Article

The Summary Informativeness of Stock Trades: An Econometric Analysis

Authors:
To read the full-text of this research, you can request a copy directly from the author.

Abstract

In a security market with asymmetrically informed participants, trades are signals of private information. In this article, new measures of trade informativeness are proposed based on a decomposition of the variance of changes in the efficient price into trade-correlated and -uncorrelated components. The trade-correlated component has a natural interpretation as an absolute measure of trade informativeness. The ratio of this component to the total variance is a relative measure (i.e., a proportion normalized with respect to the total public information). For a sample of NYSE-listed companies, trades are found to be more informative for small firms in both absolute and relative senses. From an analysis of intraday patterns, it appears that trades are in absolute terms more informative at the beginning of trading, but slightly less informative in relative terms.

No full-text available

Request Full-text Paper PDF

To read the full-text of this research,
you can request a copy directly from the author.

... for example, in Hasbrouck's seminal paper [19], defines p t−1 as the midprice just after the trade v t−1 . The price then evolves due to limit order depositions and cancellations until another trade occurs at time t, and immediately after the midprice is p t . ...
... We consider first a linear specification of the general model of Eq. (1). This model is essentially 2 the SVAR model proposed by Hasbrouck in [19] and defined by ...
... Although the solution holds for any β and λ, as discussed above, condition (19) must be satisfied to ensure that volumes remain stationary. ...
Preprint
Estimating market impact and transaction costs of large trades (metaorders) is a very important topic in finance. However, using models of price and trade based on public market data provide average price trajectories which are qualitatively different from what is observed during real metaorder executions: the price increases linearly, rather than in a concave way, during the execution and the amount of reversion after its end is very limited. We claim that this is a generic phenomenon due to the fact that even sophisticated statistical models are unable to correctly describe the origin of the autocorrelation of the order flow. We propose a modified Transient Impact Model which provides more realistic trajectories by assuming that only a fraction of the metaorder trading triggers market order flow. Interestingly, in our model there is a critical condition on the kernels of the price and order flow equations in which market impact becomes permanent.
... Most microstructure models based on information are divided into three main parts. The first section includes models that study the price effect of information (Hasbrouck, 1991a(Hasbrouck, , 1991bMadhavan & Smidt, 1991). The second group of models used certain criteria such as the bid-ask spread price (Bagehot, 1971;Jaffe & Winkler, 1976;McInish & Wood, 1992), the volume and size of the deal (Keim & Madhavan, 1995, firm size (Hasbrouck, 1991b), number of transactions (Jones, Kaul, & Lipson, 1994) and ratio of insiders (Jones et al., 1994). ...
... The first section includes models that study the price effect of information (Hasbrouck, 1991a(Hasbrouck, , 1991bMadhavan & Smidt, 1991). The second group of models used certain criteria such as the bid-ask spread price (Bagehot, 1971;Jaffe & Winkler, 1976;McInish & Wood, 1992), the volume and size of the deal (Keim & Madhavan, 1995, firm size (Hasbrouck, 1991b), number of transactions (Jones, Kaul, & Lipson, 1994) and ratio of insiders (Jones et al., 1994). The third generation provides sequential trading models that describe the trading process and estimate the probability of informed trading. ...
... This process repeats for = 1, 2, this updating procedure could be expressed in general forms since all probabilities in the event trees are constant except (0). In this model, the economic interpretation for equation (31) is that the gain from an uninformed trader on the left side is equal to the loss to the informed trader on the right side (subject to zero profit expectation for the market maker). There is net wealth transfer from the uninformed to the informed. ...
Article
Full-text available
In recent decades, the development of capital market microstructure theory has led to a broad understanding of market performance, market organizational structure, transaction costs, and asset prices. Certainly one of the most important goals of microstructure modeling is to understand and describe the quality of markets. Define market microstructure as the process by which investors' latent demands are ultimately translated into prices and volumes. Define market microstructure as the study of trading mechanisms and regulations used to accomplish a trade. definition of market microstructure which is the study of the intermediation and the institutions of exchange. The main purpose of this article is to review the most important microstructure models of the market. Defines market microstructure as the study of the process and outcomes of exchanging assets under explicit trading rules. The main body of market microstructure theory consists of inventory-based models and information-based models. This article focuses on information-based models. Studying open microstructure models can help market participants understand the pricing process and the impact of information on pricing. The study of market microstructure theory and models leads to a deep understanding of the performance and organizational structure of the market, transaction costs, asset prices, and an understanding and description of market quality.
... These trades, in and of themselves, could permanently impact the security price. Hasbrouck (1991) proposes a measure of trade informativeness in a market with asymmetrically informed participants intended to assess the impact of trade innovations on efficient price processes. The efficient price is the expected end-of-trading security value conditional on all public information n and assumed to evolve as a random walk. ...
