png 768w, https:\/\/www.figpii.com\/blog\/wp-content\/uploads\/2023\/11\/4-1536x1058.png 1536w, https:\/\/www.figpii.com\/blog\/wp-content\/uploads\/2023\/11\/4.png 1595w\" sizes=\"auto, (max-width: 770px) 100vw, 770px\" \/><\/p>\n<h3 id=\"h.fjl9x7rho2jy\" class=\"c12\"><span class=\"ez-toc-section\" id=\"Scenario_for_Type_2_Error\"><\/span><span class=\"c0\">Scenario for Type 2 Error<\/span><span class=\"ez-toc-section-end\"><\/span><\/h3>\n<p class=\"c3\"><span class=\"c1 c0\">Again, you run an A\/B test comparing the two subject lines. This time, the <a href=\"https:\/\/www.figpii.com\/blog\/analyzing-ab-testing-results\">A\/B Test results<\/a> suggest no significant difference between the &#8220;New Subject&#8221; and &#8220;Old Subject&#8221; lines. So, you stick with the &#8220;Old Subject&#8221; line.<\/span><\/p>\n<p class=\"c3\"><span class=\"c9\">Type 2 Error<\/span><span class=\"c1 c0\">: In reality, the &#8220;New Subject&#8221; line does have a higher open rate, but the test failed to detect this difference. You&#8217;ve failed to reject a false null hypothesis (&#8220;New Subject&#8221; is not better than &#8220;Old Subject&#8221;).<\/span><\/p>\n<h3 id=\"h.6e1lf2wd89tb\" class=\"c12\"><span class=\"ez-toc-section\" id=\"Causes_of_Type_2_Errors_False_Negatives\"><\/span>Causes of Type 2 Errors (False Negatives)<span class=\"ez-toc-section-end\"><\/span><\/h3>\n<ol class=\"c5 lst-kix_u68hmniakuij-0 start\" start=\"1\">\n<li>Too small a sample may not have the power to detect an actual effect, leading to a failure to reject the null hypothesis when it is false.<\/li>\n<li>Besides sample size, other factors like effect size and variability can contribute to low power, increasing the risk of a Type 2 error.<\/li>\n<li>Setting the significance level too low can make it too difficult to detect a real effect, which can result in a Type 2 error.<\/li>\n<li>High variability within test groups can obscure true differences between the control and experimental groups.<\/li>\n<li>Errors in how data is collected, such as timing issues or non-representative samples, can lead to a failure to detect real differences.<\/li>\n<\/ol>\n<h3 id=\"h.6e1lf2wd89tb\" class=\"c12\"><span class=\"ez-toc-section\" id=\"Consequences_of_Committing_a_Type_1_Error-2\"><\/span><span class=\"c16 c0\">Consequences of Committing a Type 1 Error<\/span><span class=\"ez-toc-section-end\"><\/span><\/h3>\n<ol class=\"c5 lst-kix_u68hmniakuij-0 start\" start=\"1\">\n<li class=\"c3 c11 li-bullet-0\"><span class=\"c1 c0\">Failing to recognize a genuinely better strategy can result in missed opportunities for increased revenue, customer engagement, or other key metrics.<\/span><\/li>\n<li class=\"c3 c11 li-bullet-0\"><span class=\"c1 c0\">Sticking with an outdated or less effective strategy can lead to stagnation and inhibit growth.<\/span><\/li>\n<li class=\"c3 c11 li-bullet-0\"><span class=\"c1 c0\">While you continue to invest in a less effective strategy, you&#8217;re not allocating resources to more impactful initiatives.