Why don't we understand statistics? Fixed mindsets may be to blame

October 12, 2018, Frontiers
Credit: CC0 Public Domain

Unfavorable methods of teaching statistics in schools and universities may be to blame for people ignoring simple solutions to statistical problems, making them hard to solve. This can have serious consequences when applied to professional settings like court cases. Published in Frontiers in Psychology, the study shows for the first time that fixed mindsets—potentially triggered by suboptimal education curricula—lead to difficulties finding the simple solution to statistical problems.

We are faced with probabilities and statistics on a daily basis. These are most commonly presented as percentages (i.e. 10% of the population), but a more intuitive way of understanding this information—called natural frequencies—is to present it as two whole numbers (i.e. 1 in 10 people).

Does this remind you of math problems you had to try solving in school? You're not alone.

"Even though natural frequencies are much easier to understand, people are more familiar with probabilities represented by percentages because of their education," says Patrick Weber of the University of Regensburg, Germany, who led the study with colleagues Karin Binder and Stefan Krauss.

However, although people are more familiar with probabilities, it does not mean they are any better at understanding them.

"A recent meta-analysis showed the vast majority of people have difficulties solving a task presented in probability format," says Weber. "This can result in severe misjudgments when applied in professional settings."

Weber refers to a famous example of the misuse of statistics in court when the prosecution relied heavily on flawed statistical evidence presented by a medical professional. An insufficient understanding of statistical probability led to Sally Clark being wrongly convicted of the murder of her two sons, based on the misjudgment of the probability that they could have died from natural causes.

The researchers believe that people are 'blind' to probabilities—yet have a fear of changing them into simpler natural frequencies which would make them easier to understand.

"The same meta-analysis showed that when the task was presented in natural format instead of probabilities, performance rates increased from 4% to 24%," says Weber. (See below for an example task.)

But while the success rate was much higher when the data was presented as two whole numbers rather than a percentage, around three-quarters of participants still could not solve the task at all. Weber and his colleagues were keen to find out why.

They gave groups of university students different reasoning tasks, one presented in probability format and the other in natural frequency. Participants were asked to show their working so the researchers could understand their cognitive processes behind answering the questions.

They found that, when the questions were presented in natural frequencies, half the participants did not use natural frequencies to solve the problems, but instead 'translated' them into the more difficult probability format.

Weber and his team believe that a fixed mindset—known as the Einstellung effect—may explain participants' preference to change the data.

"Students are a lot more familiar with probabilities than with natural frequencies due to their education. In high school and university contexts, natural frequencies are not considered as equally mathematically valid as probabilities," says Weber.

"This means that working with probabilities is a well-established strategy when it comes to solving statistical problems," Weber continues. "While in many situations students profit from such an established strategy, the mental sets developed over a long period of time during school and university can make them 'blind' to simpler solutions—or unable to find a solution at all."

Weber and his team believe this is a widespread problem deeply rooted in school and university curricula all over the world. They do, however, recognize their study only consisted of university students which may produce different results from the general population.

"We assume that while overall solution rates might vary, the tendency to avoid using natural frequencies is widespread across the whole population," says Weber.

The researchers hope their new insights— published in a research collection on judgment and decision making under uncertainty—will encourage global change to statistical teaching strategies in schools and universities.

"We want our findings to encourage curriculum designers to incorporate natural frequencies systematically into school mathematics and statistics. This would give students a helpful tool to understand the concept of uncertainty—in addition to the 'standard' probabilities."

Example of a problem posed in probability and natural frequency format

Probability format: The probability of being addicted to heroin is 0.01% for a person randomly picked from a population (base rate). If a randomly picked person from this population is addicted to heroin, the probability is 100% that he or she will have fresh needle pricks (sensitivity). If a randomly picked person from this population is not addicted to heroin, the probability is 0.19% that he or she will still have fresh needle pricks (false alarm rate). What is the probability that a randomly picked person with fresh needle pricks is addicted to heroin (posterior probability)?