... Because trading conveys information and has a permanent impact on security prices, Hasbrouck's (1991) uses trade variables to estimate trade informativeness. As an extension of Hasbrouck's (1991) trade informativeness measurement, we estimate basis informativeness to test our hypothesis that the S&P 500 index basis conveys information for price revisions in the SPDRs. ...
... Because trading conveys information and has a permanent impact on security prices, Hasbrouck's (1991) uses trade variables to estimate trade informativeness. As an extension of Hasbrouck's (1991) trade informativeness measurement, we estimate basis informativeness to test our hypothesis that the S&P 500 index basis conveys information for price revisions in the SPDRs. Our vector moving average (VMA) models are specified as follows: = 0 * 1, + 1 * 1, −1 + 2 * 1, −2 + ⋯ + 0 * 2, + 1 * 2, −1 + ⋯ = 0 * 1, + 1 * 1, −1 + 2 * 1, −2 + ⋯ + 0 * 2, + 1 * 2, −1 + ⋯ ...
Article
This study examines the relationship between firm size and an employee’s level of job embeddedness. A quantitative survey design was used to gather evidence from full-time accounting professionals working in public accounting firms across the United States. With a sample size of 136 full-time employees, results suggest that there is a positive relationship between firm size and job embeddedness. Two different measures of firm size were analyzed in the study. First, the number of full-time employees in the office was regressed on job embeddedness. Results indicated that the relationship was positive and significant. Second, the number of offices was used to measure firm size. The mean difference was calculated for job embeddedness and each of its six dimensions for firms with only one office, and those means were compared to the means of firms with two or more offices. Results indicated a positive relationship between job embeddedness and firm size; however, only the difference of means for the community fit dimension of job embeddedness was significant.
... An alternative approach for studying the interdependence between durations and other microstructure variables is provided by Hasbrouck (1991). He applied the vector autoregressive (VAR) system to analyzes the impact of current execution prices on the future prices and presented a bivariate model for the relation between price changes and trade dynamics such as the sign of price movement. ...
... in (33) depends on past information of , which is ( | ̅ , ̅ −1 ; , ) = ( | ̅ −1 ; , ). (2000) extended the model of Hasbrouck (1991) to account for the influence of durations on the price dynamics. They first applied an ACD model to describe the duration dynamics. ...
Preprint
Full-text available
This paper explores the duration dynamics modelling under the Autoregressive Conditional Durations (ACD) framework (Engle and Russell 1998). I test different distributions assumptions for the durations. The empirical results suggest unconditional durations approach the Gamma distributions. Moreover, compared with exponential distributions and Weibull distributions, the ACD model with Gamma distributed innovations provide the best fit of SPY durations.
... markets, assets can be traded without causing significant price changes, which can lower the risk of price manipulation and volatility. Hasbrouck (1991) and Chordia, Roll, and Subrahmanyam (2001) find that trading volume has a positive relationship with market liquidity and can reduce price volatility in normal market conditions. They added that Liquidity plummets significantly in down markets. ...
Article
Full-text available
Understanding the relationship between volume and stock returns is a central question in financial research. Volume is often considered as an essential indicator of market sentiment, liquidity, and the flow of information, and its impact on asset prices has been widely studied. However, the effect of volume on returns might be subject to shifts during different market conditions, especially during periods of financial distress such as the 2008 global financial crisis. We explore whether high trading volume affects returns differently before and after the crisis, with a focus on the S&P 500 index over the past 34 years. The results suggest a negative relationship between high volume and returns, with a pronounced effect only observed after the 2008 financial crisis. More interestingly, the effect has diminished after Covid-19 pandemic, reinforcing the complex nature of market interactions in general and the role of volume on trading returns in particular.
... To this extent, we follow [41] to examine the effects of ten key events around the EVFTA on the Vietnam stock market. Prior empirical studies document that news events influence stock prices ( [43][44][45][46][47]), and good news tends to result in positive abnormal returns, and bad news leads to negative abnormal returns [44]. However, [48,49] also point out that the events do not affect all sectors. ...
Article
Full-text available
This study examines the effects of news events related to the European Union-Vietnam Free Trade Agreement (EVFTA) on the Vietnam stock market from 2010 to 2020. We calculate sectoral abnormal returns prior to, during, and after announcements and find that the Vietnamese stock market is susceptible to these events. We discovered that the announcement had a negative impact on the market, which might diminish the effectiveness of the Agreement. The findings show that more than half of Vietnam’s sectors had an immediate reaction to EVFTA announcements, with fourteen reacting negatively and six responding positively. Two of the ten events did not have any immediate impact on these industries but all events resulted in either early or delayed reactions. We also find market scepticism and major changes in the deal led to the emergence of a diamond risk structure. We run multiple robustness tests to account for market integration and other factors that may affect stock returns. In addition, we explore potential sectoral systematic risk changes following these occurrences using different ARCH-type models. These additional tests confirm the robustness of our findings.