<\/span><\/li>\n<li class=\"c3 c11 li-bullet-0\"><span class=\"c0\">Market Lag: Failing to implement beneficial changes can result in falling behind, especially if competitors are more agile in testing and implementation.<\/span><\/li>\n<\/ol>\n<h3 id=\"h.lw7coad5d39x\" class=\"c12\"><span class=\"ez-toc-section\" id=\"How_to_minimize_type_2_errors\"><\/span><span class=\"c16 c0\">How to minimize type 2 errors<\/span><span class=\"ez-toc-section-end\"><\/span><\/h3>\n<p class=\"c3\"><span class=\"c1 c0\">While we&#8217;ve talked about how to minimize the chances of Type 1 errors, it&#8217;s also crucial to address Type II error risk.<\/span><\/p>\n<ol class=\"c5 lst-kix_89o3by7lzjrs-0 start\" start=\"1\">\n<li class=\"c3 c11 li-bullet-0\"><span class=\"c9\">Extend the Testing Duration<\/span><span class=\"c1 c0\">: Running the test for a longer period can capture more variations and seasonality, reducing the chances of a Type 2 error.<\/span><\/li>\n<li class=\"c3 c11 li-bullet-0\"><span class=\"c9\">Adjust the Significance Level<\/span><span class=\"c1 c0\">: While lowering the \u03b1 level reduces the risk of a Type 1 error, it increases the risk of a Type 2 error. Therefore, a balanced approach to setting \u03b1 is essential.<\/span><\/li>\n<li class=\"c3 c11 li-bullet-0\"><span class=\"c9\">Use a One-Tailed Test<\/span><span class=\"c1 c0\">: If applicable, using a one-tailed test can increase the test&#8217;s power, thereby reducing the likelihood of a Type 2 error.<\/span><\/li>\n<li class=\"c3 c11 li-bullet-0\"><span class=\"c9\">Pre-Test Analysis<\/span><span class=\"c1 c0\">: Conducting a power analysis before the test can help you determine the required sample size to minimize \u03b2.<\/span><\/li>\n<\/ol>\n<h2 id=\"h.j9o06rb7o9p1\" class=\"c7\"><span class=\"ez-toc-section\" id=\"Frequently_Ask_Questions\"><\/span><span class=\"c0 c10\">Frequently Ask Questions<\/span><span class=\"ez-toc-section-end\"><\/span><\/h2>\n<h3 id=\"h.txtpqotvrehz\" class=\"c12\"><span class=\"ez-toc-section\" id=\"How_do_Type_1_and_Type_2_errors_differ_from_each_other\"><\/span><span class=\"c16 c0\">How do Type 1 and Type 2 errors differ from each other?<\/span><span class=\"ez-toc-section-end\"><\/span><\/h3>\n<p class=\"c3\"><span class=\"c1 c0\">Type 1 and Type 2 errors are like two sides of the same coin, but they&#8217;re different in crucial ways. A Type 1 error, or false positive, happens when you think you&#8217;ve found a winner in your A\/B test, but it&#8217;s a false alarm. You ditch your old strategy for a new one that&#8217;s not better.<\/span><\/p>\n<p class=\"c3\"><span class=\"c1 c0\">A Type 2 error, or false negative, is the opposite. It&#8217;s like not recognizing a winning lottery ticket when you see one. You stick with your old strategy when the new one could have been a game-changer.<\/span><\/p>\n<h3 id=\"h.frve6apksxxt\" class=\"c12\"><span class=\"ez-toc-section\" id=\"What_is_the_significance_level_and_how_does_it_relate_to_Type_1_errors\"><\/span><span class=\"c0 c16\">What is the significance level, and how does it relate to Type 1 errors?