×

Frequentist-Bayes lack-of-fit tests based on Laplace approximations. (English) Zbl 1211.62047

Summary: The null hypothesis that all of a function’s Fourier coefficients are 0 is tested in a frequentist fashion using as test statistic a Laplace approximation to the posterior probability of the null hypothesis. Testing whether or not a regression function has a prescribed linear form is one application of such a test. In contrast to BIC, the Laplace approximation depends on prior probabilities, and hence allows the investigator to tailor the test to particular kinds of alternative regression functions. On the other hand, using diffuse priors produces new omnibus lack-of-fit statistics.
The new omnibus test statistics are weighted sums of exponentiated squared (and normalized) Fourier coefficients, where the weights depend on prior probabilities. Exponentiation of the Fourier components leads to tests that can be exceptionally powerful against high frequency alternatives. Evidence to this effect is provided by a comprehensive simulation study, in which one new test that had good power at high frequencies also performed comparably to some other well-known omnibus tests at low frequency alternatives.

MSC:

62F15 Bayesian inference
62F03 Parametric hypothesis testing
62E20 Asymptotic distribution theory in statistics
62G08 Nonparametric regression and quantile regression
65C60 Computational problems in statistics (MSC2010)

Software:

POLE
PDFBibTeX XMLCite
Full Text: DOI

References:

