×

Interval estimation of variance ratio in non-normal unbalanced one-way random models. (English) Zbl 1453.62586

Summary: Confidence intervals based on the harmonic mean method are proposed for estimating the ratio of variance components and/or the intraclass correlation coefficient (\( \rho \)) in unbalanced one-way random models without the normality assumptions. Since the proposed procedure is heavily dependent on the estimation of the kurtosis of the underlying distributions, bias-corrected estimators of kurtosis are proposed as well. Several asymptotic results concerning the proposed procedure are given along with simulation results to assess its performance in finite sample size situations. The proposed intervals are also compared with the corresponding confidence intervals based on the arithmetic mean method and were found to effectively maintain the nominal probability of coverage, except for leptokurtic distributions with fairly large kurtosis where the intervals tend to be liberal. According to the simulation results, the proposed harmonic mean intervals are recommended for use in practice. However, while computing the harmonic mean intervals, the bias-corrected estimators of kurtosis should be used when it is anticipated that \(\rho\) is small, but for large \(\rho\) the empirically corrected estimators of kurtosis should be adopted. The procedure is illustrated using a real data set.

MSC:

62J10 Analysis of variance and covariance (ANOVA)
62F25 Parametric tolerance and confidence regions
PDFBibTeX XMLCite
Full Text: DOI

References:

