The LOGISTIC Procedure
- Overview
- Getting Started
-
Syntax
PROC LOGISTIC Statement BY Statement CLASS Statement CONTRAST Statement EFFECT Statement EFFECTPLOT Statement ESTIMATE Statement EXACT Statement EXACTOPTIONS Statement FREQ Statement LSMEANS Statement LSMESTIMATE Statement MODEL Statement ODDSRATIO Statement OUTPUT Statement ROC Statement ROCCONTRAST Statement SCORE Statement SLICE Statement STORE Statement STRATA Statement TEST Statement UNITS Statement WEIGHT Statement -
Details
Missing Values Response Level Ordering Link Functions and the Corresponding Distributions Determining Observations for Likelihood Contributions Iterative Algorithms for Model Fitting Convergence Criteria Existence of Maximum Likelihood Estimates Effect-Selection Methods Model Fitting Information Generalized Coefficient of Determination Score Statistics and Tests Confidence Intervals for Parameters Odds Ratio Estimation Rank Correlation of Observed Responses and Predicted Probabilities Linear Predictor, Predicted Probability, and Confidence Limits Classification Table Overdispersion The Hosmer-Lemeshow Goodness-of-Fit Test Receiver Operating Characteristic Curves Testing Linear Hypotheses about the Regression Coefficients Regression Diagnostics Scoring Data Sets Conditional Logistic Regression Exact Conditional Logistic Regression Input and Output Data Sets Computational Resources Displayed Output ODS Table Names ODS Graphics
-
Examples
Stepwise Logistic Regression and Predicted Values Logistic Modeling with Categorical Predictors Ordinal Logistic Regression Nominal Response Data: Generalized Logits Model Stratified Sampling Logistic Regression Diagnostics ROC Curve, Customized Odds Ratios, Goodness-of-Fit Statistics, R-Square, and Confidence Limits Comparing Receiver Operating Characteristic Curves Goodness-of-Fit Tests and Subpopulations Overdispersion Conditional Logistic Regression for Matched Pairs Data Firth’s Penalized Likelihood Compared with Other Approaches Complementary Log-Log Model for Infection Rates Complementary Log-Log Model for Interval-Censored Survival Times Scoring Data Sets Using the LSMEANS Statement
- References
| Classification Table |
For binary response data, the response is either an event or a nonevent. In PROC LOGISTIC, the response with Ordered Value 1 is regarded as the event, and the response with Ordered Value 2 is the nonevent. PROC LOGISTIC models the probability of the event. From the fitted model, a predicted event probability can be computed for each observation. A method to compute a reduced-bias estimate of the predicted probability is given in the section Predicted Probability of an Event for Classification. If the predicted event probability exceeds or equals some cutpoint value 
, the observation is predicted to be an event observation; otherwise, it is predicted as a nonevent. A 
frequency table can be obtained by cross-classifying the observed and predicted responses. The CTABLE option produces this table, and the PPROB= option selects one or more cutpoints. Each cutpoint generates a classification table. If the PEVENT= option is also specified, a classification table is produced for each combination of PEVENT= and PPROB= values.
The accuracy of the classification is measured by its sensitivity (the ability to predict an event correctly) and specificity (the ability to predict a nonevent correctly). Sensitivity is the proportion of event responses that were predicted to be events. Specificity is the proportion of nonevent responses that were predicted to be nonevents. PROC LOGISTIC also computes three other conditional probabilities: false positive rate, false negative rate, and rate of correct classification. The false positive rate is the proportion of predicted event responses that were observed as nonevents. The false negative rate is the proportion of predicted nonevent responses that were observed as events. Given prior probabilities specified with the PEVENT= option, these conditional probabilities can be computed as posterior probabilities by using Bayes’ theorem.
Predicted Probability of an Event for Classification
When you classify a set of binary data, if the same observations used to fit the model are also used to estimate the classification error, the resulting error-count estimate is biased. One way of reducing the bias is to remove the binary observation to be classified from the data, reestimate the parameters of the model, and then classify the observation based on the new parameter estimates. However, it would be costly to fit the model by leaving out each observation one at a time. The LOGISTIC procedure provides a less expensive one-step approximation to the preceding parameter estimates. Let 
be the MLE of the parameter vector 
based on all observations. Let 
denote the MLE computed without the 
th observation. The one-step estimate of is given by
 |
where
is 1 for an observed event response and 0 otherwise
is the weight of the observation
is the predicted event probability based on
is the hat diagonal element with
and 
is the estimated covariance matrix of
False Positive and Negative Rates Using Bayes’ Theorem
Suppose 
of 
individuals experience an event, such as a disease. Let this group be denoted by 
, and let the group of the remaining 
individuals who do not have the disease be denoted by 
. The th individual is classified as giving a positive response if the predicted probability of disease (
) is large. The probability is the reduced-bias estimate based on the one-step approximation given in the preceding section. For a given cutpoint 
, the th individual is predicted to give a positive response if 
.
Let 
denote the event that a subject has the disease, and let 
denote the event of not having the disease. Let 
denote the event that the subject responds positively, and let 
denote the event of responding negatively. Results of the classification are represented by two conditional probabilities, 
and 
, where is the sensitivity and is one minus the specificity.
These probabilities are given by
 |
|||
 |
where 
is the indicator function.
Bayes’ theorem is used to compute the error rates of the classification. For a given prior probability 
of the disease, the false positive rate 
and the false negative rate 
are given by Fleiss (1981, pp. 4–5) as follows:
 |
 |
 |
|||
 |
|
 |
The prior probability can be specified by the PEVENT= option. If the PEVENT= option is not specified, the sample proportion of diseased individuals is used; that is, 
. In such a case, the false positive rate and the false negative rate reduce to
 |
 |
 |
|||
 |
|
 |
Note that for a stratified sampling situation in which and 
are chosen a priori, 
is not a desirable estimate of . For such situations, the PEVENT= option should be specified.