Get 20M+ Full-Text Papers For Less Than $1.50/day. Start a 14-Day Trial for You or Your Team.

Learn More →

A Second Comment on Homogeneity of Regression:

A Second Comment on Homogeneity of Regression: WILLIAM E. GEESLIN Stanford University In the comment section of the November AERJ, Halperin (1969) seems to suggest that homogeneity of regression techniques may be impossible to calculate. Halperin points out correctly that there are some notational errors in Wilson and Carry's article (Wilson and Carry, 1969). However, Halperin adds to the confusion rather than merely correcting the mistakes. The simplest way to correct the Wilson and Carry paper is as follows: Y (i ) has one row, i.e. a 1 X n matrix X (i ) has p rows, i.e. a p X n matrix β(i) and β ar e both 1 X p matrices Now, checking the matrix multiplication we see SS i = β (Y(i) — β • X(i) ) • (Y(i) — β • X(i)) T i = l Now β • X (i ) gives a 1 X n matrix which can be subtracted from Y (i) . (Y(i> — β • X (i) ) T will be a n X 1 matrix which means that SS will be 1 X 1 matrix or a scalar as stated by Wilson and Carry. Two other errors in the Wilson and Carry article were pointed out http://www.deepdyve.com/assets/images/DeepDyve-Logo-lg.png American Educational Research Journal SAGE

A Second Comment on Homogeneity of Regression:

Geeslin, William E.
American Educational Research Journal , Volume 7 (4): 3 – Jun 23, 2016
Download PDF
3 pages

Loading next page...
 
/lp/sage/a-second-comment-on-homogeneity-of-regression-i1fnta3tIZ

References (4)

Publisher
SAGE
Copyright
Copyright © 2019 by American Educational Research Association
ISSN
0002-8312
eISSN
1935-1011
DOI
10.3102/00028312007004636
Publisher site
See Article on Publisher Site

Abstract

WILLIAM E. GEESLIN Stanford University In the comment section of the November AERJ, Halperin (1969) seems to suggest that homogeneity of regression techniques may be impossible to calculate. Halperin points out correctly that there are some notational errors in Wilson and Carry's article (Wilson and Carry, 1969). However, Halperin adds to the confusion rather than merely correcting the mistakes. The simplest way to correct the Wilson and Carry paper is as follows: Y (i ) has one row, i.e. a 1 X n matrix X (i ) has p rows, i.e. a p X n matrix β(i) and β ar e both 1 X p matrices Now, checking the matrix multiplication we see SS i = β (Y(i) — β • X(i) ) • (Y(i) — β • X(i)) T i = l Now β • X (i ) gives a 1 X n matrix which can be subtracted from Y (i) . (Y(i> — β • X (i) ) T will be a n X 1 matrix which means that SS will be 1 X 1 matrix or a scalar as stated by Wilson and Carry. Two other errors in the Wilson and Carry article were pointed out

Journal

American Educational Research Journal – SAGE

Published: Jun 23, 2016

There are no references for this article.