<\/span><span class=\"ez-toc-section-end\"><\/span><\/h3>\n<p class=\"c3\"><span class=\"c1 c0\">The significance level, often denoted by \u03b1, is like your safety net in A\/B testing. It&#8217;s a number between 0 and 1 that you set before running the test, and it helps you decide how much risk you&#8217;re willing to take with a Type 1 error.<\/span><\/p>\n<p class=\"c3\"><span class=\"c1 c0\">The lower you set \u03b1, the less likely you are to make a Type 1 error. However, setting it too low might make it harder to detect real improvements.<\/span><\/p>\n<h3 id=\"h.hlk7k48z4pxo\" class=\"c12\"><span class=\"ez-toc-section\" id=\"What_is_statistical_power_and_how_does_it_relate_to_Type_2_errors\"><\/span><span class=\"c16 c0\">What is statistical power, and how does it relate to Type 2 errors?<\/span><span class=\"ez-toc-section-end\"><\/span><\/h3>\n<p class=\"c3\"><span class=\"c1 c0\">Statistical power is your test&#8217;s ability to spot a real difference when there is one. In A\/B testing, it&#8217;s represented as 1\u2212\u03b2, where \u03b2 is the probability of making a Type 2 error.<\/span><\/p>\n<p class=\"c3\"><span class=\"c1 c0\">Higher statistical power means you&#8217;re less likely to make a Type 2 error, so you won&#8217;t miss out on implementing a strategy that could be better.<\/span><\/p>\n","protected":false},"excerpt":{"rendered":"<p>Imagine you&#8217;re a marketer testing two different email subject lines to see which one gets more opens. It&#8217;s like choosing between two doors\u2014one leads to a room full of engaged customers, and the other, well, let&#8217;s just say it&#8217;s not where you want to be. Making the wrong choice could mean missing out on valuable<\/p>\n","protected":false},"author":9,"featured_media":3605,"comment_status":"closed","ping_status":"open","sticky":false,"template":"","format":"standard","meta":{"_eb_attr":"","footnotes":""},"categories":[2],"tags":[],"class_list":{"0":"post-3492","1":"post","2":"type-post","3":"status-publish","4":"format-standard","5":"has-post-thumbnail","7":"category-ab-testing"},"yoast_head":"<!-- This site is optimized with the Yoast SEO plugin v25.3.1 - https:\/\/yoast.com\/wordpress\/plugins\/seo\/ -->\n<title>What are Type 1 and Type 2 Errors in A\/B Testing? - FigPii blog<\/title>\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.figpii.com\/blog\/type-1-and-type-2-errors-in-a-b-testing\/\" \/>\n<meta property=\"og:locale\" content=\"en_US\" \/>\n<meta property=\"og:type\" content=\"article\" \/>\n<meta property=\"og:title\" content=\"What are Type 1 and Type 2 Errors in A\/B Testing? - FigPii blog\" \/>\n<meta property=\"og:description\" content=\"Imagine you&#8217;re a marketer testing two different email subject lines to see which one gets more opens. It&#8217;s like choosing between two doors\u2014one leads to a room full of engaged customers, and the other, well, let&#8217;s just say it&#8217;s not where you want to be. Making the wrong choice could mean missing out on valuable\" \/>\n<meta property=\"og:url\" content=\"https:\/\/www.figpii.com\/blog\/type-1-and-type-2-errors-in-a-b-testing\/\" \/>\n<meta property=\"og:site_name\" content=\"FigPii blog\" \/>\n<meta property=\"article:publisher\" content=\"https:\/\/www.facebook.com\/figpii.aii\/\" \/>\n<meta