A combination of SAS® DATA step, SAS macro, and SAS Output Delivery System code is presented here as a method to create and display a summary LR table. The summary table includes the odds ratio estimate (OR), 95% confidence interval (CI), and P value for each covariate included in the LR model.

The Excel files whose links are given below provide examples of linear and logistic regression analysis illustrated with RegressIt. Most of them include detailed notes that explain the analysis and are useful for teaching purposes. Links for examples of analysis performed with other add-ins are at the bottom of the page.

The table for a typical logistic regression is shown above. There are six sets of symbols used in the table (B, SE B,Wald χ 2, p, OR, 95% CI OR). The main variables interpreted from the table are the p and the OR. However, it can be useful to know what each variable means. B – This is the unstandardized regression weight.

For example, we could use logistic regression to model the relationship between various measurements of a manufactured specimen (such as dimensions and chemical composition) to predict if a crack greater than 10 mils will occur (a binary variable: either yes or no).

Before we can display our output in a table, we will need to add a variable to our dataset that identifies which model each line in the dataset created by ods is associated with. The data step below creates a new dataset called r2 that includes a new variable modelnum which identifies the model each coefficient is associated with.

n OLS multiple regression. In this table, the left-hand column lists the independent variables and the other columns show the values of (in order): the partial logistic regression coefficients (b), the standard errors of the partial slope coefficients (se), the z-ratio, the significance level, and the odds ratio (or expon.

Another way of evaluating the fit of a given logistic regression model is via a Classification Table. The Real Statistics Logistic Regression data analysis tool produces this table. For Example 1 of Comparing Logistic Regression Models the table produced is displayed on the right side of Figure 1. Figure 1 – Classification Table.

Use % concordant and discordant to compare the model to alternative models with different predictors and alternative link functions. The Summary Measures attempt to summarize the concordant and discordant information.

We can use statistical software to calculate the observed probabilities as the number of observed deaths out of 250 for each dose level. A binary logistic regression model is used to describe the connection between the observed probabilities of death as a function of dose level.

These examples first describe data at the individual level, and then describe summary data. Data at the individuals level, one exposure variable.