Intertrade Durations Research Articles

Scaling in the distribution of intertrade durations of Chinese stocks

The distribution of intertrade durations, defined as the waiting times between two consecutive transactions, is investigated based upon the limit order book data of 23 liquid Chinese stocks listed on the Shenzhen Stock Exchange in the whole year 2003. A scaling pattern is observed in the distributions of intertrade durations, where the empirical density functions of the normalized intertrade durations of all 23 stocks collapse onto a single curve. The scaling pattern is also observed in the intertrade duration distributions for filled and partially filled trades and in the conditional distributions. The ensemble distributions for all stocks are modeled by the Weibull and the Tsallis q -exponential distributions. Maximum likelihood estimation shows that the Weibull distribution outperforms the q -exponential for not-too-large intertrade durations which account for more than 98.5% of the data. Alternatively, nonlinear least-squares estimation selects the q -exponential as a better model, in which the optimization is conducted on the distance between empirical and theoretical values of the logarithmic probability densities. The distribution of intertrade durations is Weibull followed by a power-law tail with an asymptotic tail exponent close to 3.

Modeling a Multivariate Transaction Process

In this paper the dynamics of a joint transaction process are investigated. The transaction process is characterized by four marks: price changes, transaction volumes, bid–ask spreads and intertrade durations. Based on a copula approach, a model for their joint density is proposed, which avoids forcing a priori assumptions on the instantaneous causality relationships between the four variables as necessary in decomposition models, where the joint density is decomposed into its conditional and unconditional densities. The price change process is treated as a discrete process and specified with an integer count hurdle model and the transaction volumes, bid–ask spreads, and trade durations processes are modeled along the lines of fractionally integrated autoregressive conditional models, which are suited very well to capture the high persistency, empirically observed in these processes. The model is applied to three stocks traded at the New York Stock Exchange (NYSE) in May, 2001 and we investigate several market microstructure hypotheses in the empirical part of this paper.

Duration time‐series models with proportional hazard

Abstract. The analysis of liquidity in financial markets is generally performed by means of the dynamics of the observed intertrade durations (possibly weighted by price or volume). Various dynamic models for duration data have been considered in the literature, such as the Autoregressive Conditional Duration (ACD) model. These models are often excessively constrained, introducing, for example, a deterministic link between conditional expectation and variance in the case of the ACD model. Moreover, the stationarity properties and the patterns of the stationary distributions are often unknown. The aim of this article is to solve these difficulties by considering a duration time series satisfying the proportional hazard property. We describe in detail this class of dynamic models, discuss its various representations and provide the ergodicity conditions. The proportional hazard copula can be specified either parametrically, or nonparametrically. We discuss estimation methods in both contexts, and explain why they are efficient, that is, why they reach the parametric (respectively, nonparametric) efficiency bound.

Fitting the empirical distribution of intertrade durations

Based on the analysis of a tick-by-tick data set used in the previous work by one of the authors (DJIA stocks traded at NYSE in October 1999), in this paper, we reject the hypothesis that tails of the empirical intertrade distribution are described by a power law. We further argue that the Tsallis q-exponentials are a viable tool for fitting and describing the unconditional distribution of empirical intertrade durations and they compare well to the Weibull distribution.

Modelling a Multivariate Transaction Process

In this paper the dynamics of a joint transaction process is investigated. The transaction process is characterized by four marks: price changes, transaction volumes, bid-ask spreads and intertrade durations. Based on a copula approach a model for the joint density is proposed, which avoids forcing a priori assumptions on the instantaneous causality relationships between the four variables as necessary in decomposition models, where the joint density is decomposed into its conditional and unconditional densities. The price change process is treated as a discrete process and specified with an integer count hurdle model and the transaction volumes, bid-ask spreads and trade durations processes are modelled along the lines of fractionally integrated autoregressive conditional models, which are very well suited to capture the high persistency empirically observed in these processes. The model is applied to three stocks traded at the New York Stock Exchange (NSYE) in May, 2001 and we investigate several market microstructure hypothesis in the empirical part of this paper.