property=\"article:published_time\" content=\"2023-11-01T14:37:54+00:00\" \/>\n<meta property=\"article:modified_time\" content=\"2025-02-04T13:17:54+00:00\" \/>\n<meta property=\"og:image\" content=\"https:\/\/www.figpii.com\/blog\/wp-content\/uploads\/2023\/02\/1-1024x575.png\" \/>\n\t<meta property=\"og:image:width\" content=\"1024\" \/>\n\t<meta property=\"og:image:height\" content=\"575\" \/>\n\t<meta property=\"og:image:type\" content=\"image\/png\" \/>\n<meta name=\"author\" content=\"Usman Adepoju\" \/>\n<meta name=\"twitter:card\" content=\"summary_large_image\" \/>\n<meta name=\"twitter:creator\" content=\"@figpii\" \/>\n<meta name=\"twitter:site\" content=\"@figpii\" \/>\n<meta name=\"twitter:label1\" content=\"Written by\" \/>\n\t<meta name=\"twitter:data1\" content=\"Usman Adepoju\" \/>\n\t<meta name=\"twitter:label2\" content=\"Est. reading time\" \/>\n\t<meta name=\"twitter:data2\" content=\"8 minutes\" \/>\n<script type=\"application\/ld+json\" class=\"yoast-schema-graph\">{\"@context\":\"https:\/\/schema.org\",\"@graph\":[{\"@type\":\"Article\",\"@id\":\"https:\/\/www.figpii.com\/blog\/type-1-and-type-2-errors-in-a-b-testing\/#article\",\"isPartOf\":{\"@id\":\"https:\/\/www.figpii.com\/blog\/type-1-and-type-2-errors-in-a-b-testing\/\"},\"author\":{\"name\":\"Usman Adepoju\",\"@id\":\"https:\/\/www.figpii.com\/blog\/#\/schema\/person\/ed6908a6c1d884db14e9c28fc837b5ec\"},\"headline\":\"What are Type 1 and Type 2 Errors in A\/B Testing?\",\"datePublished\":\"2023-11-01T14:37:54+00:00\",\"dateModified\":\"2025-02-04T13:17:54+00:00\",\"mainEntityOfPage\":{\"@id\":\"https:\/\/www.figpii.com\/blog\/type-1-and-type-2-errors-in-a-b-testing\/\"},\"wordCount\":1599,\"publisher\":{\"@id\":\"https:\/\/www.figpii.com\/blog\/#organization\"},\"image\":{\"@id\":\"https:\/\/www.figpii.com\/blog\/type-1-and-type-2-errors-in-a-b-testing\/#primaryimage\"},\"thumbnailUrl\":\"https:\/\/www.figpii.com\/blog\/wp-content\/uploads\/2023\/02\/1.png\",\"articleSection\":[\"AB testing\"],\"inLanguage\":\"en-US\"},{\"@type\":\"WebPage\",\"@id\":\"https:\/\/www.figpii.com\/blog\/type-1-and-type-2-errors-in-a-b-testing\/\",\"url\":\"https:\/\/www.figpii.com\/blog\/type-1-and-type-2-errors-in-a-b-testing\/\",\"name\":\"What are Type 1 and Type 2 Errors in A\/B Testing? - FigPii blog\",\"isPartOf\":{\"@id\":\"https:\/\/www.figpii.com\/blog\/#website\"},\"primaryImageOfPage\":{\"@id\":\"https:\/\/www.figpii.com\/blog\/type-1-and-type-2-errors-in-a-b-testing\/#primaryimage\"},\"image\":{\"@id\":\"https:\/\/www.figpii.com\/blog\/type-1-and-type-2-errors-in-a-b-testing\/#primaryimage\"},\"thumbnailUrl\":\"https:\/\/www.figpii.com\/blog\/wp-content\/uploads\/2023\/02\/1.png\",\"datePublished\":\"2023-11-01T14:37:54+00:00\",\"dateModified\":\"2025-02-04T13:17:54+00:00\",\"breadcrumb\":{\"@id\":\"https:\/\/www.figpii.com\/blog\/type-1-and-type-2-errors-in-a-b-testing\/#breadcrumb\"},\"inLanguage\":\"en-US\",\"potentialAction\":[{\"@type\":\"ReadAction\",\"target\":[\"https:\/\/www.figpii.com\/blog\/type-1-and-type-2-errors-in-a-b-testing\/\"]}]},{\"@type\":\"ImageObject\",\"inLanguage\":\"en-US\