Biased and unbiased estimation in longitudinal studies with informative visit processes. (English) Zbl 1390.62293
Summary: The availability of data in longitudinal studies is often driven by features of the characteristics being studied. For example, clinical databases are increasingly being used for research to address longitudinal questions. Because visit times in such data are often driven by patient characteristics that may be related to the outcome being studied, the danger is that this will result in biased estimation compared to designed, prospective studies. We study longitudinal data that follow a generalized linear mixed model and use a log link to relate an informative visit process to random effects in the mixed model. This device allows us to elucidate which parameters are biased under the informative visit process and to what degree. We show that the informative visit process can badly bias estimators of parameters of covariates associated with the random effects, while allowing consistent estimation of other parameters.
MSC:
| 62P10 | Applications of statistics to biology and medical sciences; meta analysis |
| 62M10 | Time series, auto-correlation, regression, etc. in statistics (GARCH) |
| 62J12 | Generalized linear models (logistic models) |
Keywords:
bias; missing not at random; mixed effects model; multiplicative link; generalized linear mixed modelReferences:
| [1] | Fitzmaurice, G. M., Laird, N. M., and Shneyer, L. (2001). An alternative parameterization of the general linear mixture model for longitudinal data with non‐ignorable drop‐outs. Statistics in Medicine20, 1009-1021. |
| [2] | Fitzmaurice, G. M., Lipsitz, S. R., Ibrahim, J. G., Gelber, R., and Lipshultz, S. (2006). Estimation in regression models for longitudinal binary data with outcome‐dependent follow‐up. Biostatistics7, 469-485. · Zbl 1170.62378 |
| [3] | Heckman, J. J. (1979). Sample selection bias as a specification error. Econometrica47, 153-161. · Zbl 0392.62093 |
| [4] | Kenward, M. G. (1998). Selection models for repeated measurements with non‐random dropout: An illustration of sensitivity. Statistics in Medicine23, 2723-32. |
| [5] | Lin, H., McCulloch, C. E., and Rosenheck, R. A. (2004). Latent pattern mixture models for informative intermittent missing data in longitudinal studies. Biometrics60, 295-305. · Zbl 1132.62362 |
| [6] | Lipsitz, S. R., Fitzmaurice, G. M., Ibrahim, J. G., Gelber, R., and Lipshultz, S. (2002). Parameter estimation in longitudinal studies with outcome‐dependent follow‐up. Biometrics58, 621-630. · Zbl 1210.62181 |
| [7] | Liu, L., Huang, X., and O’Quigley, J. (2008). Analysis of longitudinal data in the presence of informative observation times and a dependent terminal event, with application to medical cost data. Biometrics64, 321-327. |
| [8] | McCulloch, C., Searle, S., and Neuhaus, J. (2008). Generalized, Linear and Mixed Models, 2nd edition. New York: Wiley. · Zbl 1165.62050 |
| [9] | Neuhaus, J. M. and McCulloch, C. E. (2011). Estimation of covariate effects in generalised linear mixed models with informative cluster sizes. Biometrika98, 147-162. · Zbl 1214.62022 |
| [10] | PCORI (2014). Patient‐centered outcomes research institute cooperative agreement funding announcement: Improving infrastructure for conducting patient‐centered outcomes research (http://www.pcori.org/assets/pcori‐cdrn‐funding‐announcement‐042313.pdf). |
| [11] | Rathouz, P. J. (2004). Fixed effects models for longitudinal binary data with drop‐outs missing at random. Statistica Sinica14, 969-988. · Zbl 1073.62108 |
| [12] | Sun, J., Sun, L., and Liu, D. (2007). Regression analysis of longitudinal data in the presence of informative observation and censoring times. Journal of the American Statistical Association102, 1397-1406. · Zbl 1332.62383 |
| [13] | Sun, J., Tong, X., and He, X. (2007). Regression analysis of panel count data with dependent observation times. Biometrics63, 1053-1059. · Zbl 1146.62099 |
| [14] | Williamson, J., Datta, S., and Satten, G. (2003). Marginal analyses of clustered data when cluster size is informative. Biometrics59, 36-42. · Zbl 1210.62082 |
| [15] | Wulfsohn, M. S. and Tsiatis, A. A. (1997). A joint model for survival and longitudinal data measured with error. Biometrics53, 330-339. · Zbl 0874.62140 |
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.
