# The MI Procedure

### Example 63.5 Monotone Discriminant Function Method for CLASS Variables

This example uses discriminant monotone methods to impute values of a CLASS variable from the observed observation values in a data set with a monotone missing pattern.

The following statements impute the continuous variables `Height` and `Width` with the regression method and the classification variable `Species` with the discriminant function method:

```proc mi data=Fish2 seed=7545417 nimpute=3 out=outex5;
class Species;
monotone discrim( Species= Length Width/ details);
var Length Width Species;
run;
```

The "Model Information"  table in Output 63.5.1 describes the method and options used in the multiple imputation process.

Output 63.5.1: Model Information

The MI Procedure

Model Information
Data Set WORK.FISH2
Method Monotone
Number of Imputations 3
Seed for random number generator 7545417

The "Monotone Model Specification"  table in Output 63.5.2 describes methods and imputed variables in the imputation model. The procedure uses the regression method to impute the variables `Height` and `Width`, and uses the logistic regression method to impute the variable `Species` in the model.

Output 63.5.2: Monotone Model Specification

Monotone Model Specification
Method Imputed Variables
Regression Width
Discriminant Function Species

The "Missing Data Patterns" table in Output 63.5.3 lists distinct missing data patterns with corresponding frequencies and percentages. The table confirms a monotone missing pattern for these variables.

Output 63.5.3: Missing Data Patterns

Missing Data Patterns
Group Length Width Species Freq Percent Group Means
Length Width
1 X X X 49 73.13 28.595918 4.482518
2 X X . 9 13.43 27.533333 4.444844
3 X . . 9 13.43 28.633333 .

When you use the DETAILS option, the parameters estimated from the observed data and the parameters used in each imputation are displayed in Output 63.5.4.

Output 63.5.4: Discriminant Model

Group Means for Monotone Discriminant Method
Species Variable Obs-Data Imputation
1 2 3
Parkki Length -0.62249 -0.917467 -0.909076 -0.146825
Parkki Width -0.71787 -0.921200 -1.036075 -0.343058
Perch Length 0.13937 0.042471 0.219096 0.079881
Perch Width 0.14408 0.047041 0.197736 0.082832

The following statements list the first 10 observations of the data set `Outex5` in Output 63.5.5. Note that all missing values of the variables `Width` and `Species` are imputed.

```proc print data=outex5(obs=10);
title 'First 10 Observations of the Imputed Data Set';
run;
```

Output 63.5.5: Imputed Data Set

 First 10 Observations of the Imputed Data Set

Obs _Imputation_ Species Length Width
1 1 Parkki 16.5 2.32650
2 1 Parkki 17.4 2.31420
3 1 Perch 19.8 3.03975
4 1 Parkki 21.3 2.91810
5 1 Parkki 22.4 3.29280
6 1 Perch 23.2 3.29440
7 1 Parkki 23.2 3.41040
8 1 Parkki 24.1 3.15710
9 1 Perch 25.8 3.66360
10 1 Parkki 28.0 4.14400