Example of Predict with a binary logistic regression model

A financial analyst investigates the factors that are associated with the probability that a college student has certain credit cards. The analyst randomly samples college students for a survey. The survey asks the students questions about their education and finances.

After fitting the model, the analyst estimates the probability that a student who has $75 cash and an annual income of $10,000 has an American Express credit card.

Open the sample data, CreditSurvey.MTW.
Choose Stat > Regression > Binary Logistic Regression > Predict.
From Response, select American Express.
In the table, enter 75 for Cash and 10000 for Annual Income.
Click OK.

Interpret the results

Minitab uses the stored model to estimate that the probability is 0.998870. The prediction interval indicates that the analyst can be 95% confident that the probability falls within the range of 0.0516175 to 1.00000. This wide range indicates that the model does not produce precise predictions.

Regression Equation

P(1)	=	exp(Y')/(1 + exp(Y'))

Y'	=	-7.71 + 0.1688 Cash + 0.000108 Annual Income + 0.000540 CashCash - 0.000003 CashAnnual Income

Settings

Variable	Setting
Cash	75
Annual Income	10000

Prediction

Fitted Probability	SE Fit	95% CI
0.998870	0.0055833	(0.0516175, 1.00000)