Essays on empirical time series modeling with causality and structural change

In this dissertation, three related issues of building empirical time series models forfinancial markets are investigated with respect to contemporaneous causality, dynamics,and structural change. In the first essay, nation-wide industry information transmissionamong stock returns of ten sectors in the U.S. economy is examined through theDirected Acyclical Graph (DAG) for contemporaneous causality and Bernankedecomposition for dynamics. The evidence shows that the information technology sectoris the most root cause sector. Test results show that DAG from ex ante forecastinnovations is consistent with the DAG fro m ex post fit innovations. This supportsinnovation accounting based on DAGs using ex post innovations.In the second essay, the contemporaneous/dynamic behaviors of real estate and stockreturns are investigated. Selected macroeconomic variables are included in the model toexplain recent movements of both returns. During 1971-2004, there was a singlestructural break in October 1980. A distinct difference in contemporaneous causalstructure before and after the break is found. DAG results show that REITs take the role of a causal parent after the break. Innovation accounting shows significantly positiveresponses of real estate returns due to an initial shock in default risk but insignificantresponses of stock returns. Also, a shock in short run interest rates affects real estatereturns negatively with significance but does not affect stock returns.In the third essay, a structural change in the volatility of five Asian and U.S. stockmarkets is examined during the post-liberalization period (1990-2005) in the Asianfinancial markets, using the Sup LM test. Four Asian financial markets (Hong Kong,Japan, Korea, and Singapore) experienced structural changes. However, test results donot support the existence of structural change in volatility for Thailand and U.S. Also,results show that the Generalized Autoregressive Conditional Heteroskedasticity(GARCH) persistent coefficient increases, but the Autoregressive Conditionalheteroskedasticity (ARCH) impact coefficient, implying short run adjustment, decreasesin Asian markets.In conclusion, when the econometric model is set up, it is necessary to considercontemporaneous causality and possible structural breaks (changes). The dissertationemphasizes causal inference and structural consistency in econometric modeling. Ithighlights their importance in discovering contemporaneous/dynamic causalrelationships among variables. These characteristics will likely be helpful in generatingaccurate forecasts.