Parameter Specifications That Make Little Difference in Anomaly Studies

Krueger, Thomas M.; Johnson, Keith H.

doi:10.1111/j.1468-5957.1991.tb01123.x

Cited by 11 publications

(8 citation statements)

References 36 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…All indices are value weighted indices; they weight of the returns of a firm within the index is determined by the market value of the index (see Krueger and Johnson, 1991). We require a stock market index for every country that has firms in our sample.…”

Section: Methods and Datamentioning

confidence: 99%

Scoring on the stock exchange? The effect of football matches on stock market returns: an event study

Scholtens¹,

Peenstra

2009

Applied Economics

View full text Add to dashboard Cite

Section: Methods and Datamentioning

confidence: 99%

Scoring on the stock exchange? The effect of football matches on stock market returns: an event study

Scholtens¹,

Peenstra

2009

Applied Economics

View full text Add to dashboard Cite

“…It generally performs slightly better with the equally weighted than with the value weighted index, and the difference is significant when event dates are shared because of lower crosscorrelation of residuals with the equally weighted index (see Section 5.1). However, Krueger and Johnson (1991), testing efficient market anomalies, obtain similar results using the CRSP equally weighted index and the NYSE composite index (value weighted); there are differences, but they believe that 'anomaly research findings are generally robust to market surrogate selection' (p. 579). Thompson (1988) uses simulation with daily data to compare the standard market model with a version in which the appropriate industry index is substituted (9 Basil Blafkwcll 1995 for the market index and with a two-factor version in which the industry index is included with the market index.…”

Section: Choice Of Market Indexmentioning

confidence: 97%

“…Their results are not affected by estimating coefficients from returns over three or five day periods rather than single days. Krueger and Johnson (1991) use the F-ratio instead of the ?-statistic to test the significance of abnormal returns arising from three efficient market anomalies using the index and beta-adjusted models, the latter being the market model without the a term, i.e. AR, = Rit -BiRm,.…”

Section: Simulation Experimentsmentioning

confidence: 99%

“…Making adjustments for regression towards their mean reduces the dispersion of betas and can significantly alter results compared with non-adjustment. For example, Krueger and Johnson (1991), using 60 months' data to estimate historic betas and a simple adjustment for their regression tendency, state that their 'results indicate that anomaly studies are sensitive to the characterisation of beta' (p. 578). The error in estimating betas due to this phenomenon can be minimised by using a split estimation period before and after the event period and is also smaller the more shares in the portfolio and the longer the return interval (Foster, Hansen and Vickrey, 1988).…”

Section: Beta Stabilitymentioning

confidence: 99%

See 1 more Smart Citation

Event Study Methods and Evidence on Their Performance

Armitage

1995

Journal of Economic Surveys

288

130

View full text Add to dashboard Cite

The paper outlines widely used methods of estimating abnormal returns and testing their significance, highlights respects in which they differ conceptually, and reviews research comparing results they produce in various empirical contexts. Direct evidence on the performance of different methods is available from simulation experiments in which known levels of abnormal return are added. The market model is most commonly used to generate expected returns and no better alternative has yet been found despite the weak relationship between beta and actual returns. Choice of procedure for significance testing depends on the characteristics of the data. The evidence indicates that in many cases the best procedure is to standardise market model abnormal returns by their time series standard errors of regression and use the ?-test. Alternatively a rank test appears to be at least as powerful. If errors are crosscorrelated or increase in variance during the test period, other methods discussed should be used.

show abstract

“…Brown and Warner (1985) suggested that an equally-weighed market index could detect the abnormal performance better than the value-weighted market index. Krueger and Johnson (1991) tested the abnormal performance for market efficiency by using both equally-weighed and value-weighted market index. The results were similar and the authors suggested the difference for the results between equallyweighed and value-weighted market index are generally robust to market surrogate selection.…”

Section: Sample Datamentioning

confidence: 99%

An empirical analysis of the effects of market response to bank loan announcements in Hong Kong stock market

Qing¹,

Gan

Li³

2011

J Bank Regul

View full text Add to dashboard Cite

of a thesis submitted in partial fulfillment of the requirements for the Degree of M.C.M An Empirical Analysis of the Effects of Market Response to Bank Loan Announcements in the Hong Kong Stock Market Qing ChenThis study will validate several key results from previous studies of bank loan announcement effects by using the data from Hong Kong market following the 1997 Asian crisis. Banks are believed to play a unique role in financial market which could effectively reduce the problem of information asymmetry and moral hazard. Banks could access borrowers' inside information which is not available to other participants.Thus bank loan announcements convey valuable information to the market, and market response of the stock price should be positive. However, because of the significant reform in both financial market and information market, the valuation of bank loan announcement conveyed need to be reconsidered. This study investigates whether banks are still "unique" in the financial market or whether they are like middlemen between borrowers and investors. Data used in this study is collected from the Hong Kong Stock Exchange Index, and a standard event study with the market model is applied in the research to conduct the empirical analysis.The results suggest bank loan announcements are associated with significantly higher positive abnormal returns than non-bank loan announcements. Based on the market model of event study, market response is found to be significantly positive for loan syndication, short maturity loan and borrower's debt ratio, and negatively related to II firm size and loan size. Bank loans with refinancing and capital expenditure and no specific purpose have significantly higher positive abnormal returns, and borrowers with property and industrial industry type have more significant positive abnormal returns compared to other industry type. The findings also suggest the Hong Kong stock market is efficient in both strong and semi-strong form for bank loan announcements. A strong evidence of information leakage problem is found for nonbank loan announcements. The results are generally consistent with the existing literature.Key Words: bank loan announcements, abnormal returns, information asymmetry, syndication, loan size, loan maturity, loan purpose, firm size, industry type, debt ratio, market efficiency. III ACKNOWLEDGEMENTS

show abstract

Parameter Specifications That Make Little Difference in Anomaly Studies

Cited by 11 publications

References 36 publications

Scoring on the stock exchange? The effect of football matches on stock market returns: an event study

Scoring on the stock exchange? The effect of football matches on stock market returns: an event study

Event Study Methods and Evidence on Their Performance

An empirical analysis of the effects of market response to bank loan announcements in Hong Kong stock market

Contact Info

Product

Resources

About