· Q. I have entered my data into an SPSS spreadsheet but would like to obtain:
a) a table of frequencies and percentages representing the amount of pregnant women in my sample within each age category
and
b) a table of frequencies and percentages representing a cross-tabulation of number of cigarettes smoked per day and age-group for my sample of pregnant women.
Can SPSS do the work for me?
A. Mercifully, yes! Have a look at the instructions on slides 1 – 13 of the tutorial
The chi-square test of association, the percentage stacked bar chart, Fisher’s exact test, odds ratios and relative risks (PowerPoint version: designed to help you learn step by step)
Hypothesis Tests for Categorical Data.
Tip: If you are specifically interested in generating a table for sensitivity, specificity, negative predictive value (NPV) or positive predictive value (PPV) and you want the percentages to appear as they do conventionally, this is a special case where it makes sense when preparing your data in Excel to code a positive result as 0 and a negative result as 1. This way, once your data are read into SPSS, the table you generate will include rows and columns the right way round for your purposes. If, in particular, you want to look at any one of sensitivity, specificity, NPV and PPV, the results of the diagnostic test pertain to your row variable and the ‘true’ results pertain to your column variable. Once you generate your table, you should know which percentages to select from the table and what numerator and denominator were used to obtain any one of them. This is evident from the definitions for sensitivity, specificity, NPV and PPV.
Relevant MedStats WordPress page for definitions: DIAGNOSTIC TESTING
Cross-Tabulating Frequencies or Percentages by Margaret MacDougall is licensed under a Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International License.