... This transformation is discussed in the appendix of Hasbrouck (1991) in detail. The moving average coefficients are obtained by stepping the system forward in response to a unit innovation as described in Hasbrouck (1992) and Hamilton (1994). ...
Article
Full-text available
This paper studies the impact of Standard & Poor's Depositary Receipts (SPDRs) on the market quality of the S&P 500 index futures contracts. SPDRs began trading on the American Stock Exchange just like shares of a stock on January 29, 1993. They are designed to track the performance of the S&P 500 index. The availability of such a security that tracks the movement of a stock index has implications for the price discovery or market quality of the other index securities in the S&P 500 index markets. This study implements Hasbrouck's (1993) Vector Autoregression (VAR) methodology to estimate market quality, or in other words, the precision of the price discovery, by employing transaction data for the S&P 500 index futures over the 200 days before and 200 days after the introduction of SPDRs. The empirical results show that the quality of S&P 500 index futures market improves, that is, the price discovery becomes more precise in the post-SPDRs period.
... Therefore, the \better than average" e®ect should be investigated in the NBA context and will be inserted into our research model. Regarding the miscalibration of one's own abilities,¯nancial literature suggests these abilities should be considered as subjective knowledge [Dorn and Huberman (2005)], as knowledge advantage represents a decisive factor in¯nancial markets [Hasbrouck (1991)]. Since this understanding strongly aligns with the de¯nition of facilitating conditions in the UTAUT2, we adopt subjective investment knowledge into our research model, representing the facilitating conditions. ...
Article
Full-text available
Disruptive neo-broker applications (NBAs) enable users to access financial markets easily and have attracted millions of investors worldwide. As a gamified implementation for financial services, NBAs provide a unique research setting in which to examine the determinants of NBA acceptance among investors, some of whom are wholly inexperienced in financial products. We propose a research model specifically designed to explain the usage intention of NBAs by drawing on established factors from technology acceptance and financial behavior research. We validated the research model empirically with structural equation modeling (N = 653) and found significant drivers of NBA acceptance. Distinct from previous finance technologies, we confirmed consumption-oriented factors, including performance expectancy, hedonic motivation, price value, and habit as antecedents of NBA usage intention. From the financial perspective, initial trust and overconfidence were identified as further drivers, while overconfidence in turn is shaped by risk aversion and subjective financial knowledge, indicating a mediated effect on NBA acceptance. Thereby, we present the first NBA-tailored acceptance model that links technology characteristics and financial behavior. Correspondingly, we provide implications for theory and practice.
... It is important to notice, also to better understand our contribution below, that the Hasbrouck's model is linear and with constant parameters, thus impacts and information content are constant and do not depend on time or on market conditions. Hasbrouck's findings show that trades convey substantial information (Hasbrouck (1988)) that causes a persistent impact on prices (Hasbrouck (1991b)). The analysis shows that the long-run impact arrives only with protracted lags and varies across securities (Hasbrouck (1991a)). ...
Preprint
The estimation of market impact is crucial for measuring the information content of trades and for transaction cost analysis. Hasbrouck's (1991) seminal paper proposed a Structural-VAR (S-VAR) to jointly model mid-quote changes and trade signs. Recent literature has highlighted some pitfalls of this approach: S-VAR models can be misspecified when the impact function has a non-linear relationship with the trade sign, and they lack parsimony when they are designed to capture the long memory of the order flow. Finally, the instantaneous impact of a trade is constant, while market liquidity highly fluctuates in time. This paper fixes these limitations by extending Hasbrouck's approach in several directions. We consider a nonlinear model where we use a parsimonious parametrization allowing to consider hundreds of past lags. Moreover we adopt an observation driven approach to model the time-varying impact parameter, which adapts to market information flow and can be easily estimated from market data. As a consequence of the non-linear specification of the dynamics, the trade information content is conditional both on the local level of liquidity, as modeled by the dynamic instantaneous impact coefficient, and on the state of the market. By analyzing NASDAQ data, we find that impact follows a clear intra-day pattern and quickly reacts to pre-scheduled announcements, such as those released by the FOMC. We show that this fact has relevant consequences for transaction cost analysis by deriving an expression for the permanent impact from the model parameters and connecting it with the standard regression procedure. Monte Carlo simulations and empirical analyses support the reliability of our approach, which exploits the complete information of tick-by-tick prices and trade signs without the need for aggregation on a macroscopic time scale.
... The literature on measuring price discovery starts with a series of papers by Hasbrouck (1991aHasbrouck ( , 1991bHasbrouck ( , 1993. These studies estimate the random-walk component of stock returns, which is interpreted as changes of the latent efficient price. ...
