On the order statistics from equally correlated normal random variables

Gupta, Shanti S.; Nagel, K.; Panchapakesan, S.

doi:10.1093/biomet/60.2.403

Cited by 100 publications

(13 citation statements)

References 14 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The h quantity appearing in this expression has been tabulated (to 3 dp) by in Table I for k = 2(1)51 and P* = .75, .90, .95, .975, and .99. Similar values are provided (to 4 dp) in Table 1 of Gupta, Nagel and Panchapakesan (1973) for the same P* and k = 2(1)11(2)51. Additional tabulation of h is provided by Milton (1963).…”

Section: Nonparametric Techniques In Multiple Decision Theorysupporting

confidence: 53%

Nonparametric Procedures in Multiple Decisions (Ranking and Selection Procedures)

Gupta¹,

McDonald²

1980

Self Cite

View full text Add to dashboard Cite

This article surveys statistical techniques which are nonparametric in nature and used in formal ranking and selection of populations. Such methods have been developed only within the last fifteen years and are usually based on rank scores and/or robust estimators (such as the Hodges-Lehmann estimator). The procedures surveyed are applicable to one-way classifications, two-way classifications, and paired-comparison models. Computational methods, useful inequalities, and appropriate numerical tables required to implement these techniques are identified and discussed. Asymptotic relative efficiencies of the nonparametric methods, compared to their parametric counterparts, are presented. Specific applications of these methods (such as traffic fatality rates) are mentioned and areas for further theoretical and computational research are identified. ITuY C&.AIICATOW OF' THIl WAGS iImU fgae De..... MUQ.LA r it rom k~..URITY CLASSIFICATION OF THIS PAGE(W~mho Does ffnee,.d the nonparametric methods, compared to their parametric counterparts, are presented. Specific applications of these methods (such-as traffic fatality rates) are mentioned and areas for further theoretical and computational research are identified. UNCLASSIFIED SECURITY CLAWICATION OF THIS PA@Ef~aa Do* Eata..Q

show abstract

Section: Nonparametric Techniques In Multiple Decision Theorysupporting

confidence: 53%

Nonparametric Procedures in Multiple Decisions (Ranking and Selection Procedures)

Gupta¹,

McDonald²

1980

Self Cite

View full text Add to dashboard Cite

show abstract

“…Table shows the results. The entries for positive ρ may also be found in Gupta et al (1973). The entries for ρ = −1, ρ = 1 and ρ = 0 are intuitive or familiar.…”

Section: Econometric Proceduresmentioning

confidence: 55%

“…5 5 Gupta et al (1973) provide critical values computed by numerical integration, in the special case when the m statistics are equicorrelated. We found that 50,000 draws were sufficient to match the Gupta et al (1973) critical values to three decimal places. …”

mentioning

confidence: 99%

Forecast evaluation of small nested model sets

Hubrich

West

2010

J of Applied Econometrics

View full text Add to dashboard Cite

show abstract

“…The right half of Figure shows the power when β O = 0.5 : minP outperforms each individual test, where each individual test includes only one covariate (because all individual tests have the same power, it is averaged and shown as the power for T 1 ). Remark For both the two‐covariate and five‐covariate cases, the critical values obtained from simulations were compared (where possible) with critical values in Gupta et al , who obtained it from the angle bisection method assuming equally correlated normally distributed random variables, and with those in Tarone . The three sets of critical values are in good agreement.…”

Section: Minp With Linear Modelsmentioning

confidence: 82%

Robust inference from multiple test statistics via permutations: a better alternative to the single test statistic approach for randomized trials

Ganju

Julie

2013

Pharmaceutical Statistics

View full text Add to dashboard Cite

Formal inference in randomized clinical trials is based on controlling the type I error rate associated with a single pre-specified statistic. The deficiency of using just one method of analysis is that it depends on assumptions that may not be met. For robust inference, we propose pre-specifying multiple test statistics and relying on the minimum p-value for testing the null hypothesis of no treatment effect. The null hypothesis associated with the various test statistics is that the treatment groups are indistinguishable. The critical value for hypothesis testing comes from permutation distributions. Rejection of the null hypothesis when the smallest p-value is less than the critical value controls the type I error rate at its designated value. Even if one of the candidate test statistics has low power, the adverse effect on the power of the minimum p-value statistic is not much. Its use is illustrated with examples. We conclude that it is better to rely on the minimum p-value rather than a single statistic particularly when that single statistic is the logrank test, because of the cost and complexity of many survival trials.

show abstract

On the order statistics from equally correlated normal random variables

Cited by 100 publications

References 14 publications

Nonparametric Procedures in Multiple Decisions (Ranking and Selection Procedures)

Nonparametric Procedures in Multiple Decisions (Ranking and Selection Procedures)

Forecast evaluation of small nested model sets

Robust inference from multiple test statistics via permutations: a better alternative to the single test statistic approach for randomized trials

Contact Info

Product

Resources

About