Premium
COMMENTS ON GLOUDEMANS AND MILLER'S MULTIPLE REGRESSION ANALYSIS APPLIED TO RESIDENTIAL PROPERTIES
Author(s) -
Brobst Robert,
Gates Roger
Publication year - 1978
Publication title -
decision sciences
Language(s) - English
Resource type - Journals
SCImago Journal Rank - 1.238
H-Index - 108
eISSN - 1540-5915
pISSN - 0011-7315
DOI - 10.1111/j.1540-5915.1978.tb01376.x
Subject(s) - regression analysis , ordinal regression , miller , regression , econometrics , computer science , regression diagnostic , property (philosophy) , a priori and a posteriori , cross sectional regression , statistics , mathematics , polynomial regression , machine learning , epistemology , ecology , philosophy , biology
Gloudemans and Miller [6] provide an interesting and useful application of regression analysis to the problem of residential property assessment. However, there are a number of problems with their model. These problems include: failure to consider the pitfalls of using stepwise regression in exploratory studies; failure to discuss levels of significance and appropriateness of signs of individual regression results; the use of ordinal data in the regression analysis; the use of an obscure and incorrect procedure for inflation adjustment; and, a general lack of a priori reasoning in the development and analysis of the article. These problems are discussed and possible remedies are considered.