{"id":3546,"date":"2019-02-01T11:30:44","date_gmt":"2019-02-01T06:00:44","guid":{"rendered":"https:\/\/sketharaman.com\/blog\/?p=3546"},"modified":"2022-02-24T15:34:16","modified_gmt":"2022-02-24T10:04:16","slug":"three-ways-to-lie-with-charts","status":"publish","type":"post","link":"https:\/\/sketharaman.com\/blog\/2019\/02\/01\/three-ways-to-lie-with-charts\/","title":{"rendered":"Three Ways To Lie With Charts"},"content":{"rendered":"<p>Lying with charts is the natural progression from <a href=\"https:\/\/gtm360.com\/blog\/2014\/12\/19\/how-to-lie-with-big-data\/\" target=\"_blank\" rel=\"noopener\"><strong>Lying With Big Data<\/strong><\/a> and\u00a0<a href=\"https:\/\/gtm360.com\/blog\/2018\/05\/25\/pixie-dust-sampling-or-how-to-commit-harakiri-by-lying-with-big-data\/\" target=\"_blank\" rel=\"noopener\"><strong>Pixie Dust Sampling \u2013 Or How To Commit Harakiri By Lying With Big Data<\/strong><\/a>.<\/p>\n<p><a href=\"https:\/\/gtm360.com\/blog\/wp-content\/uploads\/2019\/01\/3-ways-lie-charts-fi.jpg\" target=\"_blank\" rel=\"noopener\"><img loading=\"lazy\" decoding=\"async\" class=\"alignnone wp-image-5709 size-full\" src=\"https:\/\/gtm360.com\/blog\/wp-content\/uploads\/2019\/01\/3-ways-lie-charts-fi.jpg\" alt=\"\" width=\"630\" height=\"280\" \/><\/a><\/p>\n<p>I have come across the three ways of doing that.<\/p>\n<p><strong>#1. SLIPPERY SLOPE SLIDE<\/strong><\/p>\n<p>There are charts that gyrate up and down for no apparent reason other than that they were probably caught in a slippery slope.<\/p>\n<p>Here&#8217;s an example of such a chart (Exhibit 1).<\/p>\n<figure id=\"attachment_5686\" aria-describedby=\"caption-attachment-5686\" style=\"width: 300px\" class=\"wp-caption alignnone\"><a href=\"https:\/\/gtm360.com\/blog\/wp-content\/uploads\/2019\/01\/TYPO-LYING-BIG-DATA-ET-CHART-NO-CHANGE-NOSEDIVE.jpg\" target=\"_blank\" rel=\"noopener\"><img loading=\"lazy\" decoding=\"async\" class=\"wp-image-5686\" src=\"https:\/\/gtm360.com\/blog\/wp-content\/uploads\/2019\/01\/TYPO-LYING-BIG-DATA-ET-CHART-NO-CHANGE-NOSEDIVE.jpg\" alt=\"\" width=\"300\" height=\"362\" \/><\/a><figcaption id=\"caption-attachment-5686\" class=\"wp-caption-text\">EXHIBIT 1<\/figcaption><\/figure>\n<p>Although the price of the company&#8217;s share was INR 256.3 on both the first and the last day of the period covered by the chart, the chart somehow takes a nosedive.<\/p>\n<p>Likely the handiwork of some pump-and-dump operator?<\/p>\n<p><strong>#2. FLOATING ORIGIN FRAUD<\/strong><\/p>\n<p>Darrell Huff showed how statisticians mislead people by changing the origin of charts in his 1954 classic <a href=\"https:\/\/www.amazon.com\/How-Lie-Statistics-Darrell-Huff\/dp\/0393310728\" target=\"_blank\" rel=\"noopener\"><strong>How To Lie With Statistics<\/strong><\/a>.<\/p>\n<p>Although the book is nearly 60 years old, this tactic is widely used even today &#8211; well after the jargon has changed from statisticians to data scientists.<\/p>\n<p><em>Fortune\u00a0<\/em>recently published the following chart (Exhibit 2) on &#8220;cord cutting&#8221;, the relatively new trend of people disconnecting their cable connections and getting their TV content from streaming sites like Netflix, Amazon Prime, Disney \/ Hotstar, <em>et al<\/em>.<\/p>\n<figure id=\"attachment_2660\" aria-describedby=\"caption-attachment-2660\" style=\"width: 300px\" class=\"wp-caption alignnone\"><a href=\"https:\/\/gtm360.com\/blog\/wp-content\/uploads\/2015\/09\/FORTUNE-CORD-CUT-GRAPH.jpg\" target=\"_blank\" rel=\"noopener\"><img loading=\"lazy\" decoding=\"async\" class=\"wp-image-2660\" src=\"https:\/\/gtm360.com\/blog\/wp-content\/uploads\/2015\/09\/FORTUNE-CORD-CUT-GRAPH.jpg\" alt=\"\" width=\"300\" height=\"505\" \/><\/a><figcaption id=\"caption-attachment-2660\" class=\"wp-caption-text\">EXHIBIT 2<\/figcaption><\/figure>\n<p>Anyone taking a quick glance at this chart would see the curve taking a nosedive and totally believe the article&#8217;s claim that cord cutting is killing cable TV.