When you choose

Minitab offers different analyses that can do a chi-square test. The analysis you choose depends on the type of chi-square test you want to do. The calculations for these tests are the same, but the question you're trying to answer may be different.

- Test of association
- Use a test of association to determine whether one variable is associated with a different variable. For example, determine whether the sales for different colors of cars depends on the city where they are sold.
- Test of independence
- Use a test of independence to determine whether the observed value of one variable depends on the observed value of a different variable. For example, for an election, you might want to determine whether the candidate that a person votes for is independent of the gender of the voter.

For both tests, you can use either Chi Square Test for Association or Cross Tabulation and Chi-Square. Cross Tabulation and Chi-Square will handle frequency data, while Chi Square Test for Association will not.

In order to conduct a test in Cross Tabulation and Chi-Square, you must click Chi-Square and select Chi-square test. You can also get additional tests and measures of association by clicking Other Stats.

Use this analysis in a multinomial experiment to determine whether the proportions of categories in the data differ from target proportions.

For example, a researcher wants to determine whether the proportions of people who prefer certain colors of shoes agree with the values in the following table:

Proportion | Color |
---|---|

0.2 | White |

0.3 | Black |

0.4 | Blue |

0.1 | Any other color |

To perform a goodness-of-fit test, choose

.