How many data clusters are in the Galaxy data set?
Tóm tắt
In model-based clustering, the Galaxy data set is often used as a benchmark data set to study the performance of different modeling approaches. Aitkin (Stat Model 1:287–304) compares maximum likelihood and Bayesian analyses of the Galaxy data set and expresses reservations about the Bayesian approach due to the fact that the prior assumptions imposed remain rather obscure while playing a major role in the results obtained and conclusions drawn. The aim of the paper is to address Aitkin’s concerns about the Bayesian approach by shedding light on how the specified priors influence the number of estimated clusters. We perform a sensitivity analysis of different prior specifications for the mixtures of finite mixture model, i.e., the mixture model where a prior on the number of components is included. We use an extensive set of different prior specifications in a full factorial design and assess their impact on the estimated number of clusters for the Galaxy data set. Results highlight the interaction effects of the prior specifications and provide insights into which prior specifications are recommended to obtain a sparse clustering solution. A simulation study with artificial data provides further empirical evidence to support the recommendations. A clear understanding of the impact of the prior specifications removes restraints preventing the use of Bayesian methods due to the complexity of selecting suitable priors. Also, the regularizing properties of the priors may be intentionally exploited to obtain a suitable clustering solution meeting prior expectations and needs of the application.
Tài liệu tham khảo
Aitkin M (2001) Likelihood and Bayesian analysis of mixtures. Stat Model 1(4):287–304. https://doi.org/10.1177/1471082x0100100404
Aitkin M, Anderson D, Hinde J (1981) Statistical modelling of data on teaching styles. J Royal Stat Soc A 144(4):419–461. https://doi.org/10.2307/2981826
Carlin BP, Chib S (1995) Bayesian model choice via Markov chain Monte Carlo methods. J Royal Stat Soc B 57:473–484. https://doi.org/10.1111/j.2517-6161.1995.tb02042.x
Crawford SL, DeGroot MH, Kadane JB, Small MJ (1992) Modeling lake-chemistry distributions: approximate Bayesian methods for estimating a finite-mixture model. Technometrics 34(4):441–453. https://doi.org/10.1080/00401706.1992.10484955
Dempster AP, Laird NM, Rubin DB (1977) Maximum likelihood from incomplete data via the EM algorithm. J Royal Stat Soc B 39(1):1–38. https://doi.org/10.1111/j.2517-6161.1977.tb01600.x
Escobar MD, West M (1995) Bayesian density estimation and inference using mixtures. J Am Stat Assoc 90(430):577–588. https://doi.org/10.1080/01621459.1995.10476550
Fraley C, Raftery AE (2002) Model-based clustering, discriminant analysis and density estimation. J Am Stat Assoc 97(458):611–631. https://doi.org/10.1198/016214502760047131
Frühwirth-Schnatter S (2006) Finite mixture and Markov switching models. Springer, New York
Frühwirth-Schnatter S, Malsiner-Walli G, Grün B (2020) Generalized mixtures of finite mixtures and telescoping sampling. arXiv:2005.09918
Greve J, Grün B, Malsiner-Walli G, Frühwirth-Schnatter S (2020) Spying on the prior of the number of data clusters and the partition distribution in Bayesian cluster analysis. arXiv:2012.12337
Grün B (2019) Model-based clustering. In: Frühwirth-Schnatter S, Celeux G, Robert CP (eds) Handbook of mixture analysis. Chapman and Hall/CRC, pp 157–192
Hennig C, Liao TF (2013) How to find an appropriate clustering for mixed-type variables with application to socio-economic stratification. J Royal Stat Soc C 62(3):309–369. https://doi.org/10.1111/j.1467-9876.2012.01066.x
Hothorn T, Everitt BS (2014) A handbook of statistical analyses using R, 3rd edn. Chapman and Hall/CRC, USA
Lunn D, Jackson C, Best N, Thomas A, Spiegelhalter D (2012) The BUGS book: a practical introduction to Bayesian analysis. Chapman and Hall/CRC, USA
Malsiner-Walli G, Frühwirth-Schnatter S, Grün B (2016) Model-based clustering based on sparse finite Gaussian mixtures. Stat Comput 26(1):303–324. https://doi.org/10.1007/s11222-014-9500-2
McCullagh P, Yang J (2008) How many clusters? Bayesian Anal 3(1):101–120. https://doi.org/10.1214/08-BA304
McLachlan GJ (1987) On bootstrapping the likelihood ratio test statistic for the number of components in a normal mixture. J Royal Stat Soc C 36(3):318–324
Miller JW, Harrison MT (2018) Mixture models with a prior on the number of components. J Am Stat Assoc 113(521):340–356. https://doi.org/10.1080/01621459.2016.1255636
Nobile A (2004) On the posterior distribution of the number of components in a finite mixture. The Ann Stat 32(5):2044–2073. https://doi.org/10.1214/009053604000000788
Phillips DB, Smith AFM (1996) Bayesian model comparison via jump diffusions. In: Gilks W, Richardson S, Spiegelhalter DJ (eds) Markov Chain Monte Carlo in Practice. Chapman & Hall, London, pp 215–239
Postman M, Huchra JP, Geller MJ (1986) Probes of large-scale structure in the Corona Borealis region. The Astron J 92(6):1238–1247. https://doi.org/10.1086/114257
Redner RA, Walker HF (1984) Mixture densities, maximum likelihood and the EM algorithm. SIAM Rev 26(2):195–239
Richardson S, Green PJ (1997) On Bayesian analysis of mixtures with an unknown number of components. J Royal Stat Soc B 59(4):731–792. https://doi.org/10.1111/1467-9868.00095
Roeder K (1990) Density estimation with confidence sets exemplified by superclusters and voids in galaxies. J Am Stat Assoc 85(411):617–624. https://doi.org/10.1080/01621459.1990.10474918
Roeder K, Wasserman L (1997) Practical Bayesian density estimation using mixtures of normals. J Am Stat Assoc 92(439):894–902. https://doi.org/10.1080/01621459.1997.10474044
Scrucca L, Fop M, Murphy TB, Raftery AE (2016) mclust 5: clustering, classification and density estimation using Gaussian finite mixture models. The R J 8(1):289–317. https://doi.org/10.32614/RJ-2016-021