Social Science Data Analysis by Florian G. Hartmann & Johannes Kopp & Daniel Lois

Author:Florian G. Hartmann & Johannes Kopp & Daniel Lois
Language: eng
Format: epub
ISBN: 9783658412302
Publisher: Springer Fachmedien Wiesbaden

Here, n denotes the number of cases and j the number of predictors b1 to bj in the model. In our case, the corrected and the uncorrected coefficient of determination differ only slightly: 0.058 (corrected) vs. 0.059 (uncorrected).

The great advantage of multivariate regressions is that they allow to control the influence of different independent variables simultaneously. Thus, the effect of age described above of 0.006 indicates this influence under control of the level of the ISEI variable. This means that in the context of the multivariate regression, the effect of age is determined by taking into account the effect of the ISEI—the ISEI is thus kept constant, so to speak. Of course, this also applies vice versa for determining the influence of the father’s ISEI, taking into account the effect of age. How this is technically to be understood is presented in a brief excursion.

Excursion: Control of third variables

The basic idea of multivariate methods is to determine the influence of a certain independent variable while controlling for other independent variables. In our example, the effect of the father’s ISEI on the traditional gender role orientation is to be clarified while controlling for age. To better understand how this is done, three steps are necessary: In a first step, the influence of age on the traditional gender role orientation must be examined. As shown above (see Table 6.5), the following regression line results from the GGSS data:

Download

Copyright Disclaimer:
This site does not store any files on its server. We only index and link to content provided by other sites. Please contact the content providers to delete copyright contents if any and email us, we'll remove relevant links or contents immediately.