Beyond mean modelling: bias due to misspecification of dispersion in Poisson-inverse Gaussian regression. (English) Zbl 1419.62366
Summary: In clinical trials one traditionally models the effect of treatment on the mean response. The underlying assumption is that treatment affects the response distribution through a mean location shift on a suitable scale, with other aspects of the distribution (shape/dispersion/variance) remaining the same. This work is motivated by a trial in Parkinson’s disease patients in which one of the endpoints is the number of falls during a 10-week period. Inspection of the data reveals that the Poisson-inverse Gaussian (PiG) distribution is appropriate, and that the experimental treatment reduces not only the mean, but also the variability, substantially. The conventional analysis assumes a treatment effect on the mean, either adjusted or unadjusted for covariates, and a constant dispersion parameter. On our data, this analysis yields a non-significant treatment effect. However, if we model a treatment effect on both mean and dispersion parameters, both effects are highly significant. A simulation study shows that if a treatment effect exists on the dispersion and is ignored in the modelling, estimation of the treatment effect on the mean can be severely biased. We show further that if we use an orthogonal parametrization of the PiG distribution, estimates of the mean model are robust to misspecification of the dispersion model. We also discuss inferential aspects that are more difficult than anticipated in this setting. These findings have implications in the planning of statistical analyses for count data in clinical trials.
MSC:
| 62P10 | Applications of statistics to biology and medical sciences; meta analysis |
Keywords:
count data; dispersion modelling; parameter orthogonality; Poisson-inverse Gaussian regression; profile likelihood confidence intervalReferences:
| [1] | Barndorff‐Nielsen, O. (1978). Information and exponential families in statistical theory. Hoboken, NJ: John Wiley & Sons Ltd. · Zbl 0387.62011 |
| [2] | Canty, A., & Ripley, B. D. (2016). boot: Bootstrap R (S‐plus) functions. R package version 1.3‐18. |
| [3] | Cole, S. R., Chu, H., & Greenland, S. (2013). Maximum likelihood, profile likelihood, and penalized likelihood: A primer. American Journal of Epidemiology, 179(2), 252-260. |
| [4] | Cox, D. R., & Reid, N. (1987). Parameter orthogonality and approximate conditional inference. Journal of the Royal Statistical Society, Series B (Methodological), 49, 1-39. · Zbl 0616.62006 |
| [5] | Davison, A. C., & Hinkley, D. V. (1997). Bootstrap methods and their application. New York, NY: Cambridge University Press. · Zbl 0886.62001 |
| [6] | Dean, C., Lawless, J., & Willmot, G. (1989). A mixed Poisson‐inverse Gaussian regression model. Canadian Journal of Statistics, 17(2), 171-181. · Zbl 0679.62051 |
| [7] | Greenwood, M., & Yule, G. U. (1920). An inquiry into the nature of frequency distributions representative of multiple happenings with particular reference to the occurrence of multiple attacks of disease or of repeated accidents. Journal of the Royal Statistical Society, 83, 255-279. |
| [8] | Hauser, R. A., Heritier, S., Rowse, G. J., Hewitt, L. A., & Isaacson, S. H. (2016). Droxidopa and reduced falls in a trial of Parkinson disease patients with neurogenic orthostatic hypotension. Clinical Neuropharmacology, 39(5), 220-226. |
| [9] | Hilbe, J. M. (2011). Negative binomial regression (2nd ed.). New York, NY: Cambridge University Press. · Zbl 1269.62063 |
| [10] | Hollander, M., Wolfe, D. A., & Chicken, E. (2013). Nonparametric statistical methods. Hoboken, NJ: John Wiley & Sons. |
| [11] | Huber, P. J. (1967). The behavior of maximum likelihood estimates under nonstandard conditions. Proceedings of the Fifth Berkeley Symposium on Mathematical Statistics and Probability. Statistics (Vol. 1, pp. 221-233), Berkeley, CA: University of California Press. · Zbl 0212.21504 |
