Studies And Applications Of Mixed Frequency Data Model In Chinese Macroeconomy

There are many time series data in macroeconomic time series can reflect the states andtrends of current macroeconomy, such as, the quarterly GDP data, the monthly CPI and PPI data,daily financial market return data, intraday stock market volatility data, and so on. These data arefocused by individuals, enterprises, organizations, countries, and even the internationalcommunity. They try to use different data processing methods and build a variety of models tograb information from these complex data, and use them to do model estimates and projections,and then use the information to do savings, investment, decision-making and some othereconomic behaviors. However, the time series data listed above are complex, for example, thedata length, sampling frequency, as well as the data attributions are not the same, while, wemainly use the same frequency data in our time series models. In order to use the mixed frequencydate, pre-treatment are used. Some studies aggregate the high-frequency data to low frequencydata, and some interpolate the low-frequency data into high-frequency data. However, theaggregation destroys sample information, and the interpolations make some artificial data andlack economic theory support. In empirical study, the aggregation is more common thaninterpolation, and interpolation methods are used due to the data shortage or the need of themodels. The appearance of mixed frequency data can directly use the different frequencies data,and solve the above dilemma.Mixed frequency models are developed and widely used, since the accumulation of variousfrequency time data, and the development of scientific computing. For example, using mixedfrequency model to improve prediction accuracy, prediction timely forecasting and nowcasting,combining the mixed frequency model with econometric models to improve the accuracy ofmodel estimates and achieve the improvement by comparing the model with same frequencymodel. In my opinion, empirical study should use the original mixed frequency data with mixedfrequency model when the data exsit different frequencies. We use mixed frequency data model todo empirical studies in China’s macroeconomic. On one hand, we focus on the application of themixed frequency data model in Chinese macroeconomic forecasts, including the applications ofmixed frequency model in prediction, the effectiveness of the mixed frequency model and the evaluation issues. On the other hand, we pay attention to the combination of mixed frequency andeconometric models, such as factor mixed frequency model, Markov switching mixed frequencymodel, and mixed frequency vector regression model.We illustrate the research and application by the construction, estimation, and prediction ofmixed frequency models. It includes the following parts.First, Chapter3preliminarily analyzes the effectiveness and prediction accuracy by real-timeforecasting and short-term prediction of China’s macroeconomic aggregates variables. Then, weexplore the selection problem of the lag of high-frequency data, forecast horizon, and the lag ofauto regression. And then, use the results to build multivariate MIDAS models to do real-timeforecasting and short-term nowcasting. The empirical results show that the mixed frequency datamodel has a significant comparative advantage, when compared with same frequency models.Secondly, Chapter4comparatively analyzes the effectiveness and the prediction accuracy ofmixed frequency vector autoregressive (MF-VAR). MF-VAR model not only has the ability toreflect the dynamic relationship between variables, but also can use the kalman filter to doestimation and prediction. It is not enough to use a single or a few economic variables to predictand forecast macroeconomic trends, when the economic data have become increasingly diverse,and the condition of economic become complicate. Therefore, we use a pool of Chinesemacroeconomic data to anylize the MF-VAR model and compare the results with MIDAS models.The empirical results show that there are differences between the results with a single variableprediction, while it is still valid and applicable in general. The comparative analysis of theMIDAS models and the MF-VAR models show that the prediction of MF-VAR has better resultsin the longer periods, while the MIDAS models have relative advantage in a short-term. So it isuseful to combine these two mixed frequency model to provide more accurate predictions inreal-time forecasting and short-term forecasts of real GDP in China.Thirdly, Chapter5checkes and compares the effectiveness and the prediction accuracy withfactor mixed frequency model. It is not enough to forecast and nowcast the economy with singleor a few economic variables in a complex economic situation. Therefore, we adopt factor modelto extract macroeconomic factor with a large number of macroeconomic aggregates economicdata (including the data of leading indicator data, consistent indicator data and lagging indicators),and combined with MIDAS and MF-VAR models to do real-time forecasting and nowcasting, andthen compare these two mixed frequency data model with each other. The empirical results showthat, the two mixed frequency models, which using combined factor model has a comparativeadvantage compared to the traditional autoregressive model, so the projections and forecasts ofthe two mixed frequency models are applicable and effective. For the compare of the forecast results of the two models, we find there are not have a perfect model. MF-VAR model has anoverall comparative advantage in the short-term forecasting and nowcasting, while the MIDASmodel has a relatively good performance in the longer forecast period.Fourth, Chapter6characterizes the long-run equilibrium and short-term fluctuation withcointergration MIDAS (CoMIDAS) model and uses it for analysis and prediction. For the reasonof information loss when we difference the series for stationary, and cannot get the long-runequilibrium cointegration relationship, we use the CoMIDAS model to analyze the long-termcointegration relationship between the output and the money supply, and show the influence ofshort-term high-frequency changes in the money supply on the change in output. The empiricalresults show the existence of long-run equilibrium relationship between money supply and outputin China, and reflect the important reason between output volatility and short-term money supply.Fifth, Chapter7monitors and dates the business cycle with Markov Switching MIDAS(MS-MIDAS) models. We combine the mixed frequency model with nonlinear econometricmodels to characterize the non-linear and non-stationary relationship in Chinese economy, sincelinear mixed frequency regression model cannot characterize the non-stationary and non-linearrelationship between the mixed frequency data. MS-MIDAS model not only has the same abilitywith traditional regime switching in characteristic the regime changes in the mean and variance,but also can measure the ability change in forecasting low frequency data series with highfrequency data, as the regime and market conditions change. Thus, we have more accurate resultsin the nowcasting and short-term forecasts with this model. The empirical results show theadvantage of MS-MIDAS model, when compared with the results of the traditional samefrequency model, and it also precise dating the turning points and phases of business cycle.Sixth, Chapter8analyzes the supply and demand shocks based on Bayesian mixedFrequency VAR (BMF-VAR) model. We apply Bayesian approach to get the impact of supply anddemand in China and its effect on the monthly level, and the results show that China’s output ismainly affected by supply factors, while inflation is mainly affected by demand factors.In short, based on the theory and estimation of mixed frequency data model, we do real-timeforecasting and short-term forecasting with mixed frequency data in China. Then, we buildnonlinear mixed frequency models with nonlinear and a pool of series to analyze themacroeconomic theory and laws, such as business cycle, monetary policy and AS-AD model.