MONOTONE Statement
- MONOTONE < options > ;
The MONOTONE statement specifies an imputation method
for data sets with monotone missingness.
You must also specify a VAR statement and
the data set must have a monotone missing pattern
with variables ordered in the VAR list.
When both MONOTONE and MCMC statements are specified,
the MONOTONE statement is not used..
You can specify the following options in a MONOTONE statement.
- METHOD=REG | REGRESSION
- METHOD=PROPENSITY </ NGROUPS = number>
- specifies the imputation method for a data set with a
monotone missing pattern.
You can specify either METHOD=REG, a parametric regression method, or
METHOD=PROPENSITY, a nonparametric method based on propensity scores.
The default is METHOD=REG.
When METHOD=PROPENSITY is specified, the MAXIMUM=, MINIMUM=,
and ROUND= options, which make the imputed values more consistent
with the observed variable values, are not applicable.
- NGROUPS=number
- specifies the number of groups based on propensity scores
for METHOD=PROPENSITY. The default is NGROUPS=5.
See the "Regression Method for Monotone Missing Data" section for a detailed description of the
regression method, and the "Propensity Score Method for Monotone Missing Data" section for the propensity score method.
Copyright © 2001 by SAS Institute Inc., Cary, NC, USA. All rights reserved.
