Wagner's Law revisited: cointegration and causality tests for New Zealand

Wagner's Law states that the share of government expenditure in Gross National Product (GNP) will increase with economic development; many associated empirical studies substitute GNP with Gross Domestic Product (GDP). This article presents an empirical investigation into the validity of Wagner's Law for New Zealand over the period 1960 to 2007 and compares the results obtained using these two measures of output. Application of the Autoregressive Distributed Lag (ARDL) bounds test suggests a cointegrating relationship between either output measure and the share of government spending, and further application of General to Specific (GETS), Engle and Granger (EG), Phillip Hansen's Fully Modified Ordinary Least Squares (FMOLS) and Johansen's time series techniques illustrate statistical robustness and an income elasticity between 0.56 and 0.84. The results suggest that output measures Granger cause the share of government expenditure in the long run, thereby providing support for Wagner's Law, and these results are stable irrespective of the chosen output measure.