About UniLogistic Macro
This macro conducts descriptive and univariable logistic regression analyses using SAS statistical program; it exports the desired results to Excel and prepares formatted tables of results, in a format, almost ready for publication.
Experienced SAS/STAT user
A Novice user of SAS/STAT or a first time user
If you are a novice user of SAS/STAT or a first time user of this macro, read the documentation and work through the example analyses before implementing them for your own data. If you are new to logistic regression, please also read a brief introduction to the logistic regression model building or consult other resources listed on this website before conducting analyses.
What analyses can it conduct?
A single execution of this macro produces the following formatted tables in MS Excel (it automatically creates an Excel file and saves it in the folder you specify):
- Likelihood-ratio chi-square test statistics and p-values based on the unconditional associations of all explanatory variables (both categorical and continuous) with the outcome;
- Parameter estimates and their standard errors; and odds ratios and their confidence intervals for all explanatory variables (both categorical and continuous);
- Associations between all explanatory variables (Spearman rank correlation, chi-squares, P-values or other parameters as requested);
- Correlation between all quantitative variables (Pearson correlation coefficient);
- Contingency tables of all categorical explanatory variables with the outcome;
- Summary statistics of all quantitative variables for each category of the outcome.
In addition, to facilitate variable selection the macro creates two lists of explanatory variables, one sorted by their P-values and the other by their number of missing observations.
To assist in data exploration and visual appreciation of the associations, the macro creates four graphic PDF files (accessible from within the Excel file):
- Histograms (pdf) of all quantitative explanatory variables;
- Box-plots (pdf) of all quantitative explanatory variables with the outcome;
- Bar charts (pdf) of all categorical explanatory variables;
- Stacked bar charts (pdf) of all categorical explanatory variables with the outcome.
You can get an idea of the results produced by this macro by downloading the example output (xls) and graphics files listed above.
Work through the eLearning Module to learn how to implement this macro. The module could take from 15 minutes to 1 hour depending on your experience of using SAS and of conducting statistical analyses.