<\/p>\n<p>However, this is far from the truth.\u00a0The chart conveys the article&#8217;s misleading claim by shifting the origin of the vertical axis from 0% to 78%.<\/p>\n<p>If we shift the Y-axis origin to 0%, which is where it belongs, we get a different picture (Exhibit 3):<\/p>\n<figure id=\"attachment_6187\" aria-describedby=\"caption-attachment-6187\" style=\"width: 300px\" class=\"wp-caption alignnone\"><a href=\"https:\/\/gtm360.com\/blog\/wp-content\/uploads\/2019\/02\/not-cutting-cord-2.jpg\" target=\"_blank\" rel=\"noopener\"><img loading=\"lazy\" decoding=\"async\" class=\"wp-image-6187\" src=\"https:\/\/gtm360.com\/blog\/wp-content\/uploads\/2019\/02\/not-cutting-cord-2.jpg\" alt=\"\" width=\"300\" height=\"371\" \/><\/a><figcaption id=\"caption-attachment-6187\" class=\"wp-caption-text\">EXHIBIT 3<\/figcaption><\/figure>\n<p>Visually, the impact of of cord cutting on cable TV appears small.<\/p>\n<p>For the quants among you,\u00a082.1% of US households had cable TV five years ago. 79% of them still did so in 2014. The drop in cable TV penetration is 3.1 percentage points over five years i.e. CAGR of -0.77% p.a. That&#8217;s not life-threatening by any stretch of imagination.<\/p>\n<p>Let&#8217;s place the two charts side-by-side (Exhibit 4).<\/p>\n<figure id=\"attachment_5682\" aria-describedby=\"caption-attachment-5682\" style=\"width: 500px\" class=\"wp-caption alignnone\"><a href=\"https:\/\/gtm360.com\/blog\/wp-content\/uploads\/2019\/01\/FORTUNE-CORD-CUTTING-TRUTH-CHART.jpg\" target=\"_blank\" rel=\"noopener\"><img loading=\"lazy\" decoding=\"async\" class=\"wp-image-5682\" src=\"https:\/\/gtm360.com\/blog\/wp-content\/uploads\/2019\/01\/FORTUNE-CORD-CUTTING-TRUTH-CHART.jpg\" alt=\"\" width=\"500\" height=\"331\" \/><\/a><figcaption id=\"caption-attachment-5682\" class=\"wp-caption-text\">EXHIBIT 4<\/figcaption><\/figure>\n<p>Now you get the real picture and can appreciate just how much misleading was done by the original chart in the article.<\/p>\n<p><strong>#3. DUAL AXIS DECEPTION<\/strong><\/p>\n<p>This is a relatively new tactic.<\/p>\n<p>I saw the first example of it in this <a href=\"https:\/\/twitter.com\/zackvoell\/status\/1058018550122770433\" target=\"_blank\" rel=\"noopener\"><strong>tweet<\/strong><\/a>, in which a cryptoenthusiast makes the following &#8220;quick comparison of Bitcoin and Fiat ATMs&#8221; (Exhibit 5).<\/p>\n<figure id=\"attachment_5683\" aria-describedby=\"caption-attachment-5683\" style=\"width: 500px\" class=\"wp-caption alignnone\"><a href=\"https:\/\/gtm360.com\/blog\/wp-content\/uploads\/2019\/01\/2AXIS-01.jpg\" target=\"_blank\" rel=\"noopener\"><img loading=\"lazy\" decoding=\"async\" class=\"wp-image-5683\" src=\"https:\/\/gtm360.com\/blog\/wp-content\/uploads\/2019\/01\/2AXIS-01.jpg\" alt=\"\" width=\"500\" height=\"304\" \/><\/a><figcaption id=\"caption-attachment-5683\" class=\"wp-caption-text\">EXHIBIT 5<\/figcaption><\/figure>\n<p>To a casual observer, it would appear that the number of Bitcoin ATMs would exceed the number of Fiat Currency ATMs by ~2019.<\/p>\n<p>Obviously, that&#8217;s not true.<\/p>\n<p>The chart misleads readers by using drastically different scales for the vertical axis on the LHS (Fiat ATM Count) versus the RHS (Bitcoin ATM Count).<\/p>\n<p>Here&#8217;s another example of this deception in the following chart comparing the value of Bitcoin versus Gold on <em>Bloomberg<\/em> (Exhibit 6).