Visitas: 112
To Lie With Statistics
Is it feasible to lie with statistics?
The common man or the unprepared reader will surely assume that statistics is a discipline that adds and deploys a mantle of “sacred” veracity to every measurable or classifiable fact arising from diverse experiences, including those facts from everyday life.
The lie has existed, exists and will exist as long as someone presumes that they can achieve some benefit from it. Lying crosses all social and cultural strata, including science, and there are many who have a greater or lesser degree of interest in telling lies.
Although it may seem improbable, it is feasible to lie with statistics: It is possible to verify this assertion just by stopping to analyze the information provided by the media that accommodate data, often diametrically opposed depending on the particular interest of one or the other. To verify this, just open a newspaper, tune in to the radio or turn on the television, for example, after a “massive” party demonstration.
One media may claim that 100,000 individuals participated, while another, will say that the call reached 10,000 people, the police may point out that 20,000 attended, while the organizers could ensure a resounding success of such mobilization by going up. the bet on 250 thousand protesters. So; Who do we believe? where is the truth? who lies?
In any activity, including science, information can be lied or manipulated by resorting to statistics; presenting data in a misleading (biased) manner in order to defend a particular argument or conclusion. Although statistics is a powerful and objective tool when analyzing and communicating information, the way it is presented or interpreted can be influenced by malicious purposes.
There are many ways that can be used to lie using statistics. Here they are listed in no strict order of appearance or importance:
- Bias in the selection of data: presenting only those that support a certain conclusion, omitting information that could refute it
- Establish correlation without evidence of causality: Establish a causal relationship between two variables only because there is a correlation between them and not consider other possible explanations or factors that may be influencing said relationship.
- Inappropriate use of statistical terms: Handling statistical terms incorrectly to give the impression of validity and authority.
- Use of inappropriate scales: which may distort the perception of the data.
- Deceptive graphical presentation: manipulating scales on graphs in order to minimize or exaggerate differences
- Invalid extrapolation: Making inferences based on a limited number of data
- Inadequate sample size: Generalizing conclusions from a small, non-representative sample
- Lack of context: Present data and draw conclusions without carrying out a common thread aligned with the objectives and results of the study.
It is extremely important to keep in mind that these types of practices exist and to be wary of these possible manipulations when reviewing statistics or data from reports, media, political, religious speeches, etc. When consuming information, we must acquire a critical spirit and meticulously analyze the source and the methodology used to ensure an accurate and objective understanding of the data presented. Likewise, as professionals who use statistics, we must strive to present data transparently, honestly, and without bias, to maintain the integrity of research and scientific communication.
As a reference on this topic, it is worth mentioning a valuable, entertaining and at the same time concise book by Darrell Huff that deals with the subject in a plain and concrete way and whose introductory chapter we transcribe literally from its English version.
How to lie with statistics
INTRODUCTION
“There is a mighty lot of crime around here”, said my father-in-law a little while after he moved from Iowa to California. And so there was -in the newspaper he read. It is one that overlooks no crime in its own area and has been known to give more attention to an Iowa murder than was given by the principal daily in the region in which it took place.
My father-in-law’s conclusion was statistical in an informal way. It was based on a sample, a remarkably biased one. Like many a more sophisticated statistic it was guilty of semi-attachment. It assumed that newspaper space given to crime reporting is a measure of crime rate.
A few winters ago, a dozen investigators independently reported figures on antihistamine pills. Each showed that a considerable percentage of cold cleared up after treatment. A great fuss ensued, at least in the advertisements, and a medical-product boom was on. It was based on an eternally springing hope and also on a curious refusal to look past the statistics to a fact that has been known for long time. As Henry G Felsen, a humoristic and no medical authority pointed out quite a while ago, proper treatment will cure a cold in seven days, but left to itself a cold will hang on for a week.
So, it is with much that you read and hear. Averages and relationships and trends and graphs are not always what they seem. There may be more in them that meets the eye, and there may be a good deal less.
The secret language of statistics, so appealing in a fact-minded culture, is employed to sensationalize, inflate, confuse, and oversimplify. Statistical methods and statistical terms are necessary in reporting the mass data of social and economic trends, business conditions, “opinion” poll, the census. But without writers who use the words with honesty and understanding and readers who know what they mean, the results can only be semantic nonsense.
In popular writing on scientific matters the abused statistic is almost crowding out the picture of the white-jacketed hero laboring overtime without time-and-a-half in an ill-lit laboratory. Like the “little-dash of power, little-pot of pain” statistics are making many important fact “look like what she ain’t” A well-wrapped statist is better than Hitler’s “big lie”, it misleads, yet it cannot be pinned on you.
This book is a sort of primer in ways to use the statistics to deceive. It may seem altogether too much like a manual for swindlers. Perhaps I can justify it in the manner of the retired burglar whose published reminiscences amounted to a graduate course in how to pick a lock and muffle a football: The crooks already know these tricks; honest men must learn them in self-defense
References
Darrell Huff. How to lie with statistics. WW Norton & Company. Inc. New York-London. 1954. ISBN 0 393 09426.