Office of Aerospace Medicine Technical Reports
FAA Office of Aerospace Medicine
Civil Aerospace Medical Institute
Report No: DOT/FAA/AM-78/36
Title and Subtitle: The development of the ATC selection battery: A new procedure to make maximum use of available information when correcting correlations for restriction in range due to selection
Report Date: September 1978
Authors: Boone JO, Lewis MA
Abstract: A five-test selection battery was given to select Air Traffic Controllers. Data were collected on two new tests being considered for incorporation into the battery. To determine the utility of the old and new tests, it is necessary to correlate the tests with a criterion of job success. However, since criterion information is available only on persons already selected for air traffic control work, the correlation is restricted to this upper range of persons, and is, thereby, spuriously low for prediction purposes. To properly evaluate the utility of the tests, the correlation must be corrected for this restriction in range. This paper describes a new procedure to more accurately correct correlations for restriction in range. By Monte Carlo methods the new procedure is compared with Gulliksen and Thorndike's procedures and is shown to be more accurate.
Key Words: Selection, Correlation, Restriction in range
No. of Pages: 44
Civil Aerospace Medical Institute
Report No: DOT/FAA/AM-78/36
Title and Subtitle: The development of the ATC selection battery: A new procedure to make maximum use of available information when correcting correlations for restriction in range due to selection
Report Date: September 1978
Authors: Boone JO, Lewis MA
Abstract: A five-test selection battery was given to select Air Traffic Controllers. Data were collected on two new tests being considered for incorporation into the battery. To determine the utility of the old and new tests, it is necessary to correlate the tests with a criterion of job success. However, since criterion information is available only on persons already selected for air traffic control work, the correlation is restricted to this upper range of persons, and is, thereby, spuriously low for prediction purposes. To properly evaluate the utility of the tests, the correlation must be corrected for this restriction in range. This paper describes a new procedure to more accurately correct correlations for restriction in range. By Monte Carlo methods the new procedure is compared with Gulliksen and Thorndike's procedures and is shown to be more accurate.
Key Words: Selection, Correlation, Restriction in range
No. of Pages: 44
Last updated: Friday, June 1, 2012