You are not currently logged in.
Access your personal account or get JSTOR access through your library or other institution:
If You Use a Screen ReaderThis content is available through Read Online (Free) program, which relies on page scans. Since scans are not currently available to screen readers, please contact JSTOR User Support for access. We'll provide a PDF copy for your screen reader.
Incomplete Matching in Ex Post Facto Studies
American Journal of Sociology
Vol. 55, No. 5 (Mar., 1950), pp. 485-487
Published by: The University of Chicago Press
Stable URL: http://www.jstor.org/stable/2772105
Page Count: 3
Since scans are not currently available to screen readers, please contact JSTOR User Support for access. We'll provide a PDF copy for your screen reader.
Preview not available
In every ex post facto matched-group study a large proportion of the cases in the experimental group are not matched bacause of the limited size of the control panel. This introduces a serious sampling problem, since the difference between experimental and matched group may not be the same for cases matched easily as for those for which matching is difficult. Data are presented to demonstrate that educational differences between matched groups of migrants and nonmigrants are statistically significant when 58 per cent of the original experimental group is matched but not when 89 per cent of the cases is matched.
American Journal of Sociology © 1950 The University of Chicago Press