Example of a prediction for a binary logistic model
main topic     interpreting results     session command     see also 

You are a researcher who is interested in understanding the effect of smoking and weight upon resting pulse rate. Because you have categorized the response-pulse rate-into low and high, a binary logistic regression analysis is appropriate to investigate the effects of smoking and weight upon pulse rate.

1    Open the worksheet EXH_REGR.MTW.

2    Choose Stat > Regression > Binary Logistic Regression > Fit Binary Logistic Model.

3    In Response, enter RestingPulse. In Continuous predictors, enter Weight. In Categorical predictors, enter Smokes. Click OK.

4    Choose Stat > Regression > Binary Logistic Regression > Predict.

5    In Response, choose RestingPulse.

5    In the second drop-down list, choose Enter individual values.

6    In the predictors table, complete the columns of the table as shown below.

Weight

Smokes

155

Yes

7    Click OK.

Session Window Output

Binary Logistic Regression: RestingPulse versus Weight, Smokes

 

 

Prediction for RestingPulse

 

 

Regression Equation

 

P(Low)  =  exp(Y')/(1 + exp(Y'))

 

 

Y' = -1.99 + 0.0250 Weight + 0.000000 Smokes_No - 1.193 Smokes_Yes

 

 

Variable  Setting

Weight        155

Smokes        Yes

 

 

     Fitted

Probability     SE Fit         95% CI

   0.667824  0.0920068  (0.471396, 0.819248)

Interpreting the results

Minitab uses the model information to calculate that the predicted probability for the specified predictor values is 0.667824.

Additionally, the confidence interval indicates that you can be 95% confident that the probability that someone who weighs 155 pounds and smokes has a low resting pulse rate is between 0.471395 and 0.819248.

Keep in mind that this prediction is based on a model equation. You should be sure that your model is adequate before you use the prediction.