Estimating betas from nonsynchronous data

doi:10.1016/0304-405X(77)90041-1

Journal of Financial Economics

Volume 5, Issue 3, December 1977, Pages 309-327

https://doi.org/10.1016/0304-405X(77)90041-1 Get rights and content

Abstract

Nonsynchronous trading of securities introduces into the market model a potentially serious econometric problem of errors in variables. In this paper properties of the observed market model and associated ordinary least squares estimators are developed in detail. In addition, computationally convenient, consistent estimators for parameters of the market model are calculated and then applied to daily returns of securities listed in the NYSE and ASE.

References (7)

G. Schwert
Stock exchange seats as capital assets
Journal of Financial Economics
(1977)
P. Clark
A subordinated stochastic process model with finite speculative prices
Econometrica
(1973)
K. Cohen et al.
On the existence of serial correlation in an efficient market

There are more references available in the full text version of this article.

Cited by (1728)

Lottery demand, weather and the cross-section of stock returns
2024, Journal of Behavioral and Experimental Finance
We investigate the role that weather-induced mood plays in underperformance of lottery stocks. We hypothesize that during pleasant weather conditions, investors are more likely to become risk-taking and optimistic, and invest more in lottery stocks. This results in overpricing and lower expected return for these stocks. We use sky cloud cover as a proxy for the weather condition and show that the MAX effect mainly exists following sunny weather; however, there is less evidence for the MAX anomaly following cloudy weather. Our finding is robust to using alternative constructions of MAX and skewness measures as well as other proxies for weather condition such as rain, wind and temperature.
Market timing in open market bond repurchases
2024, Journal of Banking and Finance
Bond repurchases are widespread in the US and other markets but data limitations have thus far prevented market-timing analysis. Using unique Israeli daily data we show that firms time the market in their actual open market bond repurchases. Bond repurchases typically follow price decline and result in significantly positive abnormal returns in the following days: about 1 % in five trading days. The market reaction is quicker within a pre-announced repurchase program, and it is stronger when the firm repurchases high-yield bonds or when the repurchase is preceded by positive net insider share purchases. The results lend support to the information motive for bond repurchases benefiting ongoing stakeholders but detrimental to selling bondholders.
Ambiguity and risk in the oil market
2024, Economic Modelling
The empirical evidence about the risk-return relationship in the oil market is mixed and puzzling. Studies in this domain often treat risk and ambiguity (i.e., uncertainty) as interchangeable concepts without making any clear distinction. Motivated by these discrepancies and the limited knowledge about ambiguity in the oil market, we establish a clear difference between risk and ambiguity to explain future returns. Using state-of-the-art methods and high-frequency data from the oil market for 2006–2022, we estimate the risk and level of ambiguity reflected in the oil market. We test the extent to which oil market participants reflect aversion to or love for ambiguity and risk. Our findings indicate that ambiguity and risk contain different information, and both are included in the pricing of crude oil. In addition, risk positively affects expected oil returns, and aversion to ambiguity has a positive relationship with the expected probability of good news and favorable returns.
Property crime and lottery-related anomalies
2024, Global Finance Journal
In this paper, we explore the association between property crime rate and lottery demand anomalies. Motivated by criminology literature that suggests a positive relation between crime and risk-taking, we conjecture that gambling propensity in the stock market is stronger (weaker) in regions with higher (lower) property crime rate. Consistent with our conjecture, we show that underperformance of lottery stocks, proxied by MAX, is more pronounced in the US regions with higher property crime rates compared to regions with lower property crime rates. Our results are robust to alternative proxies for lottery demand, such as alternative constructions of MAX and skewness measures, and various empirical tests. Our findings suggest variation in crime-induced gambling propensity affects financial market outcomes.
More than meets the eye: On the relationship between skewness and expected returns
2024, Finance Research Letters
I investigate the relationship between skewness and expected stock returns. I find that this relationship is not lineal, as previously established, and its sign varies. Applying a methodology that estimates breakpoints in the relationship between variables results in two breakpoints, delimiting three zones. Returns are decreasing in skewness, but only for mid-skewness stocks. For low- and high-skewness stocks, the relationship is positive. An explanation of these findings is that investors who seek stocks with lottery-like characteristics such as high skewness generate the observed negative relationship in the mid-skewness zone, whereas more rational investors prevail in the other zones.
Did the Indian stock market overreact to Covid-19?
2024, North American Journal of Economics and Finance
Several studies have used event studies to determine the impact of events such as war or pandemics on individual stocks. However, standard event study methodologies assume that the event does not affect the market index. Our study introduces a framework that aims to aid in interpreting event study findings, particularly in evaluating the effects of widespread factors such as pandemics or wars on individual stocks. We then use this framework to understand the impact of Covid-19 on stock prices in India.
We examine the returns of stocks from sectors that were adversely affected and those that benefitted (or did not suffer) during the pandemic. Using the daily returns of Indian companies, we find that the returns on stocks from both sectors fell during the pandemic before the returns started increasing for the safe sectors. We find that this happens because the entire index fell after the event. After we adjusted for this, we found that the safer stocks generated positive abnormal returns while the riskier stocks generated negative abnormal returns during this period. We also find that the market overreacted initially but started correcting itself after eight trading days.

View all citing articles on Scopus

^∗: We thank Michael Jensen and the referee, G. William Schwert, for comments on a previous draft, Marvin Lipson for programming assistance, and the Center for Research in Security Prices, University of Chicago, for financial support.

View full text

Estimating betas from nonsynchronous data

Abstract

Journal of Financial Economics

A subordinated stochastic process model with finite speculative prices

Econometrica

On the existence of serial correlation in an efficient market