From the course: SAS Essential Training: 2 Regression Analysis for Healthcare Research

Unlock the full course today

Join today to access over 24,100 courses taught by industry experts.

Solution: Add interaction to a logistic regression model

Solution: Add interaction to a logistic regression model - SAS Tutorial

From the course: SAS Essential Training: 2 Regression Analysis for Healthcare Research

Start my 1-month free trial Buy for my team

Solution: Add interaction to a logistic regression model

“

(lively music) - [Instructor] Okay, here I am in SAS ODA with a solution. All this code up to here is the beginning of the challenge code. So let me highlight and run that so we get up to date. Okay, good. Let's go back to the Code tab. Let's look at this first logistic code. Remember, there are different commands you can use in SAS for logistic regression, and here I'm demonstrating PROC LOGISTIC. So I start with PROC LOGISTIC, specify the analytic dataset we developed at the beginning of the challenge, and then use the option descending because I want SAS to model the probability of one, not zero. The next line is the model statement. This first model does not have the interaction term in it. I just wanted to look at it first without the interaction term. So you'll see the model equation is SUNEXP = Shade and Sunscreen. I also request SAS to convert the regression slopes from the log odds to odds ratios by using the option risklimits. All right, let's run this first model that does…

Contents