Dummy Variables and the Analysis of Covariance (Classic Reprint) - Softcover

White, William L.

9781332258741: Dummy Variables and the Analysis of Covariance (Classic Reprint)

Softcover

ISBN 10: 1332258743 ISBN 13: 9781332258741

Verlag: Forgotten Books, 2018

Alle Exemplare dieser ISBN-Ausgabe

0 Gebraucht

2 Neu

Von EUR 19,08

Excerpt from Dummy Variables and the Analysis of Covariance

It is the purpose of this article to suggest that the technique of the analysis of covariance dominates, in a statistical sense, the use of dummy variables. We shall first show how dummy variable regressions and the analysis of covariance are related. This comparison will show why we think the analysis of covariance is a more useful technique than the use of dummy variables in a regression analysis. Then in an attempt to make our prescription of the analysis of covariance somewhat easier to apply we shall develop a set of computational short cuts. In our view these result in computational difficulties of such small extra cost that they seem clearly to suggest that the analysis of covariance is a technique much more useful than simply inserting dummy variables into regressions.

About the Publisher

Forgotten Books publishes hundreds of thousands of rare and classic books. Find more at www.forgottenbooks.com

This book is a reproduction of an important historical work. Forgotten Books uses state-of-the-art technology to digitally reconstruct the work, preserving the original format whilst repairing imperfections present in the aged copy. In rare cases, an imperfection in the original, such as a blemish or missing page, may be replicated in our edition. We do, however, repair the vast majority of imperfections successfully; any imperfections that remain are intentionally left to preserve the state of such historical works.

Die Inhaltsangabe kann sich auf eine andere Ausgabe dieses Titels beziehen.

Rese�a del editor

Excerpt from Dummy Variables and the Analysis of Covariance

Until the last fev years, nsoet regression studies have been constructed around either time series data or cross section data. As the art of ncdel building developed, considerable interest arose in the testing of hypotheses which required the pooling together of data frctn several cross sections, e.g., the data on several fims in each of many years. A veil known prcblcn in tine scries analysis had been that of autocorrelated errors. It was known that this phenomenon bad its counterpart in intcr-tcnporal or pooled cross section analysis. Regressions run on pooled cross section data assuae that error teras are independent drawings while in fact the elements in each cross section arc often saaplcd in each of the cross section years. If the errors arc not independent, that is, if there are consistent conponenta to the error term of each element every tine it is sanpled, it has been shown that the unexplained variance and the cstinntcs of the slope coefficients which arise free the usual regression techniques are in error. Carter^2ihowed that the inclusion in the pooled regression equation of a discrete (mutually exclusive and exhaustive} dumy variable (aero-one) for each cell would result in unbiased estimates of unexplained variance and slope coefficients and thus retain the desired properties of classical regression analysis.

Until recently, these techniques have required such large computational capacity that they were of little practical interest. With the advent of more exotic computation facilities, however, seme earlier statistical devices which require the pooling of data from cross sections and time scries have come to be of real use.

During this same time, the dunmy variable technique suggested by-Carter has been shown to have further interest in a paper by Suits. Suits (6) suggests that the coefficient of these dummy variables can be of significant Interest in and of then=elves. That is, the coefficients associated with the dunmy variables specifically account for these peculiarities associated with each cell that are not "explained" by the included independent variobles.

About the Publisher

Forgotten Books publishes hundreds of thousands of rare and classic books. Find more at www.forgottenbooks.com

This book is a reproduction of an important historical work. Forgotten Books uses state-of-the-art technology to digitally reconstruct the work, preserving the original format whilst repairing imperfections present in the aged copy. In rare cases, an imperfection in the original, such as a blemish or missing page, may be replicated in our edition. We do, however, repair the vast majority of imperfections successfully; any imperfections that remain are intentionally left to preserve the state of such historical works.

��ber diesen Titel� kann sich auf eine andere Ausgabe dieses Titels beziehen.