We develop a nonparametric specification test for continuous-time models using the transition density. Using a data transform and correcting for the boundary bias of kernel estimators, our test is robust to serial dependence in data and provides excellent finite sample performance. Besides univariate diffusion models, our test is applicable to a wide variety of continuous-time and discrete-time dynamic models, including time-inhomogeneous diffusion, GARCH, stochastic volatility, regime-switching, jump-diffusion, and multivariate diffusion models. A class of separate inference procedures is also proposed to help gauge possible sources of model mis-specification. We strongly reject a variety of univariate diffusion models for daily Eurodollar spot rates and some popular multivariate affine term structure models for monthly U.S. Treasury yields.

This paper considers time series Generalized Method of Moments (GMM) models where a subset of the parameters are time varying. We focus on an empirically relevant case with moderately large instabilities, which are well approximated by a local asymptotic embedding that does not allow the instability to be detected with certainty, even in the limit. We show that for many forms of the instability and a large class of GMM models, usual GMM inference on the subset of stable parameters is asymptotically unaffected by the partial instability. In the empirical analysis of presumably stable parameters—such as structural parameters in Euler conditions—one can thus ignore moderate instabilities in other parts of the model and still obtain approximately correct inference.

We propose a unique measure of information share based on the factor modeling of the price innovations, which we refer to as the Factor Information Share (FIS). We show that the proposed FIS is improved over two widely used measures by providing meaningful rationale and unique identifiability. Our simulation study suggests that FIS also leads to more accurate estimates of the market-specific contribution in the process of price discovery. The empirical results include both static and dynamic FIS of cross-listed Chinese banks traded on A-shares and H-shares. By incorporating the news sentiment, we find that positive news has a larger influence on A-shares’ FIS than negative news.

We examine the extent to which vertical and horizontal market structure can together explain incomplete retail pass-through. To answer this question, we use scanner data from a large U.S. retailer to estimate product level pass-through for three vertical structures: national brands, private label goods not manufactured by the retailer, and private label goods manufactured by the retailer. Our approach circumvents issues associated with internal firm prices and demonstrates that accounting for horizontal market structure is important for measuring the effects of vertical integration and reduced double marginalization on pass-through.

We develop a nonparametric specification test for continuous-time models using the transition density. Using a data transform and correcting for the boundary bias of kernel estimators, our test is robust to serial dependence in data and provides excellent finite sample performance. Besides univariate diffusion models, our test is applicable to a wide variety of continuous-time and discrete-time dynamic models, including time-inhomogeneous diffusion, GARCH, stochastic volatility, regime-switching, jump-diffusion, and multivariate diffusion models. A class of separate inference procedures is also proposed to help gauge possible sources of model misspecification. We strongly reject a variety of univariate diffusion models for daily Eurodollar spot rates and some popular multivariate affine term structure models for monthly U.S. Treasury yields.