Serial Correlation Of Returns Research Articles

Portfolio management of Commodity Trading Advisors with volatility-targeting

I show analytically that a volatility-targeted allocation methodology improves the risk-adjusted performance of portfolios under a broad set of assumptions regarding the serial correlation of returns, the variability of volatility and dependence of the expected Sharpe ratio on the level of volatility. I examine the impact of volatility targeting on portfolios of Commodity Trading Advisors within the large-scale simulation framework of Molyboga and L'Ahelec (2016) that accounts for the realistic constraints on institutional investors. I find a consistent and statistically significant improvement in the out-of-sample returns that ranges between 0.53% and 0.80% per annum, on average. The performance enhancement is robust to portfolio size and manager selection, and is implementable inside managed account investments.

Portfolio Management of Commodity Trading Advisors with Volatility Targeting

I show analytically that a volatility-targeted allocation methodology improves the risk-adjusted performance of portfolios under a broad set of assumptions regarding the serial correlation of returns, the variability of volatility and dependence of the expected Sharpe ratio on the level of volatility. I examine the impact of volatility targeting on portfolios of Commodity Trading Advisors within the large-scale simulation framework of Molyboga and L'Ahelec (2016) that accounts for the realistic constraints on institutional investors. I find a consistent and statistically significant improvement in the out-of-sample returns that ranges between 0.53% and 0.80% per annum, on average. The performance enhancement is robust to portfolio size and manager selection, and is implementable inside managed account investments.

Stop-loss strategies with serial correlation, regime switching, and transaction costs

Stop-loss strategies are commonly used by investors to reduce their holdings in risky assets if prices or total wealth breach certain pre-specified thresholds. We derive closed-form expressions for the impact of stop-loss strategies on asset returns that are serially correlated, regime switching, and subject to transaction costs. When applied to a large sample of individual U.S. stocks, we show that tight stop-loss strategies tend to underperform the buy-and-hold policy in a mean-variance framework due to excessive trading costs. Outperformance is possible for stocks with sufficiently high serial correlation in returns. Certain strategies succeed at reducing downside risk, but not substantially.

Dark Pool Exclusivity Matters

Recent dark pool proliferation has magnified regulatory and academic concerns about equal access and market quality implications. Some dark pools, hoping to create an environment more amenable to buy-side institutional investors, craft their rules to discourage – or even exclude – brokers, high frequency traders and order-flow-information traders. We examine the role participation constraints play in large trade execution and find that a dark pool targeting buy-side counterparties experiences less serial correlation in returns, less volume and volatility increase pre-trade, and more trade clustering within and across days. Exclusivity influences execution quality. Not all dark pools are created equal.

Repeat‐Sales Indexes: Estimation without Assuming that Errors in Asset Returns Are Independently Distributed

This article proposes an alternative specification for the second stage of the Case‐Shiller repeat‐sales method. This specification is based on serial correlation in the deviations from the mean one‐period returns on the underlying individual assets, whereas the original Case‐Shiller method assumes that the deviations from mean returns by the underlying individual assets are i.i.d. The methodology proposed in this article is easy to implement and provides more accurate estimates of the standard errors of returns under serial correlation. The repeat‐sales methodology is generally used to construct an index of prices or returns for unique, infrequently traded assets such as houses, art and musical instruments, which are likely to be prone to exhibit serial correlation in returns. We demonstrate our methodology on a data set of art prices and on a data set of real estate prices from the city of Amsterdam.

Are There Smaller Leverage Effects in Less-Developed Markets? Evidence from an Oil Exporting Country

Problem statement: This study uses daily data from the Tehran Stock Market (TSM) to illustrate the nature of stock market volatility in an undeveloped and young stock market. Although most studies suggest that a negative shock to stock prices will generate more volatility than a positive shock of equal magnitude but there is no evidence of asymmetric effect in TSM. Determine the nature of stock market volatility in an oil exporting country. Approach: Trading in Tehran Stock Market (TSM) is based on orders sent by the brokers. The data consist of 2375 daily observations of the closing value of the Tehran stock market from 3/30/1998 to 5/04/2007. Our empirical finding shows that the unconditional variance is 0.18 but visual inspections of the time series suggests that volatility of the stock return rate displays the clustering phenomenon associated with GARCH processes. Results: The estimation and test results for all models suggest that the leverage effect term, γ, is not significant at 5% level. Although, in Asym. CARCH model based on normal distribution for errors, the estimated coefficient on the asymmetry term is -0.066 with a z-statistics of -1.749 recognized as significant at 10% level, but it has the wrong sign. It seems that good news and bad news has the same effect on stock prices in TSM, a result that is contradictory to other studies for developed countries. Conclusion: The estimated models containing TARCH, EGARCH, asymmetric CARCH and PARCH with different assumptions on error distributions suggest no strong and significant asymmetric effect. There are some reasons for this finding: (1) In Iran with Islamic laws, debt contracts are illegal or at least not enforced and Iranian firms do not have any financial leverage. As a result, we would expect to find smaller leverage effects in volatility in Iran than in the United States, for example. In deed the institutional differences with western financial markets manifest themselves in different return characteristics. (2) Stock prices in the TSM by regulation and intervention cannot exceed from some range. The strong serial correlation in returns necessitating long lags in the mean equations is possibly due to such regulations. (3) The history of TSM is very short compared to other stock markets and the information flow in this market is very slow. The estimated coefficients on the expected risk (as a measure of the risk-return tradeoff) are not significant. These findings suggest that the TSM is not efficient.

