The SURVEYMEANS Procedure

The DOMAIN statement requests analysis for domains (subpopulations) in addition to analysis for the entire study population. The DOMAIN statement names the variables that identify domains, which are called domain variables.

A domain variable can be either character or numeric. The procedure treats domain variables as categorical variables. If a variable appears by itself in a DOMAIN statement, each level of this variable determines a domain in the study population. If two or more variables are joined by asterisks (*), then every possible combination of levels of these variables determines a domain. The procedure performs a descriptive analysis within each domain that is defined by the domain variables.

The formatted values of the domain variables determine the categorical variable levels. Thus, you can use formats to group values into levels. For more information, see the FORMAT procedure in Base SAS Procedures Guide and the FORMAT statement and SAS formats in SAS Formats and Informats: Reference.

When determining levels of a DOMAIN variable, an observation with missing values for this DOMAIN variable is excluded, unless you specify the MISSING option. For more information, see the section Missing Values.

It is common practice to compute statistics for domains. Because formation of these domains might be unrelated to the sample design, the sample sizes for the domains are random variables. Use a DOMAIN statement to incorporate this variability into the variance estimation.

A DOMAIN statement is different from a BY statement. In a BY statement, you treat the sample sizes as fixed in each subpopulation, and you perform analysis within each BY group independently. For more information, see the section Domain Analysis. Similarly, you should use a DOMAIN statement to perform a domain analysis over the entire data set. Creating a new data set from a single domain and analyzing that with PROC SURVEYMEANS yields inappropriate estimates of variance.

By default, the SURVEYMEANS procedure displays analyses for all levels of domains that are formed by the variables in a DOMAIN statement. Optionally, you can specify particular levels of each DOMAIN variable to be displayed by listing quoted formatted-level-values in parentheses after each variable name. You must enclose each formatted-level-value in single or double quotation marks. You can specify one or more levels of each variable; when you specify more than one level, separate the levels by a space or a comma. These examples illustrate the syntax:

domain Race*Gender(''Female'');
domain Race('White','Asian') Gender;

For example, Race*Gender(”Female”) requests that the procedure display analysis only for females within each race category, and Race(’White’,’Asian’) requests that the procedure display domain analysis only for people whose race is either white or Asian.

Specifying the same domain multiple times but with different levels for each corresponding domain variables is equivalent to specifying the union of different levels for the same variables. However, if you do not specify levels for a variable in a domain that is specified multiple times, only the specified levels are rendered. For example, the following two specifications together

domain Race('White')*Gender('Female');
domain Race('Asian')*Gender;

have the same effect as a single specification:

domain Race('White' 'Asian')*Gender('Female');

Also, the following specification

domain Race('White')*Gender Race('Asian')*Gender;

is equivalent to

domain Race('White' 'Asian')*Gender;

This syntax controls only the display of domain analysis results; it does not subset the data set, change the degrees of freedom, or otherwise affect the variance estimation.

You can specify the following options in the DOMAIN statement after a slash (/):