Article
When an asset is traded in multiple markets, the vector error‐correction model of Hasbrouck (1995, 2021) impliesthat information is priced sequentially across markets, thus underestimating price innovations in slower markets. This study introduces a common information component across markets and mitigates the speed‐induced bias. At intervals from 0.01 to 2 seconds, the common information shares are 66 ‐ 94% between the listing and other exchanges, and 60 ‐ 90% between quotes and trades. The presence of common information alters the ranking of market‐specific information shares. As trading speed increases, the common information shares have increased over time.
... Studies such asKeim (1989),Hasbrouck (1991);Conrad et al (1997) and others pointed out the relationship between the microstructure issues and negative serial autocorrelation between stock returns. ...
Article
Market microstructure invariance (MMI) stipulates that trading costs of financial assets are driven by the volume and volatility of bets, but these variables are inherently difficult to identify. With futures transactions data, we estimate bet volume as the trading volume of brokerage firms that trade on behalf of their clients and bet volatility as the trade-related component of futures volatility. We find that the futures bid–ask spread lines up with bet volume and bet volatility as predicted by MMI, and that intermediation by high-frequency traders does not interfere with the MMI relation.
Article
A key issue for decentralised markets like FX is how the market responds to extreme situations. Using data on FX transactions with a precise identification of Algorithmic trading (AT), we find that AT, broadly defined, appears to have contributed to the deterioration of market quality following the removal of the cap on the Swiss franc on 15 January 2015 by withdrawing liquidity and generating uninformative volatility. We also find that the Swiss National Bank, after initially stepping aside, played an important role, though more by signalling rather than trading. This perhaps explains why human trading – that could most easily interpret those signals – was important in stabilising the market.
Article
We examine whether heterogeneous beliefs among investors affect post‐announcement informed trading. Using a global transaction‐level dataset, we find that post‐announcement informed trading increases with heterogeneous beliefs developed at the event window. Such an inference survives from several robustness checks. As additional analyses indicate, shrinking liquidity at the earnings announcement serves as a transmission mechanism to rationalize the documented association. Eventually, we reveal that informed trading driven by belief heterogeneity plays a dominant role in explaining post‐announcement returns.
Article
The Korea Composite Stock Price Index (KOSPI) 200 futures market is one of the largest and most liquid index derivatives markets globally. We utilize high-quality intraday data on KOSPI 200 futures and find that high-frequency traders’ (HFTs’) market orders contribute much more to price discovery than their limit orders, as opposed to the findings of Brogaard, Hendershott, and Riordan (2019) in the Canadian equity market. To explain this phenomenon, we suggest that HFTs in the KOSPI 200 futures market are more speculative traders rather than market makers, which makes market orders more informative.
Article
Our study investigates traders' order submission strategies with varying market conditions under information asymmetry. It examines how a reduction in tick size affects informed traders' order choices in response to changes in market conditions and subsequently influences the information content of the limit order book on the Tokyo Stock Exchange. We quantify the permanent price impact of orders with different levels of aggressiveness to measure the information content of different kinds of orders before and after a reduction in tick size. The results show that market orders and limit orders placed within or at the best bid and offer (BBO) are more informative than limit orders placed behind the BBO. Moreover, when the quoted spread is wider (narrower) and volatility is low (high), the information content of limit orders placed within or at the BBO is larger (smaller) than market orders, providing evidence that informed traders' order choice on market orders or limit orders is a trade-off between transaction costs and adverse selection costs. We further observe that the information content increases in market orders but decreases in limit orders placed within or at the BBO when the quoted spread becomes narrower and volatility changes from low to high after tick size reduction. This suggests that informed traders tend to shift from limit orders to market orders as transaction costs decrease and adverse selection costs increase, transactions become more informative, which reduces the information content of the limit order book.
Article
We develop a new methodology to estimate the impact of a financial transaction tax (FTT) on financial market outcomes. In our sequential trading model, there are price-elastic noise and informed traders. We estimate the model through maximum likelihood for a sample of 60 NYSE stocks in 2017. We quantify the effect of introducing an FTT given the parameter estimates. An FTT increases the proportion of informed trading, improves information aggregation, but lowers trading volume and welfare. For some less liquid stocks, however, an FTT blocks private information aggregation.
Article
The US Federal Reserve doubled its balance sheet during the COVID-19 pandemic in the most aggressive unconventional monetary policy on record. I show that the scale and scope of these actions substantially impacted stock markets, explaining at least one-third of their rebound. The impact occurs predominantly through bond yields (discount rates) and expectations of future macroeconomic conditions (future cash flows). I find while the Fed’s balance sheet expansions are more rapid than its contractions, the stock market is more sensitive to contractions. The findings have implications for possible impacts of central banks unwinding the positions accumulated during the pandemic.
