Replacing missing values with the desired value like a zero is always a challenge, especially when we have a dataset with a number of columns to standardize. The OLD WAY of doing it to write a DATA step code with if……then statements like...
if var=. then var=0;
to make 0 appear instead of . (dot) in the tables output.
With the SAS option called missing you can save a lot of typing. If you place the following SAS option code before the generation of the table output:
Option missing="0";
SAS will display 0 (zero) instead of the . (dot) on the table. In fact it can display whatever the character we would like to display for missing values. You can use a - (line) or * (star).
Always change it back the option missing setting to default as Option Missing=''; otherwise you may endup getting unexpected results;
Warning: Since we are using this option to display zeros instead of .(dots), you shouldn't use this option before any of SAS procedures like PROC UNIVARIATE, PROC MEANS, PROC SUMMARY and PROC FREQ because they don’t treat missing as zero. So if you use Option Missing='0' we are telling SAS to consider missing as ZERO which is not what the above procedure generally do.
**********************************************************************************;
Proc STDIZE: Proc STDIZE is very useful in processing the missing values. It offers a simple and very effective solution when we want to process missing values.
| MISSING= | specifies the method or a numeric value for replacing missing values |
| REPLACE | replaces missing data by zero in the standardized data |
| REPONLY | replaces missing data by the location measure (does not standardize the data) |
Example:
data miss;
input a b c;
cards;
1 . 3
. . 2
3 2 .
1 3 4
2 . .
. 2 .
run;
proc stdize data=old reponly MISSING=0 out=new;
var _numeric_;
run;
Output:
