Hypothesis testing in a mixture case-control model. (English) Zbl 1217.62186
Summary: We consider a problem of testing mixture proportions using two-sample data, one from group one and the other from a mixture of groups one and two with unknown proportion, \(\lambda \), for being in group two. Various statistical applications, including microarray studies, infectious epidemiological studies, case-control studies with contaminated controls, clinical trials allowing “nonresponders”, genetic studies for gene mutation, and fishery applications can be formulated in this setup. Under the assumption that the log ratio of probability (density) functions from the two groups is linear in the observations, we propose a generalized score test statistic to test the mixture proportion. Under some regularity conditions, it is shown that this statistic converges to a weighted chi-squared random variable under the null hypothesis of \(\lambda = 0\), where the weight depends only on the sampling fraction of both groups. The permutation method is used to provide more reliable finite sample approximation. Simulation results and two real data applications are presented.
MSC:
| 62P10 | Applications of statistics to biology and medical sciences; meta analysis |
| 62N03 | Testing in survival analysis and censored data |
| 65C60 | Computational problems in statistics (MSC2010) |
References:
| [1] | Anderson, Multivariate logistic compounds, Biometrika 66 pp 17– (1979) · Zbl 0399.62029 · doi:10.1093/biomet/66.1.17 |
| [2] | Begg, Methodological issues in studies of the treatment, diagnosis, and etiology of prostate cancer, Seminars in Oncology 21 pp 569– (1994) |
| [3] | Bender, On the distribution of spontaneous SCE in human peripheral blood lymphocytes, Mutation Research 281 pp 227– (1992) · doi:10.1016/0165-7992(92)90013-8 |
| [4] | Boos, Testing for a treatment effect in the presence of nonresponders, Biometrics 42 pp 191– (1986) · doi:10.2307/2531256 |
| [5] | Carrano, Mutagenicity: New Horizons in Genetic Toxicology pp 268– (1982) |
| [6] | Cox, New Developments in Survey Sampling pp 506– (1969) |
| [7] | Davies, Hypothesis testing when a nuisance parameter is present only under the alternative, Biometrika 64 pp 247– (1977) · Zbl 0362.62026 · doi:10.2307/2335690 |
| [8] | Davies, Hypothesis testing when a nuisance parameter is present only under the alternative, Biometrika 74 pp 33– (1987) · Zbl 0612.62023 |
| [9] | Devlin, Genomic control for association studies: A semiparametric test to detect excess-haplotype sharing, Biostatistics 1 pp 369– (2000) · Zbl 1089.62527 · doi:10.1093/biostatistics/1.4.369 |
| [10] | Durairajan, Robustness of locally most powerful invariant test for normal mixture model in control and treatment populations, Journal of Statistical Planning and Inference 52 pp 33– (1996) · Zbl 0852.62023 · doi:10.1016/0378-3758(95)00105-0 |
| [11] | Efron, Using specially designed exponential families for density estimation, Annals of Statistics 24 pp 2431– (1996) · Zbl 0878.62028 · doi:10.1214/aos/1032181161 |
| [12] | Ghosh, Genomic outlier profile analysis: Mixture models, null hypotheses, and nonparametric estimation, Biostatistics 10 pp 60– (2009) · doi:10.1093/biostatistics/kxn015 |
| [13] | Godley, Adjusted odds ratios under nondifferential misclassification: Application to prostate cancer, Journal of Clinical Epidemiology 52 pp 129– (1999) · doi:10.1016/S0895-4356(98)00152-8 |
| [14] | Good, Detection of a treatment effect when not all experimental subjects will respond to treatment, Biometrics 35 pp 483– (1979) · doi:10.2307/2530351 |
| [15] | Hall, Efficient nonparametric estimation of mixture proportions, Journal of the Royal Statistical Society, Series B 46 pp 465– (1984) · Zbl 0586.62050 |
| [16] | Hosmer, A comparison of iterative maximum likelihood estimates of the parameters of a mixture of two normal distributions under three types of sample, Biometrics 29 pp 761– (1973) · doi:10.2307/2529141 |