[1] D.G. Bonett, Sample size requirements for estimating intraclass correlations with desired precision, Stat. Med. 21 (2002), pp. 1331-1335. doi: 10.1002/sim.1108[Crossref], [PubMed], [Web of Science ®], [Google Scholar]
[2] W.G. Cochran, Sampling Techniques, 3rd ed., Wiley Series in Probability and Mathematical Statistics-Applied, John Wiley & Sons, New York, 1977. [Google Scholar] · Zbl 0353.62011
[3] A. Wald, A note on the analysis of variance with unequal class frequencies, Ann. Math. Statist. 11 (1940), pp. 96-100. doi: 10.1214/aoms/1177731946[Crossref], [Google Scholar] · JFM 66.0642.02
[4] D.A. Harville and A.P. Fenech, Confidence intervals for a variance ratio, or for heritability, in an unbalanced mixed linear model, Biometrics 41 (1985), pp. 137-152. [Google Scholar] · Zbl 0607.62031
[5] R.K. Burdick, F. Maqsood, and F.A. Graybill, Confidence intervals on the intraclass correlation in the unbalanced one-way classification, Comm. Statist. Theory Methods 15 (1986), pp. 3353-3378. doi: 10.1080/03610928608829315[Taylor & Francis Online], [Web of Science ®], [Google Scholar] · Zbl 0613.62046
[6] J.D. Thomas and R.A. Hultquist, Interval estimation for the unbalanced case of the one-way random effects model, Ann. Statist. 6 (1978), pp. 582-587. doi: 10.1214/aos/1176344202[Crossref], [Web of Science ®], [Google Scholar] · Zbl 0386.62057
[7] T. Zoubeidi and M.Y. El-Bassiouni, Sequential confidence intervals for variance components in one-way random models, J. Statist. Plann. Inference 137(4) (2007), pp. 1185-1198. doi: 10.1016/j.jspi.2006.04.004[Crossref], [Web of Science ®], [Google Scholar] · Zbl 1107.62076
[8] M.Y. El-Bassiouni and T. Zoubeidi, Adaptive interval estimation in one-way random effects models, J. Statist. Plann. Inference 138 (2008), pp. 857-872. doi: 10.1016/j.jspi.2007.02.008[Crossref], [Web of Science ®], [Google Scholar] · Zbl 1130.62084
[9] D.A. Harville, Maximum likelihood approaches to variance components estimation and to related problems, J. Amer. Statist. Assoc. 72 (1977), pp. 320-332. doi: 10.1080/01621459.1977.10480998[Taylor & Francis Online], [Web of Science ®], [Google Scholar] · Zbl 0373.62040
[10] B.D. Burch and I.R. Harris, Closed-form approximations to the REML estimator of a variance ratio (or heritability) in a mixed linear model, Biometrics 57(4) (2001), pp. 1148-1156. [Google Scholar] · Zbl 1209.62154
[11] J. Jiang, REML estimation: Asymptotic behavior and related topics, Ann. Statist. 24 (1996), pp. 255-286. doi: 10.1214/aos/1033066209[Crossref], [Web of Science ®], [Google Scholar] · Zbl 0853.62022
[12] J. Jiang, Partially observed information and inference about non-Gaussian mixed linear models, Ann. Statist. 33(6) (2005), pp. 2695-2731. doi: 10.1214/009053605000000543[Crossref], [Web of Science ®], [Google Scholar] · Zbl 1084.62060
[13] J. Hannig, H. Iyer, and P. Patterson, Fiducial generalized confidence intervals, J. Amer. Statist. Assoc. 101(473) (2006), pp. 254-269. doi: 10.1198/016214505000000736[Taylor & Francis Online], [Web of Science ®], [Google Scholar] · Zbl 1118.62316
[14] E. Lidong, J. Hannig and H. Iyer, Fiducial intervals for variance components in an unbalanced two-component normal mixed linear model, J. Amer. Statist. Assoc. 103(482) (2008), pp. 854-865. doi: 10.1198/016214508000000229[Taylor & Francis Online], [Web of Science ®], [Google Scholar] · Zbl 1471.62410
[15] J. Hannig, On generalized fiducial inference, Statist. Sinica 19(2) (2009), pp. 491-544. [Web of Science ®], [Google Scholar] · Zbl 1168.62004
[16] R.K. Burdick, J. Quiroz, and H.K. Iyer, The present status of confidence interval estimation for one-factor random models, J. Statist. Plann. Inference 136(12) (2006), pp. 4307-4325. doi: 10.1016/j.jspi.2005.07.004[Crossref], [Web of Science ®], [Google Scholar] · Zbl 1099.62027
[17] B.D. Burch, Assessing the performance of normal-based and REML-based confidence intervals for the intraclass correlation coefficient, Comput. Statist. Data Anal. 55 (2011), pp. 1018-1028. doi: 10.1016/j.csda.2010.08.007[Crossref], [Web of Science ®], [Google Scholar] · Zbl 1284.62116
[18] B.D. Burch, Confidence intervals for variance components in unbalanced one-way random effects model using non-normal distributions, J. Statist. Plann. Inference 141 (2011), pp. 3793-3807. doi: 10.1016/j.jspi.2011.06.015[Crossref], [Web of Science ®], [Google Scholar] · Zbl 1235.62032
[19] M. Shoukri, D. Tracy, and I. Mian, The effect of kurtosis in the estimation of the parameters of the one-way random effects model from familial data, Comput. Statist. Data Anal. 10(3) (1990), pp. 339-345. doi: 10.1016/0167-9473(90)90016-B[Crossref], [Web of Science ®], [Google Scholar] · Zbl 0825.62596
[20] F. Teuscher, G. Herrendorfer, and V. Guiard, The estimation of skewness and kurtosis of random effects in the linear model, Biom. J. 36(6) (1994), pp. 661-672. doi: 10.1002/bimj.4710360603[Crossref], [Web of Science ®], [Google Scholar] · Zbl 0835.62058
[21] H. Singh, S. Shukla, and S. Singh, The utilization of kurtosis in the estimation of the parameters of the one-way random effects model, Biom. J. 36(6) (2002), pp. 661-672. [Google Scholar] · Zbl 1441.62497
[22] L. An and S. Ahmed, Improving the performance of kurtosis estimator, Comput. Statist. Data Anal. 52(5) (2008), pp. 2669-2681. doi: 10.1016/j.csda.2007.09.024[Crossref], [Web of Science ®], [Google Scholar] · Zbl 1452.62026
[23] A. Olsen, J. Seely, and D. Birkes, Invariant quadratic unbiased estimation for two variance components, Ann. Statist. 4(5) (1976), pp. 878-890. doi: 10.1214/aos/1176343586[Crossref], [Web of Science ®], [Google Scholar] · Zbl 0344.62060
[24] L.R. Lamotte, Invariant quadratic estimators in the random one-way ANOVA model, Biometrics 32 (1976), pp. 793-804. doi: 10.2307/2529265[Crossref], [Web of Science ®], [Google Scholar] · Zbl 0399.62073
[25] S.R. Searle, G. Casella, and C.E. McCulloch, Variance Components, Wiley Series in Probability and Statistics, Wiley-Interscience [John Wiley & Sons], Hoboken, NJ, 2006. Reprint of the 1992 original, Wiley-Interscience Paperback Series. [Google Scholar] · Zbl 1108.62064
[26] D.G. Bonett, Approximate confidence interval for standard deviation of nonnormal distributions, Comput. Statist. Data Anal. 50 (2006), pp. 775-782. doi: 10.1016/j.csda.2004.10.003[Crossref], [Web of Science ®], [Google Scholar] · Zbl 1422.62113
[27] H. Ahrens and R. Pincus, On two measures of unbalancedness in a one-way model and their relation to efficency, Biom. J. 23 (1981), pp. 227-235. doi: 10.1002/bimj.4710230302[Crossref], [Google Scholar] · Zbl 0477.62057
[28] S. Willie and S. Berman, Noaa national status and trends program eighth round intercomparison exercise results for trace metals in marine sediments and biological tissues, Technical report, NOAA Thech. Memorandum, NOS ORCA 83, 1995. [Google Scholar]
[29] P.H. Westfall, Robustness and power of tests for a null variance ratio, Biometrika 75 (1988), pp. 207-214. doi: 10.1093/biomet/75.2.207[Crossref], [Web of Science ®], [Google Scholar] · Zbl 0639.62012
[30] R. Bhansali, L. Giraitis, and P. Kokoszka, Convergence of quadratic forms with nonvanishing diagonal, Statist. Probab. Lett. 77(7) (2007), pp. 726-734. [Web of Science ®], [Google Scholar] · Zbl 1283.62027
This reference list is based on information provided by the publisher or from digital mathematics libraries. Its items are heuristically matched to zbMATH identifiers and may contain data conversion errors. In some cases that data have been complemented/enhanced by data from zbMATH Open. This attempts to reflect the references listed in the original paper as accurately as possible without claiming completeness or a perfect matching.