W. Arthur et al., CHOICE OF SOFTWARE AND PROGRAMS IN METAANALYSIS RESEARCH - DOES IT MAKE A DIFFERENCE, Educational and psychological measurement, 54(3), 1994, pp. 776-787
Citations number
19
Categorie Soggetti
Psychology, Educational","Psychologym Experimental","Mathematical, Methods, Social Sciences
Along with the increased popularity of meta-analysis, a number of arti
cles have questioned and highlighted the role that judgment calls play
in the implementation and, ultimately, outcomes of studies that use t
his technique. In the absence of standardized data analyses packages,
and coupled with the wide range of options available to meta-analysts,
the current study investigated the effect of choice of data analysis
programs on meta-analysis study outcomes. The research objective was t
o investigate the extent to which four commonly used Schmidt and Hunte
r validity generalization-based meta-analysis software programs, all b
ased on the same conceptual and theoretical assumptions, produced iden
tical outcomes when used to analyze the same data set. The results ind
icate that, although there are some differences in values obtained fro
m the programs, these differences tended to be very small, typically o
ccurring in the fourth and sometimes fifth decimal place, and did not
influence the meta-analytic outcomes.