A more rigorous application of Zehnder's own correlational
model would have found much more use in social science's findings about active conversion.
Sample sizes for major studies ranged from 40 to 881 in descriptive, correlational
studies; from 12 to 97 in experimental studies; 12 to 102 in quasi-experimental studies; from 42 to 70 in triangulated studies; and 43 in the qualitative study.
Even so, it means larger sample sizes than most of us use: ideally at least 1000 for correlational
studies without repeated measures, and about 100 for controlled trials (depending on the type of controlled trial and the reliability of the dependent variable).
I was surprised to see in Science News, conclusions about causation made on the basis of correlational
research ("Keep on Going: Busy seniors live longer, more proof that it pays to stay active" SN: 7/15/06, p.
Ware and Galassi's piece reviews the use of correlational
approaches in school counseling research, and Bauman's article discusses comparison group studies.
She covers ethics, defining, measuring and manipulating variables, choosing descriptive methods, organizing data, correctly applying correlational
and statistical methods, testing hypotheses and inferential statistics, developing a logic of experiment design, using inferential statistics in two-group designs, using complex experimental designs and nonparametric procedures, and applying the APA communication guidelines.
But with so much emphasis on this type of research, they say qualitative and correlational
studies are being ignored.
Although the results of such correlational
research do not imply causation, Ogunseitan notes, they can offer insights to guide future research.
More often than not, papers publish correlational
data only--which have no relation to cause and effect--and imply cause-and-effect relationships.
Contrasts and effect sizes in behavioral research: A correlational
Reputable researchers have correlational
analysis techniques (e.g., factorial modelling, combining factor analysis and regression).
A content correlational
and factor analytic study of four tolerance of ambiguity questionnaires.