[IPAC-List] Differential prediction generalization: a new concept
Winfred Arthur, Jr.
w-arthur at tamu.edu
Fri Sep 30 12:14:28 EDT 2016
so Joel, a contrarian view :) of course the question is "in science
are we trying to describe, explain, and predict phenomena at the level
of individual cases (and by inference individual studies) or as they
broadly exist in the population?" if the former, then we shld give
strong deference to case studies [and primary studies] and that shld be
our primary methodology; if the latter, then we are going to have to use
and rely on population parameters (based on aggregates) from which
(some) individual cases [studies] by definition will vary. so variation
in the primary studies that are included in a meta-analysis is nothing
new; indeed that is the very issue meta-analysis is trying to address .
. . is there any variation, is it real or artifactual, and if it is
real, what is the cause (moderators)? so in a domain in which there is
as much overprediction as underprediction, the question is, is this
random or systematic error (variation)? that is the question :)
- winfred
On 9/30/2016 9:35 AM, Joel Wiesen wrote:
> FYI-
>
> A new Aguinis et al. study again shows that the absence of
> differential prediction seen in aggregational analyses of criterion
> related validity studies hides actual differential prediction in both
> directions (under prediction and over prediction) seen in individual
> studies.
>
> The authors summarize with this analogy:
> "The British writer and politician Benjamin Disraeli (1804–1881) stated
> ... 'A man eats a loaf of bread, and another man eats nothing;
> statistics is the science that tells us that each of these men ate
> half a loaf of bread.'"
>
>
> Aguinis, H., Culpepper, S. A. & Pierce, C. A. (2016) Differential
> prediction generalization in college admissions testing. Journal of
> Educational Psychology, 108, 1045-1059.
>
>
>
>
>
>
More information about the IPAC-List
mailing list