Deceptive Statistics Assignment
- Evaluate statistics that you find, and look for statistics that are being disseminated to the public in a possible attempt to sway the reader.
- Find an article or infographic that might have reliable sources, such as Bureau of Labor and Statistics, but the information is skewed or falsified.
- Stay away from the databases and try different browsers on the Internet, because different browsers might yield different results. Google Chrome, Firefox, Bing, Yahoo!, DuckDuckgo.
“The Beauty of Data Visualization” (2010)
- Introduction: Information Visualizations and Their Deceptive Statistics Mark Newman goes over four main ways that statistics can be reported deceptively including: Misleading averages, ignoring the base rate, misleading comparisons, and correlation that does not equal causation (Newman, 2016).
Deceptive Statistics - What Are They?
- "deceit" - from Encyclopedia of Ethics Deception raises ethical problems only when communication is intended to mislead. Human beings are surrounded with innumerable sources of erroneous belief: Mirages may deceive us; our eyes and ears deceive us all the time. It is only when human beings purposely distort, withhold, or otherwise manipulate information reaching others so as to mislead them that we speak of deceit or intentional deception. Intentional deception may be nonverbal in form, as when messages are conveyed by gestures or false visual clues, or verbal. When a speaker makes a statement in the belief that it is false and with the INTENTION to mislead a listener, we speak of lies.
- How statistics can be misleading - Mark Liddell Published on Jan 14, 2016 View full lesson: http://ed.ted.com/lessons/how-statist... Statistics are persuasive. So much so that people, organizations, and whole countries base some of their most important decisions on organized data. But any set of statistics might have something lurking inside it that can turn the results completely upside down. Mark Liddell investigates Simpson’s paradox. Lesson by Mark Liddell, animation by Tinmouse Animation Studio. Category Education
- The most misleading charts of 2015, fixed - Quartz We make a lot of charts here at Quartz. We also spend a lot of time thinking and talking about charts. We have a 6,000-word guide to dealing with bad data and a treatise on properly using the y-axis. So when we see charts in the wild that use fuzzy or bad data, improperly skew axes, or are otherwise misleading, we get sad. We think, “The world is filled with good data! Why can’t everyone just use properly sourced and normalized data and present it in a straightforward way?!” So this year, we rounded up the worst offenders and corrected them.
How to Search for Deceptive Statistics Info on your Career
How to Search for Deceptive Statistics Info on your Career - Example
1.Determine what career you hope to get into and list below:
Nurse
2.Now determine broader field your career falls under:
Nurse > Health Services
3.So now search using the broader term “Health Services” and “Deceptive Statistics”
4.Do a search in Google.com using the IMAGES tab instead of a regular Google Search using these two terms.
5.Locate graphs or charts of deceptive statistics on a health issue.
6.I located the following chart from Google Images:
GOP Committee Chair Brandishes Data Promoted By Right-Wing Media At Planned Parenthood Hearing, Doesn't Realize It's From Anti-Choice Group Media Fact Checkers: Chart "Makes Absolutely No Sense" And "Has No Y-Axis"
Deceptive Statistics - 2020-2021
- Bad Infographics: The Worst Infographics of 2020 (+ Lessons for 2021)There’s a long history of people creating and using infographics, or visuals that communicate complex information. This history includes the good and the bad, but when it comes to the ugly 2020 takes the cake. As we know, 2020 was fraught with all sorts of communication challenges, including the COVID-19 pandemic, the hotly-contested U.S. Presidential Election, President Trump’s first impeachment, and increasing calls for racial justice across the globe. Last year infographics became a more regular part of public life, with charts tracking COVID-19 cases and deaths, graphs showing unemployment numbers, and maps announcing unfolding election results. Some of these visuals helped people better navigate various aspects of their daily lives, and unfortunately some increased confusion, conflict and mistrust. People like me who are professionals working in information design were at times amazed, at other times appalled.
FOOD FOR THOUGHT
- FOOD FOR THOUGHT - Why A Journalist Scammed The Media Into Spreading Bad Chocolate Science In fact, that's exactly what he did Wednesday, in a story for io9 that's gone viral. Bohannon, a science journalist who also has a Ph.D., lays out how he carried out an elaborate hoax to expose just how easily bad nutrition science gets disseminated in the mainstream media.
