Mr. Lieberknecht is being asked to abstract critical information from existing data tapes and to merge these data, according to study person number, on a new data tape. The new tape is required to be in the SAS format; that is, the data must be placed in a format that allows the canned Statistical Analysis System (SAS) to read the data from the tape such that complex biostatistical analyses can be routinely produced using the Division of Computer Resources and Technology (DCRT). The creation of a SAS data base requires the creation of new SAS variable names, which consist of 4 to 6 letters. Mr. Lieberknecht has been asked to create realistic names that are similar to or portions of the numerical variable labels used by the Walnut Creek study center. Because NIH wishes to have similarity of data bases, he has also been asked to create a SAS data set for another data set purchased from the National Center for Health Statistics.