Abnormal trading volume and autoregressive behavior in weekly stock returns in the Saudi stock market

This paper examines the relationship between the abnormal change in trading volume of both individual stocks and portfolios and short-term price autoregressive behavior in the Saudi stock market (SSM). Our objective is to investigate the informational role that trading volume plays in predicting the direction of short-term returns. We evaluate whether the abnormal change in lagged, contemporaneous, and lead turnovers affects serial correlation in returns. Specifically, we examine if and when the change in volume produces momentum (positive correlation) or reversal (negative autocorrelation) in consecutive weekly stock returns. We find a reversal in weekly stock returns when conditioned on the change in lagged volume in the SSM. Our results are consistent for the whole sample, the two sub-sample periods, and the large- and small-firm portfolios. The results are consistent with Campbell, Grossman, and Wang [Campbell, J. Y., S. J. Grossman, and J. Wang, 1993, Trading volume and serial correlation in stock returns, Quarterly Journal of Economics, 108, 905–939], who present a model in which risk-averse market makers accommodate the selling pressure of liquidity or non-informational traders. We also find that reversal is more pronounced with the loser portfolio as specified by filter-based methodology. The overall result of this paper is also consistent with the empirical findings of Conrad, Hameed, and Niden [Conrad, J., A. Hameed, and C. Niden, 1994, Volume and autocovariances in short-horizon individual security returns, Journal of Finance 49, 1305–1329.] and Gebka [Gebka, B., 2005, Dynamic volume-return relationship: evidence from an emerging market, Applied Financial Economics, 15, 1019–1029] in which they report price reversal for stock with high trading volume.

Makroökonomische Nachrichten und die Reaktion des 15-Sekunden-DAX: Eine Ereignisstudie zur Wirkung der ZEW-Konjunkturprognose / Announcement of Business Cycle Forecasts and the Reaction of the German Stock Market

Summary We study the response of the German stock market index DAX to the announcement of macroeconomic business cycle forecasts. Returns are computed using high-frequency data observed for 15-second intervals. Publications of macroeconomic US indicators at 2:30 p.m. (CET) have temporary and opening of the New York Stock Exchange at 3:30 p.m. (CET) have permanent effects on the volatility of the German DAX. Moreover, the intraday volatility of the DAX index has a U-shaped form, which has also been identified for other international stock markets. Major reactions of both returns and volatility occur within the first 15 to 60 seconds after the announcement, revealing a high efficiency of the German capital market. Unanticipated shocks cause asymmetric stock market returns: “good” news lead to more pronounced reactions than “bad” news. Moreover, there is evidence of mean reversion and calm-before-thestorm effects. Finally, serial correlation of returns is found to be a potentially spurious result of non-anticipated announcements of macroeconomic news.

Announcement of Business Cycle Forecasts and the Reaction of the German Stock Market

Summary: We study the response of the German stock market index DAX to the announcement of macroeconomic business cycle forecasts. Returns are computed using highfrequency data observed for 15-second intervals. Results reveal immediate stock market reactions. Major reactions involving both returns and volatility occur within the initial 15 to 60 seconds after the announcement. Unanticipated shocks cause asymmetric stock market returns: ‘good’ news leads to more pronounced reactions than ‘bad’ news. Moreover, there is evidence of mean reversion and calm-before-the-storm effects. Finally, serial correlation of returns is found to be a potentially spurious result of non-anticipated announcements of macroeconomic news.

The value of asset allocation advice: Evidence from The Economist's quarterly portfolio poll

This study analyzes the economic importance of portfolio advice for an investor with an international and multiple-asset investment strategy. We construct portfolios based upon the asset allocation and security market advice of major international investment bankers and analyze the performance using weight-based techniques. Our results indicate that portfolio advisers are not able to outperform passive benchmarks. They do not realize superior performance either through appropriate timing or selection skills. Apparent market timing skills as measured by the Portfolio Change Measure are to a large extent an artifact caused by serial correlation in the return indices used. Likewise, the apparent short-run performance persistence is more due to the serial correlation in returns than to active portfolio selection strategies.