Solution: With the help of Bayes' theorem, the corresponding posterior P(H|N), with H denoting "person is addicted to heroin" and N denoting "person has fresh needle pricks", can be calculated:

P(H|N) = (P(N|H) x P(H)) / (P(N|H) x P(H) + P(N|¬H) x P(¬H)) = (100% x 0.01%) / (100% x 0.01% + 0.19% x 99.99%) = 5%

Natural frequencies format: 10 out of 100,000 people from a given population are addicted to heroin. 10 out of 10 people who are addicted to heroin will have fresh needle pricks. 190 out of 99,990 people who are not addicted to heroin will nevertheless have fresh needle pricks. What percentage of the people with fresh needle pricks is addicted to heroin?


Number of heroin addicts: 10

Number of people with needle pricks: All the heroin addicts + 190 non-addicts = 200

Percentage of people with needle pricks who are addicts = 10/200 = 5%

Explore further: Opiate addiction spreading, becoming more complex

More information: Frontiers in Psychology (2018). DOI: 10.3389/fpsyg.2018.01833 , https://www.frontiersin.org/articles/10.3389/fpsyg.2018.01833/full

Related Stories

Opiate addiction spreading, becoming more complex

August 17, 2015
The growing availability of heroin, combined with programs aimed at curbing prescription painkiller abuse, may be changing the face of opiate addiction in the U.S., according to sociologists.

High schoolers on heroin abuse other drugs, too

June 5, 2018
(HealthDay)—High school seniors hooked on heroin are likely to misuse a multitude of other drugs, a new study finds.

Practice makes perfect, but not when it comes to decisions about risk

February 13, 2012
People aren't always good at making informed decisions that involve risk, but a new study shows that even when we know the likelihood of certain outcomes based on statistical evidence or our own experiences, we still make ...

Recommended for you

Gender bias sways how we perceive competence in faces

December 7, 2018
Faces that are seen as competent are also perceived as more masculine, according to research published in Psychological Science, a journal of the Association for Psychological Science.

Internet therapy apps reduce depression symptoms, study finds

December 7, 2018
In a sweeping new study, Indiana University psychologists have found that a series of self-guided, internet-based therapy platforms effectively reduce depression.

Targeted cognitive training benefits patients with severe schizophrenia

December 7, 2018
Schizophrenia is among the most difficult mental illnesses to treat, in part because it is characterized by a wide range of dysfunction, from hallucinations and mood disorders to cognitive impairment, especially verbal and ...

Alterations in brain networks explain why some children are resilient to maltreatment

December 6, 2018
People who experience childhood maltreatment frequently have perturbations in their brain architecture, regardless of whether they develop psychiatric symptoms, but a study in Biological Psychiatry found additional alterations ...

PTSD study of combat veterans finds similar outcomes among common therapies

December 6, 2018
In a study among United States combat veterans, researchers found no significant difference between two of the most common treatments for post-traumatic stress disorder (PTSD) and no benefit for combination treatment. The ...

Infections in the young may be tied to risk for mental illness: study

December 5, 2018
Could an infection make your child or teen prone to mental health issues?

1 comment

Adjust slider to filter visible comments by rank

Display comments: newest first

3 / 5 (2) Oct 12, 2018
There are a couple problems with statistics. Most people learn how to succeed from rules of thumb. Lets say I said, "If you work hard you will succeed." Many people will disregard this advice because it is not true all the time. However we should teach rules of thumb because they work most of the time. People need something to go on. If you give children no advice, they will have nothing to go on. So my advice, give children rules of thumb.
The other problem with statistics is using statistics for political changes to government for peoples lives. So for example a person does a study and says, clearly a school room with 15 children per teacher does better than 20 children per teacher. People with political motivations will push changing the ratio of students to teacher to 15 to 1. The problem with the statistics is that it totally ignores all the other affects on society. These other affects, overall make society worse. This is why society keeps getting more unstable.

Please sign in to add a comment. Registration is free, and takes less than a minute. Read more

Click here to reset your password.
Sign in to get notified via email when new comments are made.