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.

Integrating laboratory and field study for improving selection: Development of a battery for predicting air traffic controller success.

“…The second (corrected) set contains estimated Pearson correlations, when corrected for explicit selection on the composite OPM test score (TMC). These estimated correlations were computed with a formula developed by Thorndike (1949; see also Boone & Lewis, 1978). The critical information for these calculations is as follows: (a) the correlation between the current selection instrument and the new tests; (b) the correlation between the current selection instrument and NLCOMP (r = .278); (c) the estimated standard deviation of the current test in the population of applicants (SD= 12.5; from Manning, 1991);and(d)the standard deviation of the current selection instrument in the present sample (SD -6.03).…”

The validity of validity: An analysis of validation study designs.

“…Thus, for explicit restriction in Design 5 the correction is based on the ratio of the restricted to the unrestricted variance of the predictor test (see Thorndike, 1949, p. 173). Other formulae are available for the implicit restriction case (Designs 4 and 8–11) where only the restricted variance of the new test is known and for those designs that provide an estimate of the unrestricted variance of the new test (3, 5, and potentially 11; for correction formulae see Boone & Lewis, 1978; Linn, Harnisch, & Dunbar, 1981).…”

Selection of Air Traffic Controllers

“…A pertinent feature of these efforts was the fact that data on new tests were based for the most part on ATCS trainees, a population that had already passed screening hurdles, thus restricting the range of scores in test samples. Boone and Lewis (1978) developed a new procedure to make maximum use of available information in the adjustment of validity coefficients for restriction of range due to selection. This new proce-• dure provided a more accurate method to correct spuriously low correlations between selection and measures of ATCS job performance for samples of persons already selected for ATCS training.…”

“…Boone (1980) along "" with data collected by CAMI on new recruits to correct for restriction in range in predictor data (Boone 1980). The corrections were made using a previously developed new procedure (Boone and Lewis, 1978; presented with seven dials for each set of six questions and is required ilk to read the correct value on the appropriate dial in order to select the tight answer from among five given alternatives. The MCAT (Dailey and Pickrel, 1977 …”