multicollinearity


Also found in: Dictionary, Thesaurus, Wikipedia.

multicollinearity

[‚məl·tē·kō‚lin·ē′ar·əd·ē]
(statistics)
A concept in regression analysis describing the situation where, because of the high degree of correlation between two or more independent variables, it is not possible to separate accurately the effect of each individual independent variable upon the dependent variable.
References in periodicals archive ?
While completely insignificant one year before the occurrence of the crisis, lagging the variable by two-year periods turns the current account balance into the second-best performing indicator, once controlling for the presence of multicollinearity. A strong performance is also evident for three-year lags.
An issue with applications of stochastic frontier analysis emerges when inputs are highly correlated, from which the multicollinearity problem arises, leading to precision loss in estimates.
It has been observed that the problem of autocorrelation and multicollinearity arise simultaneously in several cases.
[34, 35] proposed a new multivariate statistical analysis method to overcome multicollinearity, namely, partial least squares regression (PLS).
No multicollinearity among variables was observed, so these variables were offered to the multivariate logistic regression model process.
In general, the width of a confidence interval of an estimated regression coefficient increases when multicollinearity occurs.
On the other hand, our proposed method reduces the possible multicollinearity problem.
Some methods of variable selection, in addition to the effects on the dependent variable is not significant variables can also be removed from the variable group collinear relations in the screening effects on the dependent variable of a few variables significantly, so as to overcome the multicollinearity. However, for some practical problems, even if the independent variables have a co linear problem, we still want to establish the regression formula of the dependent variable Y and the given independent variables, such as the problem of economic analysis.
The sample and variables were described, and the results of the tests for assumptions and multicollinearity were reported.
However, in situations such as faced in the Western case, where the high degree of competition causes significant multicollinearity among both purchase and sale prices, substantial statistical difficulties impede precise estimations.
These results indicate that the degree of multicollinearity among the four predictors could be negligible.
Several categories were integrated to avoid multicollinearity and to achieve unbiased outcome.