| [12] | Huzurbazar, V. S. (1950). Probability distributions and orthogonal parameters. Proceedings of the Cambridge Philosophical Society (Vol. 46, pp. 281-284). New York, NY: Cambridge University Press. · Zbl 0036.09304 |
| [13] | IBM Corp. (2013). IBM SPSS statistics for windows, version 22.0. Armonk, NY: Author. |
| [14] | Jørgensen, B. (1987). Exponential dispersion models. Journal of the Royal Statistical Society. Series B (Methodological), 49, 127-162. · Zbl 0662.62078 |
| [15] | Kneib, T. (2013). Beyond mean regression. Statistical Modelling, 13(4), 275-303. · Zbl 07257458 |
| [16] | Neuhäuser, M. (2011). Nonparametric statistical tests: A computational approach. Boca Raton, FL: CRC Press. |
| [17] | Ord, J. K., & Whitmore, G. A. (1986). The Poisson‐inverse Gaussian distribution as a model for species abundance. Communications in Statistics‐Theory and Methods, 15(3), 853-871. · Zbl 0603.62113 |
| [18] | R Core Team (2014). R: A language and environment for statistical computing. Vienna, AT: R Foundation for Statistical Computing. |
| [19] | Rigby, R., & Stasinopoulos, D. (2005). Generalized additive models for location, scale and shape. Journal of the Royal Statistical Society: Series C (Applied Statistics), 54(3), 507-554. · Zbl 1490.62201 |
| [20] | Rigby, R., Stasinopoulos, D., & Akantziliotou, C. (2008). A framework for modelling overdispersed count data, including the Poisson‐shifted generalized inverse Gaussian distribution. Computational Statistics & Data Analysis, 53(2), 381-393. · Zbl 1231.62019 |
| [21] | Royston, P. (2007). Profile likelihood for estimation and confidence intervals. Stata Journal, 7(3), 376-387. |
| [22] | SAS Institute Inc. (2011). SAS/STAT Software, Version 9.3. Cary, NC: Author. |
| [23] | Sichel, H. (1971). On a family of discrete distributions particularly suited to represent long‐tailed frequency data. Proceedings of the Third Symposium on Mathematical Statistics (pp. 51-97). Pretoria, SA: SACSIR. · Zbl 0274.60012 |
| [24] | Sichel, H. (1974). On a distribution representing sentence‐length in written prose. Journal of the Royal Statistical Society. Series A (General), 137, 25-34. |
| [25] | Sormani, M., Bruzzi, P., Rovaris, M., Barkhof, F., Comi, G., Miller, D., Filippi, M. (2001). Modelling new enhancing MRI lesion counts in multiple sclerosis. Multiple Sclerosis, 7(5), 298-304. |
| [26] | Stasinopoulos, M. D., Rigby, R. A., Heller, G. Z., Voudouris, V., & De Bastiani, F. (2017). Flexible Regression and Smoothing: Using GAMLSS in R. Boca Raton, FL: CRC Press. |
| [27] | Stein, G. Z., & Juritz, J. M. (1988). Linear models with an inverse Gaussian Poisson error distribution. Communications in Statistics—Theory and Methods, 17(2), 557-571. |
| [28] | Stein, G. Z., Zucchini, W., & Juritz, J. M. (1987). Parameter estimation for the Sichel distribution and its multivariate extension. Journal of the American Statistical Association, 82(399), 938-944. |
| [29] | Venzon, D., & Moolgavkar, S. (1988). A method for computing profile‐likelihood‐based confidence intervals. Journal of the Royal Statistical Society. Series C (Applied Statistics), 37(1), 87-94. |
| [30] | Willmot, G. E. (1987). The Poisson‐inverse Gaussian distribution as an alternative to the negative binomial. Scandinavian Actuarial Journal, 1987(3‐4), 113-127. |
| [31] | Woutersen, T. (2011). Missing data methods: Cross‐sectional methods and applications. In T. B.Fomby (ed.) & R.Hill (ed.) (Eds.), Consistent estimation and orthogonality (pp. 155-178). Bingley, UK: Emerald Group Publishing. · Zbl 1443.62037 |
| [32] | Young, G., & Smith, R. (2005). Negative binomial regression (2nd ed.). New York, NY: Cambridge University Press. |
| [33] | Zeileis, A. (2006). Object‐oriented computation of sandwich estimators. Journal of Statistical Software, 16(9), 1-16. |
| [34] | Zhou, X. H., & Dinh, P. (2005). Nonparametric confidence intervals for the one‐ and two‐sample problems. Biostatistics, 6(2), 187-200. · Zbl 1071.62042 |
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.
