A Monte Carlo simulation study comparing linear regression, beta regression, variable-dispersion beta regression and fractional logit regression at recovering average difference measures in a two sample design

详细信息    查看全文

• 作者：Christopher Meaney ; Rahim Moineddin
• 关键词：Regression modelling ; Linear regression ; Beta regression ; Variable ; dispersion beta regression ; Fractional Logit regression ; Beta distribution ; Multinomial distribution ; Monte Carlo simulation
• 刊名：BMC Medical Research Methodology
• 出版年：2014
• 出版时间：December 2014
• 年：2014
• 卷：14
• 期：1
• 全文大小：616 KB
• 参考文献：1. Johnson, N, Kotz, S, Balakrishnan, N (1995) Continuous Univariate Distributions. Wiley, Hoboken, New Jersey
  2. Gupta, A, Nadarajah, S (2004) Handbook of Beta Distribution and its Applications. CRC Press, Boca Raton, Florida
  3. Paolino, P (2001) Maximum likelihood estimation of models with beta distributed dependent variables. Polit Anal 9: pp. 325-346 CrossRef
  4. Ferrari, S, Cribrari-Neto, F (2004) Beta regression for modelling rates and proportions. J Appl Stat 10: pp. 1-18
  5. Smithson, M, Verkuilen, J (2006) A better lemon squeezer? Maximum-likelihood regression with beta distributed dependent variables. Psychol Methods 11: pp. 54-71 CrossRef
  6. McCullagh, P, Nelder, J (1989) Generalized linear models. CRC Press, Boca Raton CrossRef
  7. Ferrari, S (2013) Beta Regression Modelling: Recent Advances and in Theory and Applications.
  8. Papke, L, Wooldridge, J (1996) Econometric methods for fractional response variables with an application to 401(K) plan participation rates. J Appl Econ 11: pp. 619-632 CrossRef
  9. Cox, C (1996) Non-linear quasi-likelihood models: applications to continuous proportions. Comput Stat Data Anal 21: pp. 449-461 CrossRef
  10. Weisberg, S (2005) Applied Linear Regression. Wiley, Hoboken, New Jersey CrossRef
  11. White, H (2000) Asymptotic Theory for Econometricians. Academic Press, San Diego, California
  12. Kosmidis, I, Firth, D (2010) A generic algorithm for reducing bias in parametric estimation. Electron J Stat 4: pp. 1097-1112 CrossRef
  13. Grun, B, Kosmidis, I, Zeileis, A (2012) Extended beta regression in R: shaken, stirred, mixed and partitioned. J Stat Softw 48: pp. 1-25
  14. Knight, K (2000) Mathematical Statistics. CRC Press, Boca Raton, Florida
  15. Wasserman, L (2004) All of Statistics: A Concise Course in Statistical Inference. Springer, New York, New York CrossRef
  16. White I: SIMSUM: analyses of simulation studies including Monte Carlo Error. / Stata J 10(3):369-85.
  R: A language and environment for statistical computing. R Foundation for Statistical Computing, Vienna, Austria
  17. SAS Institute North Carolina, USA; 2013.http://www.sas.com/en_us/legal/editorial-guidelines.html
  18. Zeileis, A (2004) Econometric computing with HC and HAC covariance matrix estimators. J Stat Softw 11: pp. 1-17
  19. Jackson, C (2011) Multi-state models for panel data: the msm package for R. J Stat Softw 38: pp. 1-29
  20. Kieschnick, R, McCullough, B (2003) Regression analysis of variates observed on (0,1): percentages, proportions and fractions. Stat Model 3: pp. 193-213 CrossRef
  21. Hunger, M, Beaumert, J, Holle, R (2011) Analysis of SF-6D index data: is beta regression appropriate?. Value Health 14: pp. 759-767 CrossRef
  22. Swearingen, C, Tilley, B, Adams, R, Rumboldt, Z, Nicholas, J, Bandyopadhyay, D, Woolson, R (2011) Application of beta regression to analyze ischemic stroke volume in NINDS rt-PA clinical trials. Methods in Neuroepidemiology 37: pp. 73-82 CrossRef
  23. The pre-publication history for this paper can be accessed here: http://www.biomedcentral.com/1471-2288/14/14/prepub
  
• 刊物主题：Theory of Medicine/Bioethics; Statistical Theory and Methods; Statistics for Life Sciences, Medicine, Health Sciences;
• 出版者：BioMed Central
• ISSN：1471-2288

文摘

Background In biomedical research, response variables are often encountered which have bounded support on the open unit interval - (0,1). Traditionally, researchers have attempted to estimate covariate effects on these types of response data using linear regression. Alternative modelling strategies may include: beta regression, variable-dispersion beta regression, and fractional logit regression models. This study employs a Monte Carlo simulation design to compare the statistical properties of the linear regression model to that of the more novel beta regression, variable-dispersion beta regression, and fractional logit regression models. Methods In the Monte Carlo experiment we assume a simple two sample design. We assume observations are realizations of independent draws from their respective probability models. The randomly simulated draws from the various probability models are chosen to emulate average proportion/percentage/rate differences of pre-specified magnitudes. Following simulation of the experimental data we estimate average proportion/percentage/rate differences. We compare the estimators in terms of bias, variance, type-1 error and power. Estimates of Monte Carlo error associated with these quantities are provided. Results If response data are beta distributed with constant dispersion parameters across the two samples, then all models are unbiased and have reasonable type-1 error rates and power profiles. If the response data in the two samples have different dispersion parameters, then the simple beta regression model is biased. When the sample size is small (N0-?N1--5) linear regression has superior type-1 error rates compared to the other models. Small sample type-1 error rates can be improved in beta regression models using bias correction/reduction methods. In the power experiments, variable-dispersion beta regression and fractional logit regression models have slightly elevated power compared to linear regression models. Similar results were observed if the response data are generated from a discrete multinomial distribution with support on (0,1). Conclusions The linear regression model, the variable-dispersion beta regression model and the fractional logit regression model all perform well across the simulation experiments under consideration. When employing beta regression to estimate covariate effects on (0,1) response data, researchers should ensure their dispersion sub-model is properly specified, else inferential errors could arise.