Test for Independence from Summary Data

How To... > Work with Statistical Objects > Test Hypotheses > Test for Independence from Summary Data

_img165

Nothing about doing a test for independence requires you to have raw data. All you need are the tallies for each possible outcome.

1.	Create a new test by dragging one from the shelf or by choosing Object \| New \| Hypothesis Test.

2.	From the test’s the pop-up menu, choose Test for Independence.

3.	Edit the values in blue to reflect your data.

Let’s suppose you do a biology experiment with pill bugs in which you divide up the bugs’ living area into six regions according to temperature and humidity. On one occasion, you count the number of pill bugs in each region and enter the counts into a Test for Independence, as shown here. The entry of the number of categories is what expands the table and allows you to rename categories and enter counts in cells.

By choosing Test | Show Test Statistic Distribution, you can show a graph of the chi-square distribution. This graph has shading to indicate the probability of getting a value as great or greater than the observed value if the attributes are actually independent.