Abstract
MATCHING processes are constantly in use in the social sciences. Often their use is explicit, as in studies of the relative effects of different experiences or procedures. In other cases they are implicit, as in the use of specific controls for the selection of consumer panels or in quota surveys. They are also implicit in many extrapolation processes. Even so, the variables used for matching processes are in most cases of non-empirical origin, and are selected on the basis of either custom or hunch. The result may well be that the matching is inadequate, sometimes completely so.
Similar content being viewed by others
Article PDF
References
Garrett, H. E., “Statistics in Psychology and Education” (1947).
Belson, W. A., App. Statistics, 5 (3), 195 (1956).
Belson, W. A., Pub. Opin. Quart., 22 (1), 11 (1958).
Belson, W. A.,Rep. British Broadcasting Corporation (in preparation).
Williams, W. T., and Lance, G. N., Nature, 182, 1755 (1958).
Author information
Authors and Affiliations
Rights and permissions
About this article
Cite this article
BELSON, W. Matching and Prediction in the Social Sciences. Nature 183, 772 (1959). https://doi.org/10.1038/183772a0
Issue Date:
DOI: https://doi.org/10.1038/183772a0
Comments
By submitting a comment you agree to abide by our Terms and Community Guidelines. If you find something abusive or that does not comply with our terms or guidelines please flag it as inappropriate.