This site is under construction. Please check back every few weeks for updates

COMMON MISTEAKS MISTAKES IN USING STATISTICS: Spotting and Avoiding Them

Introduction        Types of Mistakes        Suggestions        Resources        Table of Contents         About

Mistakes Involving the Limitations of Frequentist Inference Procedures (Hypothesis Tests and Confidence Intervals)

The reasoning involved in frequentist hypothesis tests and confidence intervals is not simple. Sometimes people are taught "just the gist," which may be adequate up to a certain point. However, such oversimplification often leads to misinterpretations and to assuming that studies establish more certainty than they really do.

So, in order to understand the mistakes discussed in this section, it may be helpful first
to read:


Overview of Frequentist Confidence Intervals
then
Overview of Frequentist Hypothesis Tests
then
 Frequentist Hypothesis Tests and  p-values 

You may need to go back and forth between these three pages; having three screens open or printing out the three pages might help. Rest assured that most people need to go through these ideas at least twice to really understand them, so don't give up if you don't catch on instantly. Then go on the to following pages, looking back at the previous three as needed to clarify any misunderstandings that may crop up.

Misinterpretations of p-values

Type I and Type II Errors

Mistakes Involving Power

The File Drawer Problem (Publication Bias)

Multiple Inference

Data Snooping