Equity estimation has been proposed as a possibly superior technique for estimating market response functions in the presence of high predictor-variable collinearity. The relative performance of equity, ridge, and ordinary least squares (OLS) estimators is examined using simulation experiments. In part, findings are consistent with prior research and indicate that, under certain conditions, equity outperforms OLS and ridge on a number of important criteria, and equity yields coefficient estimates that assign more equal explanatory weight to correlated predictor variables than does OLS or ridge. As collinearity increases, this tendency becomes very pronounced, to the point where equity yields estimated standardized coefficients more equal in magnitude irrespective of other conditions, such as true coefficient values and model explanatory power.