# zbMATH — the first resource for mathematics

A modification of the Hartung-Knapp confidence interval on the variance component in two-variance-component models. (English) Zbl 1134.62018
Summary: We consider a construction of approximate confidence intervals on the variance components $$\sigma_1^2$$ in mixed linear models with two variance components with non-zero degrees of freedom for error. An approximate interval that seems to perform well in such a case, except that it is rather conservative for large $$\sigma_1^2/\sigma^2$$, was considered by J. Hartung and G. Knapp [J. Stat. Comput. simulation 65, No. 4, 311–323 (2000; Zbl 0966.62044)]. The expression for its asymptotic coverage when $$\sigma_1^2/\sigma^2\to\infty$$ suggests a modification of this interval that preserves some nice properties of the original and that is, in addition, exact when $$\sigma_1^2/\sigma^2\to\infty$$. It turns out that this modification is an interval suggested by M. Y. El-Bassiouni [Commun. Stat., Theory Methods 23, No. 7, 1915–1933 (1994; Zbl 0825.62194)]. We comment on its properties that were not emphasized in the original paper of El-Bassiouni, but which support use of the procedure. Also a small simulation study is provided.
##### MSC:
 62F25 Parametric tolerance and confidence regions 62J10 Analysis of variance and covariance (ANOVA)
##### Keywords:
approximate confidence intervals; mixed linear model
Full Text:
##### References:
 [1] Arendacká A.: Approximate confidence intervals on the variance component in a general case of a two-component model. Proc. ROBUST 2006 (J. Antoch and G. Dohnal, Union of the Czech Mathematicians and Physicists, Prague 2006, pp. 9-17 [2] Billingsley P.: Convergence of Probability Measures. Wiley, New York 1968 · Zbl 0944.60003 [3] Boardman T. J.: Confidence intervals for variance components - a comparative Monte Carlo study. Biometrics 30 (1974), 251-262 · Zbl 0286.62055 · doi:10.2307/2529647 [4] Burdick R. K., Graybill F. A.: Confidence Intervals on Variance Components. Marcel Dekker, New York 1992 · Zbl 0755.62055 [5] El-Bassiouni M. Y.: Short confidence intervals for variance components. Comm. Statist. Theory Methods 23 (1994), 7, 1951-1933 · Zbl 0825.62194 · doi:10.1080/03610929408831364 [6] Hartung J., Knapp G.: Confidence intervals for the between group variance in the unbalanced one-way random effects model of analysis of variance. J. Statist. Comput. Simulation 65 (2000), 4, 311-323 · Zbl 0966.62044 · doi:10.1080/00949650008812004 [7] Park D. J., Burdick R. K.: Performance of confidence intervals in regression models with unbalanced one-fold nested error structures. Comm. Statist. Simulation Computation 32 (2003), 3, 717-732 · Zbl 1081.62540 · doi:10.1081/SAC-120017858 [8] Seely J., El-Bassiouni Y.: Applying Wald’s variance component test. Ann. Statist. 11 (1983), 1, 197-201 · Zbl 0516.62028 · doi:10.1214/aos/1176346069 [9] Tate R. F., Klett G. W.: Optimal confidence intervals for the variance of a normal distribution. J. Amer. Statist. Assoc. 54 (1959), 287, 674-682 · Zbl 0096.12801 · doi:10.2307/2282545 [10] Thomas J. D., Hultquist R. A.: Interval estimation for the unbalanced case of the one-way random effects model. Ann. Statist. 6 (1978), 3, 582-587 · Zbl 0386.62057 · doi:10.1214/aos/1176344202 [11] Tukey J. W.: Components in regression. Biometrics 7 (1951), 1, 33-69 [12] Wald A.: A note on the analysis of variance with unequal class frequencies. Ann. Math. Statist. 11 (1940), 96-100 · Zbl 0063.08115 · doi:10.1214/aoms/1177731946 [13] Wald A.: A note on regression analysis. Ann. Math. Statist. 18 (1947), 4, 586-589 · Zbl 0029.30703 · doi:10.1214/aoms/1177730350 [14] Williams J. S.: A confidence interval for variance components. Biometrika 49 (1962), 1/2, 278-281 · Zbl 0138.13101 · doi:10.1093/biomet/49.1-2.278
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. It attempts to reflect the references listed in the original paper as accurately as possible without claiming the completeness or perfect precision of the matching.