Hierarchical modelling

• Statistics for Applications

• Autoregressive Prediction with Rolling Mechanism for Time Series Forecasting with Small Sample Size

• The M3-Competition: results, conclusions and implications

• Forecasting Economic Aggregates Using Dynamic Component Grouping

• Forecasting output growth rates and median output growth rates: a hierarchical Bayesian approach

• Forecasting Short Time Series with the Bayesian Autoregression
  and the Soft Computing Prior Information

• Forecasting analogous time series: Bayesian Pooling

• Forecasting international growth rates using Bayesian shrinkage and other procedures: ARLI

• Bayesian Forecasting for Seemingly Unrelated Time Series: Application to Local Government Revenue Forecasting: Kalman Filter, Conditionally Independent Hierarchical method, BVAR. Time series forecasting of demand for goods or services often involves cases subject to structural change caused by external influences like business cycles or competi- tors' actions. Methods designed for such cases, like ex- ponential smoothing (Brown 1962) and the Multi-State Kalman Filter (MSKF) method (Harrison and Stevens 1971), revise model parameter estimates over time.

• Optimal combination forecasts for hierarchical time series: bottom-up and optimal combination methods

• Time-series clustering – Decade overview

• Forecasting Method for Grouped Time Series with the Use of k-Means Algorithm

• Forecasting with group seasonality

• Statistical Shrinkage