",\"@id\":\"https:\/\/www.figpii.com\/blog\/type-1-and-type-2-errors-in-a-b-testing\/#primaryimage\",\"url\":\"https:\/\/www.figpii.com\/blog\/wp-content\/uploads\/2023\/02\/1.png\",\"contentUrl\":\"https:\/\/www.figpii.com\/blog\/wp-content\/uploads\/2023\/02\/1.png\",\"width\":1560,\"height\":876},{\"@type\":\"BreadcrumbList\",\"@id\":\"https:\/\/www.figpii.com\/blog\/type-1-and-type-2-errors-in-a-b-testing\/#breadcrumb\",\"itemListElement\":[{\"@type\":\"ListItem\",\"position\":1,\"name\":\"Home\",\"item\":\"https:\/\/www.figpii.com\/blog\/\"},{\"@type\":\"ListItem\",\"position\":2,\"name\":\"What are Type 1 and Type 2 Errors in A\/B Testing?\"}]},{\"@type\":\"WebSite\",\"@id\":\"https:\/\/www.figpii.com\/blog\/#website\",\"url\":\"https:\/\/www.figpii.com\/blog\/\",\"name\":\"FigPii blog\",\"description\":\"Let it marinate\",\"publisher\":{\"@id\":\"https:\/\/www.figpii.com\/blog\/#organization\"},\"potentialAction\":[{\"@type\":\"SearchAction\",\"target\":{\"@type\":\"EntryPoint\",\"urlTemplate\":\"https:\/\/www.figpii.com\/blog\/?s={search_term_string}\"},\"query-input\":{\"@type\":\"PropertyValueSpecification\",\"valueRequired\":true,\"valueName\":\"search_term_string\"}}],\"inLanguage\":\"en-US\"},{\"@type\":\"Organization\",\"@id\":\"https:\/\/www.figpii.com\/blog\/#organization\",\"name\":\"FigPii\",\"url\":\"https:\/\/www.figpii.com\/blog\/\",\"logo\":{\"@type\":\"ImageObject\",\"inLanguage\":\"en-US\",\"@id\":\"https:\/\/www.figpii.com\/blog\/#\/schema\/logo\/image\/\",\"url\":\"https:\/\/www.figpii.com\/blog\/wp-content\/uploads\/2023\/09\/figpii-logo-purple.png\",\"contentUrl\":\"https:\/\/www.figpii.com\/blog\/wp-content\/uploads\/2023\/09\/figpii-logo-purple.png\",\"width\":104,\"height\":40,\"caption\":\"FigPii\"},\"image\":{\"@id\":\"https:\/\/www.figpii.com\/blog\/#\/schema\/logo\/image\/\"},\"sameAs\":[\"https:\/\/www.facebook.com\/figpii.aii\/\",\"https:\/\/x.com\/figpii\"]},{\"@type\":\"Person\",\"@id\":\"https:\/\/www.figpii.com\/blog\/#\/schema\/person\/ed6908a6c1d884db14e9c28fc837b5ec\",\"name\":\"Usman Adepoju\",\"image\":{\"@type\":\"ImageObject\",\"inLanguage\":\"en-US\",\"@id\":\"https:\/\/www.figpii.com\/blog\/#\/schema\/person\/image\/\",\"url\":\"https:\/\/secure.gravatar.com\/avatar\/bbdd3896b2f568a544af94603f54223cfb9b91c41a1365212f8ffecc6006951e?s=96&d=mm&r=g\",\"contentUrl\":\"https:\/\/secure.gravatar.com\/avatar\/bbdd3896b2f568a544af94603f54223cfb9b91c41a1365212f8ffecc6006951e?s=96&d=mm&r=g\",\"caption\":\"Usman Adepoju\"},\"url\":\"https:\/\/www.figpii.com\/blog\/author\/usman\/\"}]}<\/script>\n<!-- \/ Yoast SEO plugin. -->","yoast_head_json":{"title":"What are Type 1 and Type 2 Errors in A\/B Testing? - FigPii blog","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.figpii.com\/blog\/type-1-and-type-2-errors-in-a-b-testing\/","og_locale":"en_US","og_type":"article","og_title":"What are Type 1 and Type 2 Errors in A\/B Testing? - FigPii blog","og_description":"Imagine you&#8217;re a marketer testing two different email subject lines to see which one gets more opens. It&#8217;s like choosing between two doors\u2014one leads to a room full of engaged