Misleading Graphs Real Life Examples
Determining Deceptive Statistics
The aphorism that there are "lies, damned lies, and statistics" is attributed to British statesman Benjamin Disraeli (1804–1881) and reflects the unfortunate fact that statistics can be accidentally or deliberately used to deceive just as easily as they can be used to illuminate and inform. Understanding how statistics can be accidentally or deliberately used to misrepresent data can help people to see through deceptive uses of statistics in real life.
Consider a group of four friends who graduated from the same college. Three of them earn $40,000 per year working as managers in a local factory, while the fourth earns $500,000 per year from his family's shrewd investments in the stock market. What statistic best represents the income level of the four friends? The arithmetic mean is ($40,000 + $40,000 + $40,000 + $500,000)/4 = $155,000, but in this case the arithmetic mean is not an accurate reflection of the underlying bimodal population. If anything, the median income of $40,000 is more representative of most of the group even though it does not accurately reflect the highest salary. It is likewise strictly correct to state that the incomes of the four friends range from a minimum of $40,000 to a maximum $500,000, but that simple statistic does not convey the fact that most of the friends earn the minimum amount. It would therefore be true but misleading for a university recruiter to tell prospective students that a group of its graduates earns an average of $155,000 per year or that graduates of the university earn as much as $500,000 per year. A less deceptive statement that that the group earns between $40,000 and $500,000, and that three of them earn the minimum amount (or that the mode is $40,000). But, this still does not paint an accurate picture. An even less deceptive statement would also explain that while the highest earner is indeed a graduate of that college, his income is tied to his family's investments and not necessarily related to his college education.
Correlation or Causation?
Correlation or Causation?
Some of the most common examples of real life statistics are news stories describing the results of recently published medical or economic research. A newspaper article might give details of a study showing that men and women with college degrees tend to have higher incomes than those who have never attended college. A report on the evening news might explain that researchers have found a correlation between low test scores and excessive soft drink consumption among high school students. In both cases, variables are correlated but the studies do not necessarily prove that one causes the other to occur. In other words, correlation does not necessarily imply causation.
It is easy to think of reasons why people who obtain college degrees tend to make more money than those who do not. College degrees are required for many high paying jobs in science, engineering, law, medicine, and business. College graduates also know other college graduates who can help them to get good jobs and can take advantage of on-campus interviews. People who do not attend college, in contrast, are excluded from many high paying careers and may not have the same advantages as college students. This is not to say that there are no exceptions, because someone with a college degree may choose to take a low paying job for its intrinsic satisfaction. Social workers, teachers, or artists, for example, may have college degrees but earn less money than factory workers without degrees. Likewise, some multi-millionaires and even billionaires never completed college. What about the converse? Is it possible that high earnings cause people to become college graduates? In one sense, the answer is no. People usually attend college early in life, before they begin full-time careers, so it is unlikely that high earnings cause college attendance. It also seems unlikely that someone will make a sizable amount of money and, because of that, decide to attend college. It seems safe to conclude that, all other things being equal, college degrees are likely to cause higher earnings.
The other result, showing a correlation between soft drink consumption and low test scores, may be more difficult to explain. It is difficult to imagine that soft drink consumption alone causes a chemical or biological reaction that reduces intelligence and lowers test scores. But, there may be other factors to consider. It may be that students who like soft drinks place a higher priority on instant gratification than discipline, a quality that might also cause them to spend less time studying than students who consume few soft drinks. If that is the case, then both excessive soft drink consumption and low test scores are caused by another factor such as their parents' attitudes towards delayed gratification. If so, the correlation would not reveal causation in this case.
There are several kinds of clues that can help determine if statistics are deceptive. The first is the use of only maximum or minimum values to characterize a sample or population, to the exclusion of any other statistics. Parties involved in a dispute may emphasize that reported values are as high as or as low as a certain figure without giving the range, mean, median, or mode. Or, someone hoping to use statistics to prove a point may cite a mean without mentioning the median, mode, or range. Another potential source of deception is the use of biased or misrepresentative samples, which may produce sample statistics that are not at all representative of the underlying population. Reputable statisticians will always explain how their samples were chosen.