Page 158 - Statistics II for Dummies

142
Part II: Using Different Types of Regression to Make Predictions
Carrying Out a Logistic

Regression Analysis

The basic idea of any model-fitting process is to look at all possible models
you can have under the general format and find the one that fits your data
best.

The general form of the best-fitting logistic regression model is ,
where is the estimate of p, b is the estimate of β , and b is the estimate of
0 0 1
β (from the previous section “Using an S-curve to estimate probabilities”).
1
The only values you have a choice about to form your particular model are
the values of b and b . These values are the ones you’re trying to estimate
0 1
through the logistic regression analysis.
To find the best-fitting logistic regression model for your data, complete the
following steps:
1. Run a logistic regression analysis on the data you collected (see the
next section).
2. Find the coefficients of constant and x, where x is the name of your
explanatory variable.
These coefficients are b and b , the estimates of β and β in the logistic
0 1 0 1
regression model.
3. Plug the coefficients from step one into the logistic regression model:
.
This equation is your best-fitting logistic regression model for the data.
Its graph is an S-curve (for more on the S-curve, see the section “Using
an S-curve to estimate probabilities” earlier in this chapter).

In the sections that follow, you see how to ask Minitab to do the above steps
for you. You also see how to interpret the resulting computer output, find the
equation of the best-fitting logistic regression model, and use that model to
make predictions (being ever mindful that all conditions are met).

Running the analysis in Minitab

Here’s how to perform a logistic regression using Minitab (other statistical
software packages are similar):

7/23/09 9:28:36 PM
13_466469-ch08.indd 142 7/23/09 9:28:36 PM
13_466469-ch08.indd 142