Structural Estimation of Dynamic Macroeconomic Models using Higher-Frequency Financial Data

In this paper we show how high-frequency financial data can be used in a combined macro-finance framework to estimate the underlying structural parameters. Our formulation of the model allows for substituting macrovariables by asset prices in a way that enables casting the relevant estimation equationspartly (or completely) in terms of financial data. We show that using only financial data allows for identification of the majority of the relevant parameters. Adding macrodata allows for identification of all parameters. In our simulation study, we find that it also improves the accuracy of the parameter estimates. In the empirical application we use interest rate, macro, and S&P500 stock index data, and compare the results using different combinations of macroand financial variables.