Abstract
It is well known that the regular likelihood ratio test of a bounded parameter is not valid if the boundary value is being tested. This is the case for testing the null value of a scalar variance component. Although an adjusted test of variance component has been suggested to account for the effect of its lower bound of zero, no adjustment of its interval estimate has ever been proposed. If left unadjusted, the confidence interval of the variance may still contain zero when the adjusted test rejects the null hypothesis of a zero variance, leading to conflicting conclusions. In this research, we propose two ways to adjust the confidence interval of a parameter subject to a lower bound, one based on the Wald test and the other on the likelihood ratio test. Both are compatible to the adjusted test and parametrization-invariant. A simulation study and two examples are given in the framework of ACDE models in twin studies.
Similar content being viewed by others
Notes
All upper and lower limits of CIs in this article are non-inclusive except for two cases: (1) a zero lower limit in both adjusted CIs and (2) a lower limit in Wald test adjusted CI that takes the value of the middle point between the observed and the boundary values.
This assumption is satisfied for most models as long as θ0 is not an natural boundary and no nuisance parameter is on or close to their boundaries. See "Discussion" for the issues of a natural boundary and boundary nuisance parameters.
i.e. the probability that the true value is not covered by the CI.
Non-convergent replications were handled by manually adjusting the starting values until convergence was reached.
See “Discussion” section for the distinction between natural and attainable boundaries.
Similarly, a regular CI for an unbounded parameter may not be valid when another parameter is close to its boundary.
References
Boker S, Neale M, Maes H, Wilde M, Spiegel M, Brick T, Spies J, Estabrook R, Kenny S, Bates T, Mehta P, Fox J (2011) OpenMx: an open source extended structural equation modeling framework. Psychometrika 76:306–317
Carey G (2005) Cholesky problems. Behav Genet 35:653–665
Dominicus A, Skrondal A, Gjessing HK, Pedersen NL, Palmgren J (2006) Likelihood ratio tests in behavioral genetics: problems and solutions. Behav Genet 36:331–340
Lehmann EL (1986) Testing statistical hypotheses. Wiley, New York
Neale MC (2004) Mx Manual. Available at http://www.vcu.edu/mx/documentation.html
Neale MC, Cardon LR (1992) Methodology for genetic studies of twins and families. Kluwer, Dordrecht
Neale MC, Heath AC, Hewitt JK, Eaves LJ, Fulker DW (1989) Fitting genetic models with LISREL: hypothesis testing. Behav Genet 19:37–49
Neale MC, Miller MB (1997) The use of likelihood based confidence intervals in genetic models. Behav Genet 27:113–120
Self SG, Liang K-Y (1987) Asymptotic properties of maximum likelihood estimators and likelihood ratio tests under non-standard conditions. J Am Stat Assoc 82:605–610
Shapiro A (1988) Towards a unified theory of inequality constrained testing in multivariate analysis. Int Stat Rev 56:49–62
Visscher PM (2006) A note on the asymptotic distribution of likelihood ratio tests to test variance components. Twin Res Hum Genet 9:490–495
Wu H, Neale MC (in press) On the likelihood ratio tests in bivariate ACDE models. Psychometrika
Acknowledgments
This research is supported by the National Institute of Drug Abuse training grant R25DA026119 to the second author. We thank Gregory Carey, Sophie van der Sluis and Conor Dolan for their helpful comments that have led to the improvement of the style of this article.
Author information
Authors and Affiliations
Corresponding author
Additional information
Edited by Gitta Lubke.
Rights and permissions
About this article
Cite this article
Wu, H., Neale, M.C. Adjusted Confidence Intervals for a Bounded Parameter. Behav Genet 42, 886–898 (2012). https://doi.org/10.1007/s10519-012-9560-z
Received:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s10519-012-9560-z