Regression To The Mean

Why Perfection Rarely Lasts

Whenever correlation is imperfect, and thus causation is unproven, over time the best score will get worse and the worst will get better


Towards Data Science

Regression to the mean shows that following an extreme random event, the next random event is likely to be less extreme.

The concept was first presented by Sir Francis Galton and the more comprehensive statement of regression to the mean is that:

In any series of events with complex phenomena that are dependent on many variables, and where chance is involved, extreme outcomes tend to be followed by more moderate ones.

It is not a mathematical law but a statistical tendency.



    "Regression to the mean is a common statistical phenomenon that can mislead us when we observe the world.

    Learning to recognize when regression to the mean is at play can help us avoid misinterpreting data and seeing patterns that don’t exist." [Shane Parrish]






Regression To The Mean - The Imperfect Correlation Of Factors/Causes and Chance

To be able to understand regression to the mean, we first need to understand correlation.

Correlation is a relationship, thus action A relates to outcome B.

The strength or weakness of the correlation of shared factors [or causes] will show the level of dependency of the outcome [or score] on those factors.

If the correlation is strong there will be little to no regression to the mean, whereas as a weak or non-existent correlation between shared factors will likely show that there is a regression.

Examples:

[1] Strong correlation of factors - TEMPERATURE

The only factor determining temperature – velocity of molecules — is shared by all scales, hence each degree in Celsius will have exactly one corresponding value in Fahrenheit.

So the temperature in Celsius and Fahrenheit will have a correlation coefficient of 1 and a plotting of temperature score will be a straight line.

[2] Weak to non-existent correlation of factors - BOTTLED WATER CONSUMPTION  and DEATHS FROM AIR CRASHES

If we looked at all countries in the world and plotted death rates from air crashes per country, in any specific year , against per capita consumption of bottled water, the plotting of scores for each event would show no pattern at all. Thus the correlation coefficient is 0, i.e. there is no correlation.



    Whenever the correlation between two outcomes or scores is weak to non existent, there will be regression to the mean.






Regression To The Mean - The Dangers Of False Attribution Of Cause & Effect

We need to be especially careful of regression to the mean when we are trying to establish causality between two factors.

As we have already established:

Correlation is a relationship, thus action A relates to outcome B.

Whereas:

# Causation can be defined as action A causes outcome B.

# Causation results from a perfect correlation between action A and outcome B.



  • Correlation and causation are often confused because the human mind likes to find patterns even when they do not exist.
  • We can not assume causation just because we see an apparent connection or link between A and B, such as we see that B follows A or we see A and B simultaneously.
  • We can only show a causation when we know how it causes B and why it causes B.
  • We need to be able to separate action A from all other variable factors
  • We must also be able to show how Action A can be replicated under the same conditions to achieve outcome B, AND be able to support this with supporting empirical evidence [thus following scientific method].




This is something that many people, social media, the general media, and sometimes even trained scientists, fail to understand or recognise.



    Whenever correlation is imperfect, and thus a causation is unproven, the best score or outcome will always appear to get worse and the worst will appear to get better over time, regardless of any additional treatment.





Regression To The Mean - Examples

Can you recall a wonderful evening out? The weather was fabulous, your table was great and restaurant was excellent, the food and wine were superb and you were with great people.

Then you tried to repeat the experience and somehow it wasn't as good and you were disappointed. Why was this?  It was because your perfect evening was due to a random series of chance events that all fell in place on the wonderful evening.

Whenever you try to repeat the perfect experience, chances are that at least one thing won't be perfect the next time.




Regression to the mean is prevalent in sport and can explain the “manager of the month curse” in football.

This award is usually won by managers who have had four or more wins in a row, often because of a combination of skill and luck.

When the luck runs out, the “curse” strikes.




Regression to the mean can be harmless, but it becomes a problem when it is misinterpreted:

"For example, imagine you ran a hospital and were told that hospital-acquired infections were five times higher than average last month. A colleague tells you they know the cause and it can solved by using more prophylactic antibiotics.

You agree and in the following month you’re told that prophylactic antibiotic use is through the roof and infections have come down. Your mind makes a causal connection and you’re now convinced of the need for widespread prophylactic antibiotics, a potentially dangerous connection given that the unusual infection rate could have been due to chance events.

Now your hospital budget will be tighter because of the costs of using more antibiotics, and you’re contributing to serious problem of antibiotic resistance."






Countering The Dangers Of False Attribution Of Cause & Effect

Here are 4 suggestions for identifying and countering false attribution of cause and effect and understanding the regression to the mean


  • Gather more data
  • Identify the variables
  • Wait and watch
  • Rinse and repeat






Return to: Mental Models






Chinese (Traditional)EnglishFrenchGermanItalianRussianSpanishVietnamese


Custom Site Search


3 Keys Solutions

Think -> Action = Change


Enter your email address:

Delivered by FeedBurner

LATEST ARTICLES

  1. Roxanne - I Will Not Share You With 1,300 Other Men

    May 16, 21 12:00 AM

    The Toxicity Of Addiction To Instagram Self-Validation Roxanne...
    You don't have to put on the red light
    Those days are over
    No more posting selfies on Instagram tonight
    You don't have to sell your bo…

    Read More

  2. Less Is More - Subtractive Solutions

    May 12, 21 12:00 AM

    Why do we nearly always add something, regardless of whether it helps or not. Why do our brains miss opportunities to improve through subtraction? How to reduce your subtraction bias? Ask yourself “Wh…

    Read More

  3. Understanding The Effect of Multiplying by Zero

    May 09, 21 12:00 AM

    In a multiplication equation each number is entirely dependent on the number it is being multiplied by. Thus a zero in the equation wipes out the whole total. You need to be very clear whether you're…

    Read More

  4. Regression To The Mean - Why Perfection Rarely Lasts

    May 06, 21 12:00 AM

    Regression to the mean shows that following an extreme random event, the next random event is likely to be less extreme. "Regression to the mean is a common statistical phenomenon that can mislead us…

    Read More

  5. Pareto Principle - 80/20 Rule

    May 03, 21 12:00 AM

    In practical terms: 20% of your actions/activities will account for 80% of your results/outcomes. However, the disparities are even larger than most people think. The really striking part is just how…

    Read More

  6. Compounding - Making Gains On Gains

    Apr 30, 21 12:00 AM

    Compounding is the process whereby a gain made on an invested resource is reinvested alongside the original resource, and further gains are made on that gain. "Compound interest is the eight wonder of…

    Read More

  7. Margin Of Safety - If It Can Go Wrong, Assume That It Will

    Apr 27, 21 12:00 AM

    How much slack, or scope, have we got if something goes wrong or it doesn't work out according to plan? Assume that it will take twice as long to happen than you think it will, that it will cost twice…

    Read More

  8. Incentives - What's In it For Me?

    Apr 25, 21 12:00 AM

    Incentives are what drive human behavior. Understanding this is the key to understanding people. Conversely, failing to recognize their importance often leads us to make major errors. In seeking to un…

    Read More

  9. The Red Queen Effect - Running Faster and Faster Only to Stay in the Same Place

    Apr 23, 21 12:00 AM

    The message of The Red Queen Effect is you can’t be complacent or you'll fall behind. To survive you have to run very fast and hard, and you need to co-evolve with the people and the systems you inter…

    Read More

  10. Leverage - Achieving A Large Output For A Small Input At The Right Place

    Apr 21, 21 10:44 AM

    A small well-focused action can produce a significant and long-lasting improvement - when applied in the right place. High leverage activities are those where you can achieve a large increase in outpu…

    Read More




Support This Site