customers, and the other, well, let&#8217;s just say it&#8217;s not where you want to be. Making the wrong choice could mean missing out on valuable","og_url":"https:\/\/www.figpii.com\/blog\/type-1-and-type-2-errors-in-a-b-testing\/","og_site_name":"FigPii blog","article_publisher":"https:\/\/www.facebook.com\/figpii.aii\/","article_published_time":"2023-11-01T14:37:54+00:00","article_modified_time":"2025-02-04T13:17:54+00:00","og_image":[{"width":1024,"height":575,"url":"https:\/\/www.figpii.com\/blog\/wp-content\/uploads\/2023\/02\/1-1024x575.png","type":"image\/png"}],"author":"Usman Adepoju","twitter_card":"summary_large_image","twitter_creator":"@figpii","twitter_site":"@figpii","twitter_misc":{"Written by":"Usman Adepoju","Est. reading time":"8 minutes"},"schema":{"@context":"https:\/\/schema.org","@graph":[{"@type":"Article","@id":"https:\/\/www.figpii.com\/blog\/type-1-and-type-2-errors-in-a-b-testing\/#article","isPartOf":{"@id":"https:\/\/www.figpii.com\/blog\/type-1-and-type-2-errors-in-a-b-testing\/"},"author":{"name":"Usman Adepoju","@id":"https:\/\/www.figpii.com\/blog\/#\/schema\/person\/ed6908a6c1d884db14e9c28fc837b5ec"},"headline":"What are Type 1 and Type 2 Errors in A\/B Testing?","datePublished":"2023-11-01T14:37:54+00:00","dateModified":"2025-02-04T13:17:54+00:00","mainEntityOfPage":{"@id":"https:\/\/www.figpii.com\/blog\/type-1-and-type-2-errors-in-a-b-testing\/"},"wordCount":1599,"publisher":{"@id":"https:\/\/www.figpii.com\/blog\/#organization"},"image":{"@id":"https:\/\/www.figpii.com\/blog\/type-1-and-type-2-errors-in-a-b-testing\/#primaryimage"},"thumbnailUrl":"https:\/\/www.figpii.com\/blog\/wp-content\/uploads\/2023\/02\/1.png","articleSection":["AB testing"],"inLanguage":"en-US"},{"@type":"WebPage","@id":"https:\/\/www.figpii.com\/blog\/type-1-and-type-2-errors-in-a-b-testing\/","url":"https:\/\/www.figpii.com\/blog\/type-1-and-type-2-errors-in-a-b-testing\/","name":"What are Type 1 and Type 2 Errors in A\/B Testing? - FigPii blog","isPartOf":{"@id":"https:\/\/www.figpii.com\/blog\/#website"},"primaryImageOfPage":{"@id":"https:\/\/www.figpii.com\/blog\/type-1-and-type-2-errors-in-a-b-testing\/#primaryimage"},"image":{"@id":"https:\/\/www.figpii.com\/blog\/type-1-and-type-2-errors-in-a-b-testing\/#primaryimage"},"thumbnailUrl":"https:\/\/www.figpii.com\/blog\/wp-content\/uploads\/2023\/02\/1.png","datePublished":"2023-11-01T14:37:54+00:00","dateModified":"2025-02-04T13:17:54+00:00","breadcrumb":{"@id":"https:\/\/www.figpii.com\/blog\/type-1-and-type-2-errors-in-a-b-testing\/#breadcrumb"},"inLanguage":"en-US","potentialAction":[{"@type":"ReadAction","target":["https:\/\/www.figpii.com\/blog\/type-1-and-type-2-errors-in-a-b-testing\/"]}]},{"@type":"ImageObject","inLanguage":"en-US","@id":"https:\/\/www.figpii.com\/blog\/type-1-and-type-2-errors-in-a-b-testing\/#primaryimage","url":"https:\/\/www.figpii.com\/blog\/wp-content\/uploads\/2023\/02\/1.png","contentUrl":"https:\/\/www.figpii.com\/blog\/wp-content\/uploads\/2023\/02\/1.png","width":1560,"height":876},{"@type":"BreadcrumbList","@id":"https:\/\/www.figpii.com\/blog\/type-1-and-type-2-errors-in-a-b-testing\/#breadcrumb","itemListElement":[{"@type":"ListItem","position":1,"name":"Home","item":"https:\/\/www.figpii.com\/blog\/"},{"@type":"ListItem","position":2,"name":"What are Type 1 and Type 2 Errors in A\/B Testing?"