The BCHOICE Procedure

specifies an inverse Wishart prior distribution, IWISHART(a,b), for the covariance matrix of the random effects.

You can specify the following options, enclosed in parentheses:

displays results (summary, diagnostics statistics and plots ) for the individual-level random-effects parameters. By default, PROC BCHOICE does not print results for individual-level random-effects parameters to save time and space. In models that have a large number of individual random effects (for example, tens of thousands individuals), it may take a long time to display the summary, diagnostics statistics, and plots for all the individual-level parameters, so be cautious when using the MONITOR option.

You can monitor a subset of the random-effects parameters. You can provide a numeric list of the SUBJECT indexes, or PROC BCHOICE can randomly choose a subset of all subjects for you.

To monitor a list of random-effects parameters for certain subjects, you can provide their indexes as follows:

random x / subject=index monitor=(1 to 5 by 2 23 57);

PROC BCHOICE outputs results of random effects for subjects 1, 3, 5, 23, and 57. PROC BCHOICE can also randomly choose a subset of all the subjects to monitor, if you submit a statement such as the following:

random x / subject=index monitor=(random(12));

PROC BCHOICE outputs results of random effects for 12 randomly selected subjects. You control the sequence of the random indexes by specifying the SEED= option in the PROC BCHOICE statement.

When you specify the MONITOR option, it uses the specification of the STATISTICS= and PLOTS= options in the PROC BCHOICE statement.

suppresses storing the posterior samples of individual random-effects parameters in the OUTPOST= data set. By default, PROC BCHOICE outputs the posterior samples of all random-effects parameters to the OUTPOST= data set. You can use the NOOUTPOST option to not save the random-effects parameters. In models that have a large number of individual random-effects (for example, tens of thousands individuals), PROC BCHOICE can run faster if it does not save the posterior samples of all the individual random-effects.

When you specify both the NOOUTPOST option and the MONITOR option, PROC BCHOICE outputs the list of variables that are monitored.

There is a limit on the maximum number of variables that can be saved to an OUTPOST= data set. If you run a large-scale random-effects model in which the number of parameters exceeds that limit, the NOOUTPOST option is invoked automatically and PROC BCHOICE does not save the individual random-effects draws to the output data set. You can use the MONITOR option to select a subset of the parameters to store in the OUTPOST= data set.

creates an output data set to contain the estimates of subject-level (individual) random-effects coefficients. PROC BCHOICE saves the posterior means of all individual random effects by subject to this data set. The columns in this data set are the random effects that are listed in the RANDOM statement, and the rows are the subjects that are specified in the SUBJECT= command of the RANDOM statement.

requests to always output the summary, diagnostics statistics and plots for the parameters in the covariance matrix of the random effects. By default, PROC BCHOICE produces the summary, diagnostics statistics and plots for the parameters in the covariance matrix of the random effects. However, if there are too many parameters, greater than 36, in the covariance matrix of random effects, then the summary, diagnostics statistics and plots are not displayed. You can use this option to have them printed if you would like to.

requests to estimate the mean of the individual random effects, so that the mean of the random effects, , is not assumed to be zero and is estimated. This option is recommended when there are no fixed effects specified in the MODEL statement.

You can also model the mean of the random effects as a function of individual characteristics, such as demographic variables. Rossi, McCulloch, and Allenby (1996) and Rossi, Allenby, and McCulloch (2005) propose adding another layer of flexibility to the random-effects-only model by allowing heterogeneity that is driven by observable (demographic) characteristics of the individuals. Effects specified in the REMEAN= option are not supposed to change within each SUBJECT= level in the RANDOM statement. PROC BCHOICE takes only the first value of all effects in the REMEAN= option within each SUBJECT= level.

The following REMEAN=(AGE GENDER) option in the RANDOM statement estimates the mean of the random effect, X, and models the mean as a function of Age and Gender:

random X / subject=Index remean=(Age Gender);

identifies the subjects in the model for the random effects. A set of random effects will be estimated for each subject. PROC BCHOICE assumes complete independence across subjects; thus, for the RANDOM statement, the SUBJECT= option produces a block-diagonal structure that has identical blocks. Specifying a subject effect is equivalent to nesting all other effects in the RANDOM statement within the subject effect.

The effect in the RANDOM statement must be specified in the CLASS list. The effect can be continuous variables.

PROC BCHOICE does not sort by the values of the SUBJECT= variable; rather, it considers the data to be from a new subject or group whenever the value of the variable changes from the previous observation.

specifies the covariance structure. Although a variety of structures are available, most applications call for either TYPE=VC or TYPE=UN. The TYPE=VC (variance components) option, which is the default structure, models a different variance component for each random effect. The TYPE=UN (unstructured) specifies a full structured covariance matrix for the random effects. The unstructured form accommodates any pattern of correlation between the random effects in addition to fitting a different variance component for each random effect.