Testing For Uncorrelated Residuals In Dynamic Count Models With An Application To Asset Reorganization

In this paper,we propose a new diagnostic test for dynamic count models.Our test proposal is of the Portmanteau-type test for lack of residual autocorrelation.This test has a quadratic form and follows a chi squared distribution asymptotically.Its simplicity comes from an innovative transform of the sample autocorrelations of residuals,which allows for the uncorrelated innovations and the parameters estimation effect.A major advantage of our test statistic is that it is asymptotically pivotal when innovations are uncorrelated,but not necessarily iid nor a martingale difference.which is in contrast with classical lack of autocorrelation tests.e.g.Ljung and Box(1978).A comprehensive Monte Carlo experiment demonstrates that the new Portmanteau test enjoys better size and power balance than Ljung and Box(1978),when the sample size is 200 and 400.In the empirical part,using the dynamic counting model described in this article,we will not focus on specific listed companies or industries from a macro perspective.We will use the major reorganization of listed companies as an independent event to study the number of major asset reorganizations that occur on the Shanghai Stock Exchange every month.,And use the residual autocorrelation test proposed in this paper to test whether the model setting is correct.The results of the study show that there is a significant negative correlation between the macroeconomic developments lagging by three months and the monthly count of major asset reorganization suspension events on the Shanghai Stock Exchange.