Duration Time-Series Models With Proportional Hazard

. The analysis of liquidity in financial markets is generally performed by means of the dynamics of the observed intertrade durations (possibly weighted by price or volume). Various dynamic models for duration data have been considered in the literature, such as the Autoregressive Conditional Duration (ACD) model. These models are often excessively constrained, introducing, for example, a deterministic link between conditional expectation and variance in the case of the ACD model. Moreover, the stationarity properties and the patterns of the stationary distributions are often unknown. The aim of this article is to solve these difficulties by considering a duration time series satisfying the proportional hazard property. We describe in detail this class of dynamic models, discuss its various representations and provide the ergodicity conditions. The proportional hazard copula can be specified either parametrically, or nonparametrically. We discuss estimation methods in both contexts, and explain why they are efficient, that is, why they reach the parametric (respectively, nonparametric) efficiency bound. (This abstract was borrowed from another version of this item.)

Trade intensity in the Russian stock market: dynamics, distribution and determinants

The distribution and evolution of intertrade durations for frequently traded stocks at the Moscow Interbank Currency Exchange are investigated. A flexible econometric model based on ARMA and GARCH is used which, when coupled with a certain class of distributions that allow for skewness and slim-tailedness, adequately captures the characteristics of conditional distribution of durations for Russian stocks, and is able to generate high quality density forecasts. What factors determine the dynamics of log-durations, and in which way, are also analyzed. The results in particular indicate that the Russian market is characterized by aggressive informed traders and timid liquidity traders, and that the participants react evenly to upward and downward short-run price trends.

Econometric Analysis of Intra-Daily Activity on Tokyo Stock Exchange

We analyze statistically inter-trade durations of four stocks listed on the Tokyo Stock Exchange in 2003. We find that these data display the usual stylized facts (intra-daily seasonality clustering and overdispersion) found for similar data of the New York Stock Exchange, but with some differences. We also estimate autoregressive conditional duration models for fitting the durations. We find that, like for comparable data of the NYSE, some models fit in a satisfactory way the dynamic properties of the durations, but do not always fit well the conditional distribution of the data.

Quantile estimation in ultra-high frequency financial data: a comparison between parametric and semiparametric approach

In the context of ACD models for ultra-high frequency data different specifications are available to estimate the conditional mean of intertrade durations, while quantiles estimation has been completely neglected by literature, even if to trading extent it can be more informative. The main problem arising with quantiles estimation is the correct specification of durations’ probability law: the usual assumption of Exponentially distributed residuals, is very robust for the estimation of parameters of the conditional mean, but dramatically fails the distributional fit. In this paper a semiparametric approach is formalized, and compared with the parametric one, deriving from Exponential assumption. Empirical evidence for a stock of Italian financial market strongly supports the former approach.

Stochastic volatility duration models

We propose a class of two factor dynamic models for duration data and related risk analysis in finance and insurance. Empirical findings suggest that the conditional mean and (under) overdispersion of times elapsed between stock trades feature various patterns of temporal dependence. Therefore durations seem to be driven jointly by movements of two underlying factors. The paper presents a new model, called the stochastic volatility duration (SVD) model for processes that involve time varying uncertainty and time related risk. SVD-based estimation of market activity allows for the presence or absence of temporal interactions between the factors, depending on the market organization and the traded stock. The paper presents the distributional properties of SVD, and compares its performance to the performance of ACD models in an empirical study of intertrade durations of the Alcatel stock. Several new diagnostic tools for risk analysis are proposed, such as the conditional overdispersion and Time at Risk.

Intertrade Duration and Information-Based Trading on an Electronic Order-Driven Market

Microstructure theories offered conflicting predictions regarding the relationship between trading intensity and information-based trading. In this paper, I make use of transaction-level data from the Chinese stock market to test the conflicting theories. I develop a high-frequency measure to capture the trading activities of informed traders. I show that trading based on good news is associated with increased trading intensity (or a shorter intertrade duration), whereas that based on bad news is associated with a longer duration. I also find that long durations are associated with declining prices and low volatility in the subsequent period. On balance, the findings are consistent with Diamond and Verrecchia (1987), where short sale constraints reduce the adjustment speed of stock prices to bad news.

Persistence in Intertrade Durations

This paper examines long memory in durations between trades of stocks on financial markets. The approach is based on semi-parametric methods as well as on the fractionally integrated autoregressive conditional duration model (FIACD). The persistence is also investigated in endogenously aggregated duration processes, representing times between consecutive returns to the states of null, positive or negative returns on stocks. This analysis captures the relationship between the duration persistence and stock return dynamics in varying market regimes. The paper also explores the sojourn times measuring durations of various states of stock returns.The long memory patterns are examined in data on the Alcatel and IBM stocks traded on the SBF Paris Bourse and NYSE.

On Some Limit Theorems Similar to the Arc-Sin Law

On Some Limit Theorems Similar to the Arc-Sin Law