The value of asset allocation advice: Evidence from The Economist's quarterly portfolio poll

This study analyzes the economic importance of portfolio advice for an investor with an international and multiple-asset investment strategy. We construct portfolios based upon the asset allocation and security market advice of major international investment bankers and analyze the performance using weight-based techniques. Our results indicate that portfolio advisers are not able to outperform passive benchmarks. They do not realize superior performance either through appropriate timing or selection skills. Apparent market timing skills as measured by the Portfolio Change Measure are to a large extent an artifact caused by serial correlation in the return indices used. Likewise, the apparent short-run performance persistence is more due to the serial correlation in returns than to active portfolio selection strategies.

Returns Momentum, Returns Reversals and Earnings Surprises

Abnormal stock returns measured over intervals of less than a year exhibit positive serial correlation, or returns momentum, while returns measured over longer periods exhibit negative serial correlation, or returns reversals. This paper examines if patterns in earnings surprises, together with investors? inefficient reactions to those earnings surprises, account for the observed serial correlation in returns. Prior literature has documented that over periods of less than one year, earnings surprises are positively serially correlated. We document that over longer periods, they are negatively serially correlated. This pattern is strikingly similar to the pattern in returns. In addition to documenting these patterns across intervals, we also show that for any particular interval, the serial correlation of returns and the serial correlation of earnings surprises are related. Controlling for cross-sectional differences in firms? serial correlations in earnings surprises, we are able to eliminate the serial correlation in returns at 3-, 24-, 36-, and 48-month intervals. We find some evidence of residual serial correlation in returns at 6-, 12-, and 60-month intervals. Overall, our results suggest that the serial correlation in earnings surprises is an important factor in determining the sign and magnitude of the serial correlation in returns.

Feedback Effect of Stock Prices on Fundamental Values: Price Manipulation and Herding with Rational Expectations

In this paper, we attribute a resource allocation role to stock prices. When informed investors possess private information important to a firm's investment decision, they need to transmit it to the firm manager. A natural way to achieve this is by trading in a way that allows the manager to infer their information. However, when their trading patterns affect firm investments, there is an incentive to generate the pattern the manager responds to. For instance, if managers respond favorably to a string of price increases, later investors have an incentive to manipulate prices by buying shares (after observing earlier investors buying) even with unfavorable information. In most models of rational expectations, such price manipulation results in trading losses and can be supported only by imposing market incompleteness or restricted participation. However, with a feedback effect, just giving investors positive inventory leads to potential herding as investors can recoup their trading loss through the value increase of their inventory. Also, price manipulation is value increasing since informed investors generate investment-affecting patterns only when the resulting investment is desirable. However, since prices are martingales, herding in trades does not translate into serial correlation of returns and momentum based profits.

Sensitivity of Systematic Risk Estimates to the Return Measurement Interval Under Serial Correlation

This paper analytically and empirically investigates the sensitivity of the return measurement interval to the market beta estimate and suggests a market beta estimation method incorporating the investment horizon through a vector autoregressive (VAR) model when there is serial correlation in returns. The analytical relation between the beta estimate and the return measurement interval is obtained. Based on the analytical relation, a decision function for the intervalling effect is provided. It is found that the intervalling effect is mostly caused by January returns.

Market Efficiency, Rational Expectations, and Estimation Risk

In asset pricing, estimation risk refers to investor uncertainty about the parameters of the return or cashflow process. We show that estimation risk can significantly affect the time-series and cross-sectional behavior of asset prices. In particular, parameter uncertainty will tend to induce price reversals and negative serial correlation in returns. Prices can violate familiar 'volatility bounds' when investors are rational. Cross-sectionally, expected returns deviate from the CAPM even if investors attempt to hold mean-variance efficient portfolios, and these deviations will be predictable based on past dividends, prices, and returns. In short, we argue that estimation risk is likely to be important for characterizing an efficient market.

Arithmetic versus geometric mean estimators: Setting discount rates for capital budgeting

AbstractThis paper addresses an issue central to the estimation of discount rates for capital budgeting: should the geometric mean or arithmetic mean of past data be used when estimating the discount rate? the use of the arithmetic mean ignores estimation error and serial correlation in returns. Unbiased discount factors have been derived that correct for both these effects. In all cases, the corrected discount rates are closer to the arithmetic than the geometric mean.

Reply: Specialists' Performance and Serial Dependence of Stock Price Changes

In my paper utilized time-variance relationships to detect the impact of NYSE specialists on stock price changes. Schwartz and Whitcomb (SW) seem to agree that return variability and not average bid ask spreads is the appropriate measure on which performance of NYSE specialists should be evaluated. They raise, however, several objections regarding the use of time-variance relationships to evaluate specialists' performance. In particular they show that the proposed performance measure which is the average (per specialist unit) ratio of short term relative to long term return variance depends on the degree of autocorrelation in the return series. For first order serial correlation of returns they obtain, where r is the performance measure (in terms of a single security), T is the length of the differencing interval, are returns variances for one day and T day intervals respectively, ρ 1,2 is first order serial correlation.