WEIGHT Statement |
The WEIGHT statement names a numeric variable that provides a weight for each observation in the input data set. The WEIGHT statement is most commonly used to input cell count data. See the section Inputting Frequency Counts for more information. If you use a WEIGHT statement, PROC FREQ assumes that an observation represents n observations, where n is the value of variable. The value of the WEIGHT variable is not required to be an integer.
If the value of the WEIGHT variable is missing, PROC FREQ does not use that observation in the analysis. If the value of the WEIGHT variable is zero, PROC FREQ ignores the observation unless you specify the ZEROS option, which includes observations with zero weights. If you do not specify a WEIGHT statement, PROC FREQ assigns a weight of one to each observation. The sum of the WEIGHT variable values represents the total number of observations.
If any value of the WEIGHT variable is negative, PROC FREQ displays the frequencies computed from the weighted values but does not compute percentages and statistics. If you create an output data set by using the OUT= option in the TABLES statement, PROC FREQ assigns missing values to the PERCENT variable. PROC FREQ also assigns missing values to the variables that the OUTEXPECT and OUTPCT options provide. If any value of the WEIGHT variable is negative, you cannot create an output data set by using the OUTPUT statement because statistics are not computed when there are negative weights.
You can specify the following option in the WEIGHT statement:
includes observations with zero weight values. By default, PROC FREQ ignores observations with zero weights.
If you specify the ZEROS option, frequency and and crosstabulation tables display any levels corresponding to observations with zero weights. Without the ZEROS option, PROC FREQ does not process observations with zero weights, and so does not display levels that contain only observations with zero weights.
With the ZEROS option, PROC FREQ includes levels with zero weights in the chi-square goodness-of-fit test for one-way tables. Also, PROC FREQ includes any levels with zero weights in binomial computations for one-way tables. This makes it possible to compute binomial tests and estimates when the specified level contains no observations with positive weights.
For two-way tables, the ZEROS option enables computation of kappa statistics when there are levels that contain no observations with positive weight. For more information, see the section Tables with Zero Rows and Columns.
Note that even with the ZEROS option, PROC FREQ does not compute the CHISQ or MEASURES statistics for two-way tables when the table has a zero row or zero column because most of these statistics are undefined in this case.
The ZEROS option invokes the SPARSE option in the TABLES statement, which includes table cells with a zero frequency count in the LIST output and in the OUT= data set. By default, without the SPARSE option, PROC FREQ does not include zero frequency cells in the LIST output or in the OUT= data set. If you specify the ZEROS option in the WEIGHT statement but do not want the SPARSE option, you can specify the NOSPARSE option in the TABLES statement.