Article
We study the extent to which private information is revealed through trades in the foreign exchange market. The trade informativeness measured from the VAR framework of trades and quotes allows us to quantify the impact of asymmetric information on return variation. We find the intraday variation in the proportion of permanent price variation driven by trade-related information has a repetitive periodic pattern, and trades in the overlapping trading hours of London and New York carry most information than the other time segments. The results show the fraction of trade-related component to exchange rate variation positively relates to trading volume and reversely relates to effective spread. With a comprehensive set of 48 real-time US, European, and Japanese macroeconomic news surprises variables, and controlling for the effect of trading volume, spread, and volatility, we find news of production-related economic indicator, e.g., GDP and industrial production, has a positive relationship with the trade informativeness in a trading period, suggesting the increased private information share may be attributed to heterogeneous interpretations of the announcement among market participants. Announcement-related information is gradually resolved into the price, and the information is transited via the channel of trading activities.
Article
Using intraday data, we document statistically strong, but temporary, impacts of commodity index trade flows on commodity futures prices. We also examine the previously documented positive returns around the issuance of commodity-linked notes and find that these returns are an order of magnitude too large to be caused by the small trades necessary to hedge the notes. We provide new evidence that they are instead the result of endogenous issuance. Our results provide novel support for commodity financialization but highlight the importance of measuring the magnitude of financial investment, since even large financial flows have economically modest impacts on prices.
Article
We develop a return variance decomposition model to distinguish the roles of different types of information and noise in stock price movements. We disentangle four components: noise, private firm-specific information revealed through trading, firm-specific information revealed through public sources and market-wide information. Overall, we find that 31%\% of the return variance is from noise, 24%\% from private firm-specific information, 37%\% from public firm-specific information and 8%\% from market-wide information. Since the mid-1990s, there has been a dramatic decline in noise and an increase in firm-specific information, consistent with increasing market efficiency. The Internet Appendix that accompanies this paper can be obtained here: https://bit.ly/3FcV9UR
Preprint
Full-text available
This paper proposes a multiplicative component intraday volatility model. The intraday conditional volatility is expressed as the product of intraday periodic component, intraday stochastic volatility component and daily conditional volatility component. I extend the multiplicative component intraday volatility model of Engle (2012) and Andersen and Bollerslev (1998) by incorporating the durations between consecutive transactions. The model can be applied to both regularly and irregularly spaced returns. I also provide a nonparametric estimation technique of the intraday volatility periodicity. The empirical results suggest the model can successfully capture the interdependency of intraday returns.
Chapter
… sometimes time flows very rapidly in financial markets while in other periods it moves slowly…
Article
Full-text available
We use stock exchange message data to quantify the negative aspect of high-frequency trading, known as “latency arbitrage.” The key difference between message data and widely familiar limit order book data is that message data contain attempts to trade or cancel that fail. This allows the researcher to observe both winners and losers in a race, whereas in limit order book data you cannot see the losers, so you cannot directly see the races. We find that latency arbitrage races are very frequent (about one per minute per symbol for FTSE 100 stocks), extremely fast (the modal race lasts 5–10 millionths of a second), and account for a remarkably large portion of overall trading volume (about 20%). Race participation is concentrated, with the top six firms accounting for over 80% of all race wins and losses. The average race is worth just a small amount (about half a price tick), but because of the large volumes the stakes add up. Our main estimates suggest that races constitute roughly one-third of price impact and the effective spread (key microstructure measures of the cost of liquidity), that latency arbitrage imposes a roughly 0.5 basis point tax on trading, that market designs that eliminate latency arbitrage would reduce the market’s cost of liquidity by 17%, and that the total sums at stake are on the order of $5 billion per year in global equity markets alone.
Article
Full-text available
This paper develops and tests a model of intraday security price movements which incorporates the effects of both trading volume and unanticipated information. We estimate our model using transaction data from a NYSE specialist and find strong evidence of information asymmetry, although the inventory effect appears weak. The parameter estimates are used to compute the costs of trading, and we find that implicit bid-ask spreads were significantly higher in October 1987 than in the rest of that year. We also examine large-block versus smaller trades and buyer-initiated versus seller-initiated trades.
Article
Full-text available
In an adverse selection model of a securities market with one informed trader and several liquidity traders, we study the implications of the assumption that the informed trader has more information on Monday than on other days. We examine the interday variations in volume, variance, and adverse selection costs, and find that on monday the trading costs and the variance of price changes are highest, and the volume is lower than on Tuesday. These effects are stronger for firms with better public reporting and for firms with more discretionary liquidity trading.