| [17] | Johnson, Two sample rank tests for detecting changes that occur in a small proportion of the treated population, Biometrics 43 pp 641– (1987) · Zbl 0623.62039 · doi:10.2307/2532001 |
| [18] | Kitua, Plasmodium falciparum malaria in the first year of life in an area of intense and perennial transmission, Tropical Medicine and International Health 1 pp 475– (1996) · doi:10.1046/j.1365-3156.1996.d01-89.x |
| [19] | Lancaster, Case-control studies with contaminated controls, Journal of Econometrics 71 pp 145– (1996) · Zbl 0842.62096 · doi:10.1016/0304-4076(94)01698-4 |
| [20] | LaPointe, Gene expression profiling identifies clinically relevant subtypes of prostate cancer, Proceedings of the National Academy of Sciences 101 pp 811– (2004) · doi:10.1073/pnas.0304146101 |
| [21] | Lemdani, Tests for genetic linkage and homogeneity, Biometrics 51 pp 1033– (1995) · Zbl 0867.62080 · doi:10.2307/2533002 |
| [22] | Liang, Hypothesis testing under mixture models, application to genetic linkage analysis, Biometrics 55 pp 65– (1999) · Zbl 1059.62514 · doi:10.1111/j.0006-341X.1999.00065.x |
| [23] | Lindsay, Mixture Models: Theory, Geometry and Applications (1995) · Zbl 1163.62326 |
| [24] | McLachlan, Mixture Models: Inference and Applications to Clustering (1988) · Zbl 0697.62050 |
| [25] | Murray, Estimation problems with data from a mixture, Applied Statistics 27 pp 325– (1978) · Zbl 0437.62036 · doi:10.2307/2347169 |
| [26] | Ott, Analysis of Human Genetic Linkage (1999) |
| [27] | Pearson, Contributions to the mathematical theory of evolution, Philosophical Transactions A 185 pp 71– (1893) |
| [28] | Pearson, Contributions to the mathematical theory of evolution. II. Skew variation in homogeneous material, Philosophical Transactions A 186 pp 342– (1895) |
| [29] | Prentice, Logistic disease incidence models and case-control studies, Biometrika 66 pp 403– (1979) · Zbl 0428.62078 · doi:10.1093/biomet/66.3.403 |
| [30] | Qin, Inferences for case-control and semiparametric two-sample density ratio models, Biometrika 85 pp 619– (1998) · Zbl 0954.62053 · doi:10.1093/biomet/85.3.619 |
| [31] | Qin, Empirical likelihood ratio based confidence intervals for mixture proportions, Annals of Statistics 27 pp 1368– (1999) · Zbl 0960.62048 · doi:10.1214/aos/1017938930 |
| [32] | Qin, A goodness of fit test for logistic regression models based on case-control data, Biometrika 84 pp 609– (1997) · Zbl 0888.62045 · doi:10.1093/biomet/84.3.609 |
| [33] | Qin, Quantifying the change of melanoma incidence by Breslow thickness, Biometrics 58 pp 665– (2002) · Zbl 1210.62202 · doi:10.1111/j.0006-341X.2002.00665.x |
| [34] | Rayner, Smooth Tests of Goodness of Fit (1989) · Zbl 0731.62064 |
| [35] | Smith, Attributable fraction estimates and case definitions for malaria in endemic areas, Statistics in Medicine 13 pp 2345– (1994) · doi:10.1002/sim.4780132206 |
| [36] | Titterington, Statistical Analysis of Finite Mixture Distributions (1985) · Zbl 0646.62013 |
| [37] | Van Wieringen, A test for partial differential expression, Journal of the American Statistical Association 103 pp 1039– (2008) · Zbl 1205.62189 · doi:10.1198/016214507000001319 |
| [38] | Vardi, Nonparametric estimation in the presence of length bias, The Annals of Statistics 10 pp 616– (1982) · Zbl 0491.62034 · doi:10.1214/aos/1176345802 |
| [39] | Vounatsou, Bayesian analysis of two-component mixture distributions applied to estimating malaria attributable fractions, Applied Statistics 47 pp 575– (1998) · Zbl 0911.62111 |
| [40] | White, Choice of test for comparing two groups, with particular application to skewed outcomes, Statistics in Medicine 22 pp 1205– (2003) · doi:10.1002/sim.1420 |
| [41] | Wilks, The large-sample distribution of the likelihood ratio for testing composite hypothesis, Annals of Mathematical Statistics 9 pp 60– (1938) · Zbl 0018.32003 · doi:10.1214/aoms/1177732360 |
| [42] | Zou, On empirical likelihood for a semiparametric mixture model, Biometrika 89 pp 61– (2002) · Zbl 0997.62095 · doi:10.1093/biomet/89.1.61 |
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.
