Confounding and collinearity in regression analysis: a cautionary tale and an alternative procedure, illustrated by studies of British voting behaviour.

First, the regression coefficient for qualifications increases from 0.52 (the first block in Table 1 ) to 0.79; and second—and very importantly—the (highly significant) coefficient for deprivation is positive (0.23) when that is the only variable regressed against UKIP performance but negative (− 0.41), and again highly significant statistically, when both variables are included.

also in 132,142 other papers