Article
SAMPLING THEORY AND BAYESIAN APPROACHES TO INFERENCE. The Classical Inference Approach for the General Linear Model. Statistical Decision Theory and Biased Estimation. The Bayesian Approach to Inference. INFERENCE IN GENERAL STATISTICAL MODELS AND TIME SERIES. Some Asymptotic Theory and Other General Results for the Linear Statistical Model. Nonlinear Statistical Models. Time Series. DYNAMIC SPECIFICATIONS. Autocorrelation. Finite Distributed Lags. Infinite Distributed Lags. SOME ALTERNATIVE COVARIANCE STRUCTURES. Heteroskedasticity. Disturbance--Related Sets of Regression Equations. Inference in Models that Combine Time Series and Cross--Sectional Data. INFERENCE IN SIMULTANEOUS EQUATION MODELS. Specification and Identification in Simultaneous Equation Models. Estimation and Inference in a System of Simultaneous Equations. Multiple Time Series and Systems of Dynamic Simultaneous Equations. FURTHER MODEL EXTENSIONS. Unobservable Variables. Qualitative and Limited Dependent Variable Models. Varying and Random Coefficient Models. Non--Normal Disturbances. On Selecting the Set of Aggressors. Multicollinearity. Appendices.
Article
This article develops a theory in which concentrated-trading patterns arise endogenously as a result of the strategic behavior of liquidity traders and informed traders. Our results provide a partial explanation for some of the recent empirical findings concerning the patterns of volume and price variability in intraday transaction data.
Article
This paper investigates the effect of trade size on security prices. We show that trade size introduces an adverse selection problem into security trading because, given that they wish to trade, informed traders perfer to trade larger amounts at any given price. As a result, market makers' pricing strategies must also depend on trade size, with large trades being made at less favorable prices. Our model provides one explanation for the price effect of block trades and demonstrates that both the size and the sequence of trades matter in determining the price-trade size relationship.
Article
This is an invited expository article for The American Statistician. It reviews the nonparametric estimation of statistical error, mainly the bias and standard error of an estimator, or the error rate of a prediction rule. The presentation is written at a relaxed mathematical level, omitting most proofs, regularity conditions, and technical details.
Article
This paper discusses detrending economic time series, when the trend is modelled as a stochastic process. It considers unobserved components models in which the observed series is decomposed into a trend (a random walk with drift) and a residual stationary component. Optimal detrending methods are discussed, as well as problems associated with using these detrended data in regression models. The methods are applied to three time series: GNP, disposable income, and consumption expenditures. The detrended data are used to test a version of the Life Cycle consumption model.
Article
The presence of traders with superior information leads to a positive bid-ask spread even when the specialist is risk-neutral and makes zero expected profits. The resulting transaction prices convey information, and the expectation of the average spread squared times volume is bounded by a number that is independent of insider activity. The serial correlation of transaction price differences is a function of the proportion of the spread due to adverse selection. A bid-ask spread implies a divergence between observed returns and realizable returns. Observed returns are approximately realizable returns plus what the uninformed anticipate losing to the insiders.
Article
This paper introduces a general procedure for decomposition of non-stationary time series into a permanent and transitory component allowing both components to be stochastic. The permanent component is shown to be a random walk with drift and the transitory or cyclical component is a stationary process with mean zero. The decomposition methodology, which depends only on past data and therefore is computable in ‘real time’, is applied to the problem of measuring and dating business ‘cycles’ in the portwar U.S. economy. We find that measured expansions and contractions are of roughly equivalent duration and that our dating of cyclical episodes tends to lead the traditional NBER dating and, to a lesser extent, the ‘growth cycle’ chronology of Zarnowitz and Boschan (1977).
Article
This empirical examination of the relation between trades and quote revisions for New York Stock Exchange-listed stocks is designed to ascertain asymmetric-information and inventory-control effects. This study finds that negative autocorrelation in trades consistent with inventory-control behavior characterizes low-volume stocks, but not high-volume stocks. The evidence of inventory control in the impact of trades on quote revisions is inconclusive. The information content of trades, on the other hand, is found to be substantial. There is also strong evidence that large trades convey more information than small trades.
Article
Trading on private information creates inefficiencies because there is less than optimal risk sharing. This occurs because the response of marketmakers to the existence of traders with private information is to reduce the liquidity of the market. The institution of the monopolist specialist may ease this inefficiency somewhat by increasing the liquidity of the market. While competing marketmakers will expect a zero profit on every trade, the monopolist will average his profits across trades. This implies a more liquid market when there is extensive trading on private information. Copyright 1989 by the University of Chicago.
