Premium
Multivariate Analysis of Economic Variables
Author(s) -
Gudmundsson G.
Publication year - 1977
Publication title -
journal of the royal statistical society: series c (applied statistics)
Language(s) - English
Resource type - Journals
SCImago Journal Rank - 1.205
H-Index - 72
eISSN - 1467-9876
pISSN - 0035-9254
DOI - 10.2307/2346867
Subject(s) - multivariate statistics , multivariate analysis , statistics , multivariate analysis of variance , mathematics , econometrics
Summary In econometric models each dependent variable is usually a linear function of a small number of dependent and independent variables which are selected on economic considerations. Here uncorrelated linear combinations of all independent variables are used for explaining every dependent variable. The linear combinations are selected by maximizing the sum of their squared correlation coefficients with the dependent variables. Two numerical examples are given by data from “An econometric model of the United Kingdom” by Klein et al. (1961). One is based on the data after subtracting the average value of each quarter from respective series. In the second example the values of the variables are residuals from a simple Box‐Jenkins model of each series.