<\/p>\n<figure id=\"attachment_5694\" aria-describedby=\"caption-attachment-5694\" style=\"width: 503px\" class=\"wp-caption alignnone\"><a href=\"https:\/\/gtm360.com\/blog\/wp-content\/uploads\/2019\/01\/2AXIS-03-BLOOMERG-BITCOIN-GOLD-2.jpg\" target=\"_blank\" rel=\"noopener\"><img loading=\"lazy\" decoding=\"async\" class=\"wp-image-5694\" src=\"https:\/\/gtm360.com\/blog\/wp-content\/uploads\/2019\/01\/2AXIS-03-BLOOMERG-BITCOIN-GOLD-2.jpg\" alt=\"\" width=\"503\" height=\"300\" \/><\/a><figcaption id=\"caption-attachment-5694\" class=\"wp-caption-text\">EXHIBIT 6<\/figcaption><\/figure>\n<p>Thankfully, these charts get lampooned on social media repeatedly. Here&#8217;s a ROTFL spoof by <a href=\"https:\/\/twitter.com\/Edmund_Schuster\/status\/1058327226196860929\" target=\"_blank\" rel=\"noopener\">@Edmund_Schuster<\/a> (Exhibit 7):<\/p>\n<figure id=\"attachment_5685\" aria-describedby=\"caption-attachment-5685\" style=\"width: 499px\" class=\"wp-caption alignnone\"><a href=\"https:\/\/gtm360.com\/blog\/wp-content\/uploads\/2019\/01\/2AXIS-02-spoof.jpg\" target=\"_blank\" rel=\"noopener\"><img loading=\"lazy\" decoding=\"async\" class=\"wp-image-5685\" src=\"https:\/\/gtm360.com\/blog\/wp-content\/uploads\/2019\/01\/2AXIS-02-spoof.jpg\" alt=\"\" width=\"499\" height=\"300\" \/><\/a><figcaption id=\"caption-attachment-5685\" class=\"wp-caption-text\">EXHIBIT 7<\/figcaption><\/figure>\n<hr style=\"width: 70%;\" \/>\n<p>These are just the three ways of lying with charts that I&#8217;ve come across personally*.<\/p>\n<p>I&#8217;m sure there are more. If you know any, please share in the comments.<\/p>\n<p>The kind-hearted souls among you might argue that lying is not necessarily the culprit for the misleading charts displayed above.<\/p>\n<p>I won&#8217;t disagree with them because I can myself think of at least one non lying-related reason. But it&#8217;s arguably worse than lying.<\/p>\n<p>More on that in a follow-on post\u00a0(Spoiler Alert: It&#8217;s one of the seven deadly sins).<\/p>\n<p>* <em>Please see comments below for a few more ways of lying with charts.<\/em><\/p>\n","protected":false},"excerpt":{"rendered":"<p>Lying with charts is the natural progression from Lying With Big Data and\u00a0Pixie Dust Sampling \u2013 Or How To Commit Harakiri By Lying With Big Data. I have come across&hellip;<\/p>\n","protected":false},"author":1,"featured_media":3546,"comment_status":"open","ping_status":"open","sticky":false,"template":"","format":"standard","meta":{"footnotes":""},"categories":[5,7,1],"tags":[],"class_list":["post-3546","post","type-post","status-publish","format-standard","has-post-thumbnail","hentry","category-b1-integrated-marketing","category-bfsi","category-uncategorized"],"_links":{"self":[{"href":"https:\/\/sketharaman.com\/blog\/wp-json\/wp\/v2\/posts\/3546","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/sketharaman.com\/blog\/wp-json\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/sketharaman.com\/blog\/wp-json\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/sketharaman.com\/blog\/wp-json\/wp\/v2\/users\/1"}],"replies":[{"embeddable":true,"href":"https:\/\/sketharaman.com\/blog\/wp-json\/wp\/v2\/comments?post=3546"}],"version-history":[{"count":1,"href":"https:\/\/sketharaman.com\/blog\/wp-json\/wp\/v2\/posts\/3546\/revisions"}],"predecessor-version":[{"id":6459,"href":"https:\/\/sketharaman.com\/blog\/wp-json\/wp\/v2\/posts\/3546\/revisions\/6459"}],"wp:featuredmedia":[{"embeddable":true,"href":"https:\/\/sketharaman.com\/blog\/wp-json\/wp\/v2\/posts\/3546"}],"wp:attachment":[{"href":"https:\/\/sketharaman.com\/blog\/wp-json\/wp\/v2\/media?parent=3546"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/sketharaman.com\/blog\/wp-json\/wp\/v2\/categories?post=3546"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/sketharaman.com\/blog\/wp-json\/wp\/v2\/tags?post=3546"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}