}]},{"@type":"WebSite","@id":"https:\/\/www.figpii.com\/blog\/#website","url":"https:\/\/www.figpii.com\/blog\/","name":"FigPii blog","description":"Let it marinate","publisher":{"@id":"https:\/\/www.figpii.com\/blog\/#organization"},"potentialAction":[{"@type":"SearchAction","target":{"@type":"EntryPoint","urlTemplate":"https:\/\/www.figpii.com\/blog\/?s={search_term_string}"},"query-input":{"@type":"PropertyValueSpecification","valueRequired":true,"valueName":"search_term_string"}}],"inLanguage":"en-US"},{"@type":"Organization","@id":"https:\/\/www.figpii.com\/blog\/#organization","name":"FigPii","url":"https:\/\/www.figpii.com\/blog\/","logo":{"@type":"ImageObject","inLanguage":"en-US","@id":"https:\/\/www.figpii.com\/blog\/#\/schema\/logo\/image\/","url":"https:\/\/www.figpii.com\/blog\/wp-content\/uploads\/2023\/09\/figpii-logo-purple.png","contentUrl":"https:\/\/www.figpii.com\/blog\/wp-content\/uploads\/2023\/09\/figpii-logo-purple.png","width":104,"height":40,"caption":"FigPii"},"image":{"@id":"https:\/\/www.figpii.com\/blog\/#\/schema\/logo\/image\/"},"sameAs":["https:\/\/www.facebook.com\/figpii.aii\/","https:\/\/x.com\/figpii"]},{"@type":"Person","@id":"https:\/\/www.figpii.com\/blog\/#\/schema\/person\/ed6908a6c1d884db14e9c28fc837b5ec","name":"Usman Adepoju","image":{"@type":"ImageObject","inLanguage":"en-US","@id":"https:\/\/www.figpii.com\/blog\/#\/schema\/person\/image\/","url":"https:\/\/secure.gravatar.com\/avatar\/bbdd3896b2f568a544af94603f54223cfb9b91c41a1365212f8ffecc6006951e?s=96&d=mm&r=g","contentUrl":"https:\/\/secure.gravatar.com\/avatar\/bbdd3896b2f568a544af94603f54223cfb9b91c41a1365212f8ffecc6006951e?s=96&d=mm&r=g","caption":"Usman Adepoju"},"url":"https:\/\/www.figpii.com\/blog\/author\/usman\/"}]}},"_links":{"self":[{"href":"https:\/\/www.figpii.com\/blog\/wp-json\/wp\/v2\/posts\/3492","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/www.figpii.com\/blog\/wp-json\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/www.figpii.com\/blog\/wp-json\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/www.figpii.com\/blog\/wp-json\/wp\/v2\/users\/9"}],"replies":[{"embeddable":true,"href":"https:\/\/www.figpii.com\/blog\/wp-json\/wp\/v2\/comments?post=3492"}],"version-history":[{"count":8,"href":"https:\/\/www.figpii.com\/blog\/wp-json\/wp\/v2\/posts\/3492\/revisions"}],"predecessor-version":[{"id":5404,"href":"https:\/\/www.figpii.com\/blog\/wp-json\/wp\/v2\/posts\/3492\/revisions\/5404"}],"wp:featuredmedia":[{"embeddable":true,"href":"https:\/\/www.figpii.com\/blog\/wp-json\/wp\/v2\/media\/3605"}],"wp:attachment":[{"href":"https:\/\/www.figpii.com\/blog\/wp-json\/wp\/v2\/media?parent=3492"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/www.figpii.com\/blog\/wp-json\/wp\/v2\/categories?post=3492"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/www.figpii.com\/blog\/wp-json\/wp\/v2\/tags?post=3492"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}