Three Essays in Time Series Econometric Analysis

This dissertation focused on developing new econometric methods that have practical implications for the accurate modelling and forecasting of macroeconomic and financial time series. The first chapter investigates changes in the factor structure of the U.S. economy. To do this a two-step Markov-switching static factor estimation procedure is developed and applied to a well-studied U.S. macroeconomic data set. Strong evidence for Markov-switching in the factors processes, with switching variances being most dominant, is found. The results suggest that regime-dependent factor processes are the main explanation for the diverging number of estimated factors in empirical applications and questions the global linearity assumption implicit in large dimensional factor models of the U.S. economy.The second chapter proposes alternative Heteroskedasticity and Autocorrelation Consistent (HAC) estimators with improved finite sample properties. This is achieved by exploiting existing transformations from the related Heteroskedasticity Consistent estimator literature. Monte Carlo simulation results provide strong evidence in favour of using these alternative estimators to construct standard error estimates instead of the traditional OLS residual-based estimator. In an empirical application to forecasting exchange rates it is shown how different inference from using the alternative HAC estimators can be important, not only from a statistical perspective, but also from an economic one as well.The third chapter introduces a test of symmetry for a stationary time series based on the difference between the dispersion above the central tendency of the series with that below it. The test has many attractive features: it is applicable to dependent processes, it has a familiar form, it can be implemented using regression, and it has a standard Gaussian limiting distribution under the null hypothesis of symmetry. The finite sample properties of the test are examined via Monte Carlo simulation and suggest that it is more powerful than competing tests in the literature for the DGPs considered. The test is then used to investigate business cycle asymmetry in U.S. nonfarm payroll data by sector. The results confirm previous findings that asymmetry is more often detected in goods producing sectors than service producing sectors