2 min read ⌚ 

Stripping the Dread from the Data 

Numbers are everywhere.

Learn the language of “Naked Statistics” and reap all the benefits that come with it.

About Charles Wheelan

Charles Wheelan is an author, economist, professor and political candidate. He has also written Naked Economics.

“Naked Statistics Summary”

Many number-based events and predictions rely on statistics and statistical analysis. In fact, we use statistics each day of our lives.

Just think of all those movie-grade averages, academical averages, etc.

When you search online, the suggestions that pop up connected to your search are also a result of statistics.

You can make good use of statistical analysis when it comes, say, to different investment or betting decisions.

So, what is statistics?

Simply said, statistics is a result of combinations of different types of data, which various people have analyzed, and collapsed it into easily understandable numbers.

In other words, statistics summarizes vast quantities of information into simple numbers, which enable people to make better and more informed decisions.

It also enables researchers to work with small amounts of data, otherwise known as representative samples, and come up with powerful conclusions that apply universally.

When applying statistics, it is important that you learn the statistical language, so you can correctly comprehend the data, and not make mistakes.

Of course, context also plays an essential role when it comes to numbers.

However, the most critical step of the statistical analysis is gathering good data.

Good results are impossible without reliable data. When an analysis is not right, bad data, and not a bad formula, is usually to blame.

All statistical facts are subject to bias since it is impossible to get completely clean and accurate data. However, strive to decrease the bias as much as possible.

Knowing this, we can conclude that statistics does not guarantee the conclusions with a 100% certainty. Instead, it uses estimates and hypotheses.

When a hypothesis is made, it can only be further proven by testing.

So, we can conclude that statistics gives probabilities and estimates, and facts are a result of observations and testing.

Key Lessons from “Naked Statistics”

1.      Correlation and Probability
2.      Possible Data Biases
3.      Seven Common Cases of Abuse of Regression Analysis

Correlation and Probability

Differentiate between correlation and causation. When variable changes it may affect another variable, but it is not always the case.

When it comes to probability – it deals with uncertain outcomes.

Sometimes, the likelihood of an event is very low, but that does not mean that the event is impossible.

The improbable always happens.

Maybe not to you, but it will happen.

Possible Data Biases

• • Improperly sampled data

• • Purposely misreported data

• Data based on false memories given as fact during surveys

Seven Common Cases of Abuse of Regression Analysis

• • “Using regression to analyze a nonlinear relationship.”

• • “Correlation does not equal causation.”

• • “Reverse causality.”

• • “Omitted variable bias.”

• • “Highly correlated explanatory variables.”

• • “Extrapolating the data.”

• “Data mining (too many variables)”

Like this summary? We’d Like to invite you to download our free 12 min app, for more amazing summaries and audiobooks.

“Naked Statistics” Quotes