This paper aims to explain changes in real house prices in Australia from 1970 to 2003. We develop and estimate a long‐run equilibrium model that shows the real long‐run economic determinants of house prices and a short‐run asymmetric error correction model to represent house price changes in the short run. We find that, in the long run, real house prices are determined significantly and positively by real disposable income and the consumer price index. They are also determined significantly and negatively by the unemployment rate, real mortgage rates, equity prices and the housing stock. Employing our short‐run asymmetric error correction model, we find that there are significant lags in adjustment to equilibrium. When real house prices are rising at more than 2 per cent per annum, the housing market adjusts to equilibrium in approximately four quarters. When real house prices are static or falling, the adjustment process takes six quarters.

Standard-Nutzungsbedingungen:Die Dokumente auf EconStor dürfen zu eigenen wissenschaftlichen Zwecken und zum Privatgebrauch gespeichert und kopiert werden.Sie dürfen die Dokumente nicht für öffentliche oder kommerzielle Zwecke vervielfältigen, öffentlich ausstellen, öffentlich zugänglich machen, vertreiben oder anderweitig nutzen.Sofern die Verfasser die Dokumente unter Open-Content-Lizenzen (insbesondere CC-Lizenzen) zur Verfügung gestellt haben sollten, gelten abweichend von diesen Nutzungsbedingungen die in der dort genannten Lizenz gewährten Nutzungsrechte. Abstract. Changes in residual volatility in vector autoregressive (VAR) models can be used for identifying structural shocks in a structural VAR analysis. Testable conditions are given for full identification for the case where the volatility changes can be modelled by a multivariate GARCH process. Formal statistical tests are presented for identification and their small sample properties are investigated via a Monte Carlo study. The tests are applied to investigate the validity of the identification conditions in a study of the effects of U.S. monetary policy on exchange rates. It is found that the data do not support full identification in most of the models considered, and the implied problems for the interpretation of the results are discussed. Terms of use: Documents in

We use the cost-of-carry model to investigate the extent of market efficiency in the EU futures market for carbon dioxide allowances over the period of June 2005 to December 2007. We reject the cost-of-carry hypothesis for the entire data sample, but find some evidence of improvement in market efficiency over the period. Recursive estimates of some cost-of-carry model parameters start approaching their theoretical values when estimated on progressively smaller and more recent sub-samples.

a b s t r a c tWe propose an identified structural GARCH model to disentangle the dynamics of financial market crises. We distinguish between the hypersensitivity of a domestic market in crisis to news from foreign non-crisis markets, and the contagion imported to a tranquil domestic market from foreign crises. The model also enables us to connect unobserved structural shocks with their source markets using variance decompositions and to compare the size and dynamics of impulses during crises periods with tranquil period impulses. To illustrate, we apply the method to data from the 1997-1998 Asian financial crisis which consists of a complicated set of interacting crises. We find significant hypersensitivity and contagion between these markets but also show that links may strengthen or weaken. Impulse response functions for an equally-weighted equity portfolio show the increasing dominance of Korean and Hong Kong shocks during the crises and covariance responses demonstrate multiple layers of contagion effects.

We employ 47 different algorithms to forecast Australian log real house prices and growth rates, and compare their ability to produce accurate out-of-sample predictions. The algorithms, which are specified in both singleand multi-equation frameworks, consist of traditional time series models, machine learning (ML) procedures, and deep learning neural networks. A method is adopted to compute iterated multistep forecasts from nonlinear ML specifications. While the rankings of forecast accuracy depend on the length of the forecast horizon, as well as on the choice of the dependent variable (log price or growth rate), a few generalizations can be made. For one-and two-quarter-ahead forecasts we find a large number of algorithms that outperform the random walk with drift benchmark. We also report several such outperformances at longer horizons of four and eight quarters, although these are not statistically significant at any conventional level. Six of the eight top forecasts (4 horizons × 2 dependent variables) are generated by the same algorithm, namely a linear support vector regressor (SVR). The other two highest ranked forecasts are produced as simple mean forecast combinations. Linear autoregressive moving average and vector autoregression models produce accurate olne-quarter-ahead predictions, while forecasts generated by deep learning nets rank well across medium and long forecast horizons.