• Skip to secondary menu
  • Skip to main content
  • Skip to primary sidebar
  • My Store
  • Glossary
  • Home
  • About Me
  • Contact Me

Statistics By Jim

Making statistics intuitive

  • Graphs
  • Basics
  • Hypothesis Testing
  • Regression
  • ANOVA
  • Probability
  • Time Series
  • Fun

As a Statistician, Can I Say Age is Just a Number?

By Jim Frost 1 Comment

My last birthday wasn’t one of those difficult ages that end with a zero. Thank goodness! However, the passage of another year got me thinking. At that point, I told myself that age is just a number. Can you do a mental double-take? I think I did one. Can a statistician say that age is just a number? After all, it’s through numbers that statisticians understand the world and how it works.

Photograph of candles on a birthday cake.After some pondering, I concluded that, yes, age is just a number! If anyone asks, tell them that’s the conclusion of a statistician.

You’re probably wondering how I came to this finding. I don’t think I’m deceiving myself just to feel better. In statistics, if you can’t trust your data, you can’t trust the results. Garbage data goes in and garbage results come out. This idea applies to all areas of statistical analysis including hypothesis tests, ANOVA, and regression.

But, wait a minute. Surely it’s an easy matter to calculate your age. Of course, it is. I have no doubt that my age represents the correct number of Earth orbits around the sun since I was born. Trust me; I’ve tried to find ways of coming up with smaller numbers, but nothing works!

In this post, I’ll walk you through the question of age and use a statistical perspective to show you why you shouldn’t put much stock in this number.

Is Age a Trustworthy Number?

Numbers can deceive you in a variety of ways. In statistics, we are interested in both the reliability and the validity of data. Are the measurements consistent and do they measure what you think they are measuring?

Reliability refers to the repeatability of measurements and experimental results. If you measure something several times, do you obtain the same measurements? Do similar studies tend to produce consistent results? Regarding my age, we’re good. At least we’re good in terms of reliability. Whenever I check the calendar, I’m the same age and no younger.

Validity refers to how well a conclusion satisfies the rigors of the scientific method, which includes a variety of different ideas. Consequently, there are different types of validity including internal, external and construct. For this post, I’ll focus on internal validity, which relates to confidence in the cause-and-effect relationships that we’re studying. It is here where I think age has problems as a measure.

Developing a Hypothetical Age Study

Before we proceed, we need to determine what we are studying. Variables aren’t good or bad in a vacuum. Before we can assess a variable, like age, we need to understand the context in which we’ll use it.

I’ll assume that we have some reason for why we don’t like higher ages. Given the dislike, it’s safe to assume that people imagine a correlation between age and adverse outcomes. As you grow older, you presumably expect more unpleasant things to happen. That explains why people want a younger age. But, which outcomes? That’s not entirely clear as we mourn the passage of another year. For a proper study, we need to define these. Also, we need to assess not only whether there is a correlation between age and negative outcomes but whether age truly causes these outcomes.

All of these issues suggest that our hypothetical age study falls short in terms of internal validity. We’re not sure which outcomes we’re studying, and we can’t be sure of causal relationships. So far we don’t have much reason to trust our conclusion that older ages cause negative outcomes.

Defining Age-Related Outcomes

Let’s see if we can add some clarity by defining outcomes. For my initial assessment, it appears that there are two broad categories of life outcomes that we can use in our hypothetical age study.

Biological changes: It’s true that as we age, natural processes occur and we change. For example, we start as infants, go through puberty, mental and physical abilities increase and then decline, and so on. These changes are unavoidable, but they happen at different rates for different people. We can affect some of the underlying factors. For instance, we can eat healthier, exercise, reduce UV exposure, etc. However, some of the underlying variables are not controllable, such as genetics.

For our hypothetical study, we need to know which way the causal arrow points. Does the increasing calendar age cause the biological changes? Or, do these changes define our concept of age? I’d argue that the causality runs in this order: Underlying variables -> Biological changes -> Concept of age.

Important life affairs: These outcomes are not biological processes and are, therefore, less dependent on the passage of time. These outcomes include happiness, maximizing your potential, developing strong relationships, performing gratifying activities, and making positive contributions to your community. For assessing the quality of life, these seem much more important.

Where does this leave us? For biological changes, causality appears to run counter to the theoretical underpinnings of our study. In other words, it might be that biological changes create our concept of age rather age causing negative outcomes.

The important life affairs category doesn’t seem to depend on age at all, and these are the most important life outcomes. You can use these outcomes to define a life as being well lived.

Conclusions About Using Age as a Measure

None of this fits our thought experiment hypothesis that age causes bad things to happen. Based on these issues, my opinion as a statistician is that age does not have a causal relationship with the important outcomes in our thought experiment. In other words, age is just a number!

Let this conclusion free you from worrying about your age increasing every year. Don’t sweat that number. However, this finding places responsibility firmly on you for making smart choices. The choices you make have a greater impact on your life than a meaningless number. And, the rest you can’t control.

Share this:

  • Tweet

Related

Filed Under: Fun Tagged With: conceptual

Reader Interactions

Comments

  1. Jerry Tuttle says

    June 21, 2017 at 9:51 am

    Hi. I’d appreciate your advice on statistically demonstrating causation. It has been said that smoking causes lung cancer. But not every smoker gets lung cancer, and confounding variables also contribute to lung cancer. In general, how does one statistically demonstrate causality?

    Reply

Comments and Questions Cancel reply

Primary Sidebar

Meet Jim

I’ll help you intuitively understand statistics by focusing on concepts and using plain English so you can concentrate on understanding your results.

Read More...

Buy My Introduction to Statistics Book!

Cover of my Introduction to Statistics: An Intuitive Guide ebook.

Buy My Hypothesis Testing Book!

Cover image of my Hypothesis Testing: An Intuitive Guide ebook.

Buy My Regression Book!

Cover for my ebook, Regression Analysis: An Intuitive Guide for Using and Interpreting Linear Models.

Subscribe by Email

Enter your email address to receive notifications of new posts by email.

    I won't send you spam. Unsubscribe at any time.

    Follow Me

    • FacebookFacebook
    • RSS FeedRSS Feed
    • TwitterTwitter

    Top Posts

    • How to Interpret P-values and Coefficients in Regression Analysis
    • How To Interpret R-squared in Regression Analysis
    • Mean, Median, and Mode: Measures of Central Tendency
    • Multicollinearity in Regression Analysis: Problems, Detection, and Solutions
    • How to Interpret the F-test of Overall Significance in Regression Analysis
    • Interpreting Correlation Coefficients
    • Choosing the Correct Type of Regression Analysis
    • Measures of Variability: Range, Interquartile Range, Variance, and Standard Deviation
    • Difference between Descriptive and Inferential Statistics
    • How to Find the P value: Process and Calculations

    Recent Posts

    • Principal Component Analysis Guide & Example
    • Fishers Exact Test: Using & Interpreting
    • Percent Change: Formula and Calculation Steps
    • X and Y Axis in Graphs
    • Simpsons Paradox Explained
    • Covariates: Definition & Uses

    Recent Comments

    • Dave on Control Variables: Definition, Uses & Examples
    • Jim Frost on How High Does R-squared Need to Be?
    • Mark Solomons on How High Does R-squared Need to Be?
    • John Grenci on Normal Distribution in Statistics
    • Jim Frost on Normal Distribution in Statistics

    Copyright © 2023 · Jim Frost · Privacy Policy