Chi Square test in Excel using the QI Macros

Chi Square tests in Excel

There are different types of Chi Square tests:

• Chi Square Goodness of Fit Tests
• Chi Square test of a Contingency Table - see below
• Fisher Exact Test for 2X2 Tables - Use Fisher's Exact Test for 2x2 tables.

Chi Square test of a Contingency Table

Watch Chi Square Test of a Contingency Table in Excel Video

A Chi Square test evaluates if two variables are independent of each other. We've all taken surveys and probably wondered what happened. A Chi Square test of a contingency table helps identify if there are differences between two or more demographics. Consider the following example.

Men vs Women - Chi Square test Example

Imagine asking men and women if they agree, disagree or are neutral about a given topic. How will we know if they have the same or differing opinions? We can develop a null hypothesis (H₀) that men and women have independent views and an alternate hypothesis (H_a) that their views are related:

• H₀ men <> women
• H_a men =women

Now, conduct the survey and enter the number of responses into Excel. As you can see, men seem to agree more than the women do, but is it statistically different?

Select the data with the mouse and click on the QI Macros Menu to select the one sample Chi Square test:

The Chi Square test macro will calculate the values and interpret the results for you:

Note that we don't need the same number of responses from each group to get a result.

Interpreting the Chi Square results

In the above results the p value is 0.00031.

If the p value is less than the significance (e.g., a=0.05), we can reject the null hypothesis that men and women have independent views on the subject.

Chi square is just one of the tools in the QI Macros Statistical Process Control Software for Excel. Other tools include:

• Hypothesis Tests like anova, t test and f tests.
• Data Normality Test

Download the FREE 30-day Evaluation copy of the QI Macros Excel SPC Software for Six Sigma