Joachim Grammig

Non-monotonic hazard functions and the autoregressive conditional duration model

This paper shows that the monotonicity of the conditional hazard in traditional ACD models is both econometrically important and empirically invalid. To counter this problem we introduce a more flexible parametric model which is easy to fit and performs well both in simulation studies and in practice. In an empirical application to NYSE price duration processes, we show that non-monotonic conditional hazard functions are indicated for all stocks. Recently proposed specification tests for financial duration models clearly reject the standard ACD models, whereas the results for the new model are quite favorable.

Knowing me, knowing you:: Trader anonymity and informed trading in parallel markets☆

Abstract In this paper we empirically analyze whether the degree of trader anonymity is related to the probability of information-based trading. We use data from the German stock market where non-anonymous traditional floor based exchanges co-exist with an anonymous computerized trading system. We use an extended version of the Easley et al. (J. Finance 51 (1996) 1405) model that allows for simultaneous estimation for two parallel markets. We find that the probability of informed trading is significantly lower in the floor based trading system. We further document that the size of the spread and the adverse selection component are positively related to the estimated probabilities of information-based trading.

Modeling the interdependence of volatility and inter-transaction duration processes

In this paper we motivate, specify and estimate a model in which the intra-day volatilty process affects the inter-transaction duration process and vice versa. In order to solve the estimation problems implied by this interdependent formulation, we first propose a GMM estimation procedure for the Autoregressive Conditional Duration model. The method is then extended to the simultaneous estimation of the interdependent duration-volatility model. In an empirical application we utilize the model for an indirect test of the hypothesis that volatility is caused by private information that affects prices when informed investors trade. The result that volatility shocks significantly increase expected inter-transaction durations supports this hypothesis.

Commonalities in the order book

This paper uses data from one of the most important European stock markets and shows that, in line with predictions from theoretical market microstructure, a small number of latent factors captures most of the variation in stock specific order books. We show that these order book commonalities are much stronger than liquidity commonality across stocks. The result that bid and ask side as well as the visible and hidden parts of the order book exhibit quite specific dynamics is interpreted as evidence that open order book markets attract a heterogeneous trader population in terms of asset valuations and impatience. Quantifying the informational content of the extracted factors with respect to the evolution of the asset price, we find that the factor information shares are highest (about 10%) for less frequently traded stocks. We also show that the informational content of hidden orders is limited.

Telltale Tails: A New Approach to Estimating Unique Market Information Shares

The trading of securities on multiple markets raises the question of each market’s share in the discovery of the informationally efficient price. We exploit salient distributional features of multivariate financial price processes to uniquely determine these contributions, thereby resolving the main drawback of the widely used Hasbrouck (1995) methodology, which merely provides upper and lower bounds of a market’s information share. We show how tail dependence of price changes, which may emerge as a result of differences in market design, can be exploited to estimate unique information shares. Two empiricalapplications illustrate the practical use of the new methodology.

A New Marked Point Process Model for the Federal Funds Rate Target Methodology and Forecast Evaluation

Forecasts of key interest rates set by central banks are of paramount concern for investors and policy makers. Recently it has been shown that forecasts of the federal funds rate target, the most anticipated indicator of the Federal Reserve Banks monetary policy stance, can be improved considerably when its evolution is modeled as a marked point process (MPP). This is due to the fact that target changes occur in discrete time with discrete increments, have an autoregressive nature and are usually in the same direction. We propose a model which is able to account for these dynamic features of the data. In particular, we combine Hamilton and Jordas [2002. A model for the federal funds rate target. Journal of Political Economy 110(5), 1135-1167] autoregressive conditional hazard (ACH) and Russell and Engles [2005. A discrete-state continuous-time model of financial transactions prices and times: the autoregressive conditional multinomial-autoregressive conditional duration model. Journal of Business and Economic Statistics 23(2), 166 - 180] autoregressive conditional multinomial (ACM) model. The paper also puts forth a methodology to evaluate probability function forecasts of MPP models. By improving goodness of fit and point forecasts of the target, the ACH-ACM qualifies as a sensible modeling framework. Furthermore, our results show that MPP models deliver useful probability function forecasts at short and medium term horizons.

Creative Destruction and Asset Prices

We relate Schumpeters notion of creative destruction to asset pricing, thereby offering a novel explanation of size and value premia. We argue that small-value firms are more likely to be destroyed by serendipitous invention activity, and investors demand higher expected returns for bearing that risk. Large-growth stocks provide protection against creative destruction, so they receive expected return discounts. An ICAPM that accounts for creative destruction risk explains a considerable part of the cross-sectional return variation of size- and book-to-market-sorted portfolios. The estimated risk compensations associated with creative destruction are economically and statistically significant.

Give me strong moments and time - Combining GMM and SMM to estimate long-run risk asset pricing models

The long-run consumption risk (LRR) model is a convincing approach towards resolving prominent asset pricing puzzles. Whilst the simulated method of moments (SMM) provides a natural framework to estimate its deep parameters, caveats concern model solubility and weak identification. We propose a two-step estimation strategy that combines GMM and SMM, and for which we elicit informative moment matches from the LRR model structure. In particular, we exploit the persistent serial correlation of consumption and the equilibrium conditions for market return and risk-free rate, as well as the model-implied predictability of the risk-free rate. We match analytical moments when possible and simulated moments when necessary and determine the crucial factors that are required for identification and reasonable estimation precision. By means of a simulation study---the first in the context of long-run risk modeling---we delineate the pitfalls associated with SMM estimation of LRR models, and we present a blueprint for successful estimation.

A Comparative Empirical Analysis of Labour Supply and Wages of Married Women in the FRG and the USA

The object ive of this paper is to compare the effects o f individual and household characteristics and regional and industry-specific labour market indicators on individual wage rates and labour supply in the USA and the F R G . T h e main goal o f our empirical work is to provide a comparat ive microeconometr ic study where sample selection process, estimation procedure and identifying restrictions do not differ between both countries. M r o z ( 1 9 8 7 ) showed that estimation results o f labour supply models are rather sensitive to varying statistical assumptions and empirical specifications. T h e significant differences o f estimated labour supply parameters (see e.g. the survey o f Laisney et al., 1 9 9 2 a ) reflect this. Hence, our study offers the chance o f an inter-country comparison of labour supply parameters that is largely free of such effects. Tradit ional labour supply models do not explicitly take into account industryspecific or regional labour market conditions. T h e way we include regional and sectoral unemployment indicators in our empirical model is similar to the method suggested by H a m ( 1 9 8 6 ) . Because labour market conditions can influence labour supply indirectly

A Two-Step Indirect Inference Approach to Estimate the Long-Run Risk Asset Pricing Model

The long-run consumption risk model provides a theoretically appealing explanation for prominent asset pricing puzzles, but its intricate structure presents a challenge for econometric analysis. This paper proposes a two-step indirect inference approach that disentangles the estimation of the models macroeconomic dynamics and the investors preference parameters. A Monte Carlo study explores the feasibility and efficiency of the estimation strategy. We apply the method to recent U.S. data and provide a critical re-assessment of the long-run risk models ability to reconcile the real economy and financial markets. This two-step indirect inference approach is potentially useful for the econometric analysis of other prominent consumption-based asset pricing models that are equally difficult to estimate.