This paper examines the housing-output growth nexus in South Africa by accounting for the time variationin the causal link with a bootstrapped rolling Granger non-causality test. We use quarterly data on real grossdomestic product, real house prices, real gross fixed capital formation and number of building plans passed.Our data span 1971Q2–2012Q2. Using full sample bootstrap Granger causality tests, we find a uni-directionalcausality from output to number of building plans passed; a uni-directional causality from real house price tooutput and a bi-directional causal link between residential investment and output. However, using parameterstability tests, we show that estimated VARs are unstable, thus full-sample Granger causality inference maybe invalid. Hence, we use a bootstrap rolling window estimation to evaluate Granger causality between thehousing variables and the growth rate. In general, we find that the causality from housing to output and, viceversa, differ across different sample periods due to structural changes. Specifically speaking, house price isfound to have the strongest causal relationship with output compared to residential investment and numberof building plans passed, with real house price showing predictive ability in all but one downward phase ofthe business cycle during this period.