Article
We develop and test a model of intraday price formation based on an explicit description of a representative market maker whose beliefs evolve according to Bayes’ rule. We derive an estimating equation where the weight the market maker places on the order flow as an information signal can be recovered from the parameter estimates. This weight is a natural measure of information asymmetry since it is the ratio of the quality of private information to the quality of public information. The model is interesting for other reasons as well. First, the model encompasses several other models of intraday price formation. Second, the error term arises endogenously and possesses a natural economic interpretation. Third, the model permits us to partially distinguish the price effects of information asymmetry and inventory control by market makers. Fourth, the model provides a method to assess the implicit costs of trading. We show that there are substantial non-linearities in pricing that may reflect the way in which large blocks are traded in the upstairs market. We estimate the model with a new data set obtained from a NYSE specialist. The data set comprises almost 75,000 records for most of the year 1987 and is o independent interest given the paucity of inventory data. The results provide strong support of information asymmetries, as perceived by the market.
Article
The relation between the square of the quoted bid-ask spread and two serial covariances--the serial covariance of transaction returns and the serial covariance of quoted returns--is modeled as a function of the probability of a price reversal, pi, and the magnitude of a price change, delta, where delta is stated as a function of the quoted spread. Different models of the spread are contrasted in term of the parameters, pi and delta. Using data on transaction prices and price quotations for NASDAQ/NMS stocks, pi and delta are estimated and the relative importance of the components of the quoted spread--adverse information costs, order processing costs, and inventory holding costs--is determined. Copyright 1989 by American Finance Association.
Article
This paper develops and implements a technique for estimating a model of the bid/ask spread. The spread is decomposed into two components, one due to asymmetric information and one due to inventory costs, specialist monopoly power, and clearing costs. The model is estimated using NYSE common stock transaction prices in the period 1981–1983. Cross-sectional regression analysis is then used to relate time-series estimated spread components to other stock characteristics. The results cannot reject the hypothesis that significant amounts of NYSE common stock spreads are due to asymmetric information.
Article
The dangers of shouting ``fire'' in a crowded theater are well understood, but the dangers of rushing to the exit in the financial markets are more complex. Yet, the two events share several features, and I analyze why people crowd into theaters and trades, why they run, what determines the risk, whether to return to the theater or trade when the dust settles, and how much to pay for assets (or tickets) in light of this risk. These theoretical considerations shed light on the recent global liquidity crisis and, in particular, the quant event of 2007.
Article
The behavior of time-weighted bid-ask spreads over the trading day are examined. The plot of minute-by-minute spreads versus time of day has a crude reverse J-shaped pattern. Schwartz identifies four determinants of spreads: activity, risk, information, and competition. Using a linear regression model, a significant relationship between these same factors and intraday spreads is demonstrated, but dummy variables for time of day have a reverse J-shape. For given values of the activity, risk, information, and competition measures, spreads are higher at the beginning and end of the day relative to the interior period. Copyright 1992 by American Finance Association.
Article
This paper evaluates alternative methods for classifying individual trades as market buy or market sell orders using intraday trade and quote data. The authors document two potential problems with quote-based methods of trade classification: quotes may be recorded ahead of trades that triggered them, and trades inside the spread are not readily classifiable. These problems are analyzed in the context of the interaction between exchange floor agents. The authors then propose and test relatively simple procedures for improving trade classifications. Copyright 1991 by American Finance Association.
Article
Fluctuations in real GNP have traditionally been viewed as transitory deviations from a deterministic time trend. The purpose of this paper is to review some of the recent developments that have led to a new view of output fluctuations and then to provide some additional evidence. Using post-war quarterly data, it is hard to reject the view that real GNP is as persistent as a random walk with drift. We also consider the hypothesis that the recent finding of persistence are due to the failure to distinguish the business cycle from other fluctuations in real GNP. We use the measured unemployment rate to decompose output fluctuations. We find no evidence for the view that business cycle fluctuations are more quickly trend-reverting.
Article
A dynamic model of insider trading with sequential auctions, structured to resemble a sequential equilibrium, is used to examine the informational content of prices, the liquidity characteristics of a speculative market, and the value of private information to an insider. The model has three kinds of traders: a single risk neutral insider, random noise traders, and competitive risk neutral market makers. The insider makes positive profits by exploiting his monopoly power optimally in a dynamic context, where noise trading provides camouflage which conceals his trading from market makers. As the time interval between auctions goes to zero, a limiting model of continuous trading is obtained. In this equilibrium, prices follow Brownian motion, the depth of the market is constant over time, and all private information is incorporated into prices by the end of trading.
Article
This paper delineates the link between the existence of information, the timing of trades, and the stochastic process of prices. The authors show that time affects prices, with the time between trades affecting spreads. Because the absence of trades is correlated with volume, the authors' model predicts a testable relation between spreads and normal and unexpected volume, and demonstrates how volume affects the speed of price adjustment. Their model also demonstrates how the transaction price series will be a biased representation of the true price process, with the variance being both overstated and heteroskedastic. Copyright 1992 by American Finance Association.
