Chi Square Analysis


Return to Two-way Page 1

Chi Square according to SPSS 8.0 :
Tests the hypothesis that the row and column variables are independent, without indicating strength or direction of the relationship. Pearson chi-square, likelihood-ratio chi-square, and linear-by-linear association chi-square are displayed. For 2x2 tables, Fisher's exact test is computed when a table that does not result from missing rows or columns in a larger table has a cell with an expected frequency of less than 5. Yates' corrected chi-square is computed for all other 2x2 tables.

To run a Chi Square Analysis:

1.  Open keast4j.sav

2.  Click on Statistics, Summarize, Crosstabs and enter roof in the Row and wazprev in the Column.

3.  Click on the button marked Statistics and click on the box for chi-square then Continue.

4.  Click on the button marked Cells and choose the box for row Percentages and click Continue.

5. Click on OK.

 

The output will look like the following:

wpe3.jpg (20076 bytes)

wpe4.jpg (20231 bytes)

What is indicated in the results of the cross-tab is that there is a greater chance of finding a malnourished child among those with Grass /Thatch houses (38%) then out of those with Corrugated Iron houses (26%).  As long as all of the cells have at least a count of 5, then use the Pearson Chi-Square for the significance level, which is 0.001 in this case.  If any cell is less than 5, then use Fisher's Exact Test for the significance value.  The value of 0.001 tells us that the difference in malnutrition levels seen between those with good versus poor roof is likely not by chance (>1/ 1000).  Roofing (an estimate of SES) has gained evidence towards having a true association with nutritional status.

 

Return to Top of Page