Two key economic issues are:

• Given recent economic data, what is the chance of a next economic recession or expansion and when is a turning point expected between one situation and the next one?
• Given the different levels of income between individuals, will an average person be able to repay bank loans in good and bad times?

In recent years many different information sources have become available that can be used to analyze these and other key economic issues. Such as: large macroeconomic data sets, big microeconomic data sets and huge opinion pools. These information sources can be combined applying advanced algorithms like machine learning and parallel computing. My research has therefore focused on two topics:

• Develop a Forecast Density Combination (FDC) approach using a set of econometric models where large data sets are available and advanced algorithms can be applied to compute the complete combined forecast density with weights that are learning over time.
• Use the ‘computational revolution’ that occurred in Monte Carlo simulation methods in Bayesian econometrics in order to develop a novel class of algorithms that approximates very nonstandard stochastic distributions of econometric models using mixtures of probability processes.

This research allows for predictive and policy analysis of operational models in economics and finance. Ultimately this leads to improved measurement of risk, uncertainty and policy effectiveness in the context of important economic issues like the uncertainty of job placement, duration and retirement; time-varying effects of education on earned income; length and duration of shock effects in the macro-economy and the financial world and better risk analysis of extreme outcomes and crises.
Specific methodological and computational research topics are:

• Simulation-Based Bayesian Econometrics (SBBE)
• Long-run macro-econometric modeling: growth and cycles
• Short-run macro-finance modeling: Volatility and Risk
• Mixture processes/Neural Networks with learning
• Income distributions using large sets of micro data.