Article
This paper suggests that the interactions of security trades and quote revisions be modeled as a vector autoregressive system. Within this framework, a trade's information effect may be meaningfully measured as the ultimate price impact of the trade innovation. Estimates for a sample of NYSE issues suggest a trade's full price impact arrives only with a protracted lag; the impact is a positive and concave function of the trade size; large trades cause the spread to widen; trades occurring in the face of wide spreads have larger price impacts; and information asymmetries are more significant for smaller firms. Copyright 1991 by American Finance Association.
Article
An individual who chooses to serve as a market‐maker is assumed to optimize his position by setting a bid‐ask spread which maximizes the difference between expected revenues received from liquidity‐motivated traders and expected losses to information‐motivated traders. By characterizing the cost of supplying quotes, as writing a put and a call option to an information‐motivated trader, it is shown that the bid‐ask spread is a positive function of the price level and return variance, a negative function of measures of market activity, depth, and continuity, and negatively correlated with the degree of competition. Thus, the theory of information effects on the bid‐ask spread proposed in this paper is consistent with the empirical literature.
Article
The bid-ask spread can be decomposed into two parts-one part due to asymmetric informat ion and the other part due to other factors such as monopoly power. T he part due to asymmetric information attenuates statistical biases i n mean return, variance, and serial covariance. Thus, using spread da ta to adjust for biases in return moments requires knowing not only t he spread but the composition of the spread. Furthermore, any spread estimation procedure using transaction prices must estimate two sprea d components. Copyright 1987 by American Finance Association.
Article
T he two most striking historical features of aggregate output are its sustained long run growth and its recurrent fluctuations around this growth path. Real per capita GNP, consumption and investment in the United States during the postwar era are plotted in Figure 1. Both growth and deviations from the growth trend-often referred to as "business cycles"-are apparent in each series. Over horizons of a few years, these shorter cyclical swings can be pronounced; for example, the 1953, 1957 and 1974 recessions are evident as substantial temporary declines in aggregate activity. These cyclical fluctuations are, however, dwarfed in magnitude by the secular expansion of output. But just as there are cyclical swings in output, so too are there variations in the growth trend: growth in GNP in the 1960s was much stronger than it was in the 1950s. Thus, changes in long run patterns of growth are an important feature of postwar aggregate economic activity. In this article we discuss the implications of changing trends in macroeconomic data from two perspectives. The first perspective is that of a macroeconomist reassessing the conventional dichotomy between growth and stabilization policies. As an empirical matter, does this dichotomy make sense for the postwar United States? What is the relative "importance" of changes in the trend and cyclical swings in explaining the quarterly movements in economic aggregates? We next adopt the perspective of an econometrician interpreting empirical evidence based on data that contain variable trends. The presence of variable trends in time series data can lead one to draw mistaken inferences using conventional econometric techniques. How can these techniques-or our interpretation of them-be modified to avoid these mistakes?
Applied Time Series Analysis of Economic Data, U.S. Department of Commerce, Bureau of the Census Macroeconomic TheoryVariable Trends in Economic Time SeriesInferring the Components of the Bid-Ask Spread: Theory and Empirical TestsUnivariate Detrending Methods with Stochastic Trends
  • P Newbold
  • T J Sargent
Newbold, P., 1983, “Model Checking in Time Series Analysis,” in Arnold Zellner (cd.). Applied Time Series Analysis of Economic Data, U.S. Department of Commerce, Bureau of the Census. pp. 133-149. Sargent, T. J., 1979, Macroeconomic Theory, Academic Press, New York. Stock, J. H., and M. W. Watson, 1988, ‘Variable Trends in Economic Time Series,” Journal of Economic Perspectives 2,147-174. Stoll, H. R., 1989, “Inferring the Components of the Bid-Ask Spread: Theory and Empirical Tests,” Journal of Finance, 44, 115-134. Watson, M. W., 1986, “Univariate Detrending Methods with Stochastic Trends,” Journal of Monetary Economics 18,49-75. 595
Model Checking in Time Series Analysis Applied Time Series Analysis of Economic Data
  • P Newbold
Newbold, P., 1983, " Model Checking in Time Series Analysis, " in Arnold Zellner (cd.). Applied Time Series Analysis of Economic Data, U.S. Department of Commerce, Bureau of the Census. pp. 133-149.
Variations in Volumes, Variances and Trading Costs,” working paper
  • D F Foster
  • S Viswanathan
A New Approach to the Decomposition of Economic Time Series into Permanent and Transitory Components with Particular Attention to the Measurements of the ‘Business Cycle
  • Nelson C Beveridge
Trading Costs of Target Firms and Corporate Takeovers,” working paper
  • D F Foster
  • S Viswanathan
An Analysis of Intraday Patterns in Bid/Ask Spreads for NYSE Stocks,” working paper
  • T Mclnish
  • R Wood
Applied Time Series Analysis of Economic Data
  • P Newbold