multicollinear

Labor economists routinely tease out relationships in multicollinear worlds in other aspects with great care, and great success, but it seems to these same people that estimating IQ's effect is impossible Heckman's other tact, that IQ is malleable, was abandoned when he found that IQ was pretty consistent over an individual's life.

Two Educational Heresies: Ability Bias vs. Signaling, Bryan Caplan | EconLog | Library of Economics and Liberty 2009

However, from a multiple regression point of view, the non correlation reduces multicollinear problems which helps reduce variance inflation.

Nature's Style: "Naturally Orthogonal"? « Climate Audit 2007

“from a multiple regression point of view, the non correlation reduces multicollinear problems which helps reduce variance inflation”

Nature's Style: "Naturally Orthogonal"? « Climate Audit 2007

IF there’s a “signal”, the series will be multicollinear – something that’s not wanted in regressions, but desirable in signal processing.

Regression and Varimax Rotation « Climate Audit 2007

You’d certainly learn to more wary of things like stepwise regression between multicollinear time series which Rob Wilson has employed in his most recent article, argggh.

Curry on the Wegman Reports « Climate Audit 2006