A new hidden Markov model for the space-time evolution of daily rainfall is developed which models precipitation within hidden regional weather types by censored power-transformed Gaussian distributions. The latter provide flexible and interpretable multivariate models for the mixed...

Evolving volatility is a dominant feature observed in most financial time series and a key parameter used in option pricing and many other financial risk analyses. A number of methods for non-parametric scale estimation are reviewed and assessed with regard to the stylized features of financial...

The variance of New Zealand's real GDP has fallen by a third since the mid 1980s. Decomposing the variance of chain-weighted estimates of production-based real GDP growth since 1977 into sector shares, sector growth rate variances and co-variances, this paper concludes that the principal reason...

This paper fits Markov switching models to quarterly New Zealand aggregate GDP growth rates for the period 1978:1 to 2003:2 in order to analyse changes in mean and volatility over time. The models considered are drawn from a simple class of parsimonious, four state, Markov switching models which...

The variance of New Zealand’s real GDP has declined since the mid-1980s. To investigate why, this paper decomposes the variance of chain-weighted estimates of production-based real GDP growth into sector shares, sector growth rate variances and co-variances. The principal explanation for the...

A non-linear dynamic model is introduced for multiplicative seasonal time series that follows and extends the X-11 paradigm where the observed time series is a product of trend, seasonal and irregular factors. A selection of standard seasonal and trend component models used in additive dynamic...

We present new empirical evidence on trend robustness and end-point issues, utilising the macroeconomic data set investigated in McKelvie and Hall (2012). We consider the relative merits of non-robust Hodrick-Prescott (HP) and robust loess (LOcal regrESSion) trend filtering methods, and assess...