Estimating extreme monthly rainfall for Spain using non-stationary techniques

In hydrology, extreme value analysis is normally applied at stationary yearly maxima. However, climate variability can bias the estimation of extremes by partially invalidating assumption. Extreme for sub-yearly data may depart from stationarity (since maxima one month not be exchangeable with another) in terms requiring to include it analysis. Here, we analyse non-stationary structure monthly rainfall Spain using two approaches: a parametric approach and an based on autoregressive time series models. Our considers seasonality, long-term trends both approaches, compares including their goodness fit complexity. The uses maximum likelihood Bayesian techniques. results show that models outperform models, providing more accurate representation events when extrapolating outside period fit.