[1] Aerts, M.; Claeskens, G.; Hart, JD, Testing the fit of a parametric function, J. Amer. Statist. Assoc., 94, 869-879 (1999) · Zbl 0996.62044
[2] Aerts, M.; Claeskens, G.; Hart, JD, Testing lack of fit in multiple regression, Biometrika, 87, 405-424 (2000) · Zbl 0948.62028
[3] Aerts, M.; Claeskens, G.; Hart, JD, Bayesian-motivated tests of function fit and their asymptotic frequentist properties, Ann. Statist., 32, 2580-2615 (2004) · Zbl 1068.62053
[4] Baraud, Y.; Huet, S.; Laurent, B., Adaptive tests of linear hypotheses by model selection, Ann. Statist., 31, 225-251 (2003) · Zbl 1018.62037
[5] Bayarri, M. J.; Berger, JO, The interplay of Bayesian and frequentist analysis, Statist. Sci., 19, 58-80 (2004) · Zbl 1062.62001
[6] Bickel, PJ; Ritov, Y.; Stoker, TM, Tailor-made tests for goodness-of-fit to semiparametric hypotheses, Ann. Statist., 34, 721-741 (2006) · Zbl 1092.62050
[7] Bogdan, M., Data driven versions of Neyman’s test for uniformity based on a Bayesian rule, J. Statist. Comput. Simul., 68, 203-222 (2001) · Zbl 1172.62304
[8] Buckley, MJ, Detecting a smooth signal: optimality of cusum based procedures, Biometrika, 78, 253-262 (1991)
[9] Chang, M.; Chow, SC, A hybrid Bayesian adaptive design for dose response trials, J. Biopharma-ceutical Statist., 15, 677-691 (2005)
[10] Claeskens, G.; Hjort, NL, Goodness of fit via nonparametric likelihood ratios, Scandinavian Journal of Statistics, 31, 487-513 (2004) · Zbl 1065.62056
[11] Cline, D., 1983. Infinite series of random variables with regularly varying tails. Technical Report #83-24, University of British Columbia, Institute of Applied Mathematics and Statistics, http://www.stat.tamu.edu/ dcline/papers/infiniteseries.pdf.
[12] Cole, G.M., 1997. Water Boundaries. Wiley & Sons, Inc., New York.
[13] Conrad, J.; Botner, O.; Hallgren, A.; Pérez de los Heros, C., Including systematic uncertainties in confidence interval construction for poisson statistics (2003)
[14] De Bruijn, N.G., 1970. Asymptotic Methods in Analysis. North-Holland, Amsterdam.
[15] Dette, H.; Munk, A., Validation of linear regression models, Ann. Statist., 26, 778-800 (1998) · Zbl 0930.62041
[16] Dette, H., A consistent test for the functional form of a regression based on a difference of variance estimators, Ann. Statist., 27, 1012-1040 (1999) · Zbl 0957.62036
[17] Dümbgen, L.; Spokoiny, VG, Multiscale testing in the nonlinear structural errors-in-variables model, Ann. Statist., 29, 124-152 (2001) · Zbl 1029.62070
[18] Eubank, RL, Testing for no effect by cosine series methods, Scandinavian Journal of Statistic, 27, 747-763 (2000) · Zbl 0962.62031
[19] Eubank, RL; Hart, JD, Commonality of cusum, von Neumann and smoothing-based goodness-of-fit tests, Biometrika, 80, 89-98 (1993) · Zbl 0792.62042
[20] Fan, J.; Huang, LS, Goodness-of-fit tests for parametric regression models, J. Amer. Statist. Assoc., 96, 640-652 (2001) · Zbl 1017.62014
[21] Fan, J.; Zhang, C.; Zhang, J., Generalized likelihood ratio statistics and Wilks phenomenon, Ann. Statist., 29, 153-193 (2001) · Zbl 1029.62042
[22] Good, IJ, Saddle-point methods for the multinomial distribution, Ann. Math. Statist., 28, 861-881 (1957) · Zbl 0091.14302
[23] Guerre, E.; Lavergne, P., Data-driven rate-optimal specification testing in regression models, Ann. Statist., 33, 840-870 (2005) · Zbl 1068.62055
[24] Hall, P.; Kay, JW; Titterington, DM, Asymptotically optimal difference-based estimation of variance in nonparametric regression, Biometrika, 77, 521-528 (1990) · Zbl 1377.62102
[25] Hart, J.D., 1997. Nonparametric Smoothing and Lack-of-Fit Tests. Springer-Verlag, New York. · Zbl 0886.62043
[26] Horowitz, JL; Spokoiny, VG, An adaptive, rate-optimal test of a parametric mean-regression model against a nonparametric alternative, Econometrica, 69, 599-631 (2001) · Zbl 1017.62012
[27] Inglot, T.; Ledwina, T., Asymptotic optimality of data driven Neyman’s tests, Ann. Statist., 24, 1982-2019 (1996) · Zbl 0905.62044
[28] Inglot, T.; Ledwina, T., Data driven score tests for a homoscedastic linear regression model: asymptotic results, Probability and Mathematical Statistics, 26, 41-61 (2006) · Zbl 1104.62051
[29] Janssen, A., Global power functions of goodness of fit tests, Ann. Statist., 28, 239-253 (2000) · Zbl 1106.62329
[30] Kallenberg, WCM, Intermediate efficiency, theory and examples, Ann. Statist., 11, 170-182 (1983) · Zbl 0512.62057
[31] Kallenberg, WCM, The penalty in data driven Neyman’s tests, Mathematical Methods of Statistics, 11, 323-340 (2002)
[32] Kass, RE; Raftery, AE, Bayes factors, J. Amer. Statist. Assoc., 90, 773-795 (1995) · Zbl 0846.62028
[33] Kass, RE; Wasserman, L., A reference Bayesian test for nested hypotheses and its relationship to the schwarz criterion, J. Amer. Statist. Assoc., 90, 928-934 (1995) · Zbl 0851.62020
[34] Kuchibhatla, M.; Hart, JD, Smoothing-based lack-of-fit tests: variations on a theme, J. Nonparametr. Statist., 7, 1-22 (1996) · Zbl 0877.62041
[35] Ledwina, T., Data-driven version of Neyman’s smooth test of fit, J. Amer. Statist. Assoc., 89, 1000-1005 (1994) · Zbl 0805.62022
[36] Lee, G.; Hart, JD, Model selection criteria with data dependent penalty, with application to data-driven Neyman smooth tests, Nonparametric Statistics, 12, 683-707 (2000) · Zbl 1056.62519
[37] Lehmann, E., 1959. Testing Statistical Hypotheses. John Wiley & Sons, New York. · Zbl 0089.14102
[38] Lucito, R.; West, J.; Reiner, A.; Alexander, D.; Esposito, D.; Mishra, B.; Powers, S.; Norton, L.; Wigler, M., Detecting gene copy number fluctuations in tumor cells by microarray analysis of genomic representations, Genome Research, 10, 1726-1736 (2000)
[39] Mallows, CL, Some comments on cp, Technometrics, 15, 661-675 (1973) · Zbl 0269.62061
[40] Neyman, J., ‘Smooth’ test for goodness of fit, Skandinavisk Aktuarietidskrift, 20, 149-199 (1937) · JFM 63.1092.02
[41] Ogden, R.T., 1997. Essential Wavelets for Statistical Applications and Data Analysis. Birkhäuser, Boston. · Zbl 0868.62033
[42] Rayner, J.C.W., Best, D.J., 1989. Smooth Tests of Goodness of Fit. Oxford University Press, New York. · Zbl 0731.62064
[43] Snijders, A.; Nowak, N.; Segraves, R.; Blackwood, S.; Brown, N.; Conroy, J.; Hamilton, G.; Hindle, A.; Huey, B.; Kimura, K.; Law, S.; Myambo, K.; Palmer, J.; Ylstra, B.; Yue, J.; Gray, J.; Jain, A.; Pinkel, D.; Albertson, D., Assembly of microarrays for genome-wide measurement of DNA copy number, Nature Genetics, 29, 263-264 (2001)
[44] Spokoiny, VG, Adaptive hypothesis testing using wavelets, Ann. Statist., 24, 2477-2498 (1996) · Zbl 0898.62056
[45] Stute, W., Nonparametric model checks for regression, Ann. Statist., 25, 613-641 (1997) · Zbl 0926.62035
[46] Tierney, L.; Kadane, JB, Accurate approximations for posterior moments and marginal densities, J. Amer. Statist. Assoc., 81, 82-86 (1986) · Zbl 0587.62067
[47] Verdinelli, I.; Wasserman, L., Bayesian goodness-of-fit testing using infinite-dimensional exponential families, Ann. Statist., 26, 1215-1241 (1998) · Zbl 0930.62027
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.