Regression analyses of how state occupation probabilities or expected lengths of stay depend on covariates in multistate settings can be performed using the pseudo-observation method, which involves calculating jackknife pseudo-observations based on some estimator of the expected value of the outcome. In this article, we present a new command, stpmstate, that calculates such pseudo-observations based on the Aalen–Johansen estimator. We give examples of use of the command, and we conduct a small simulation study to offer insights into the pseudo-observation regression approach.
AalenO. O.JohansenS.1978. An empirical transition matrix for nonhomogeneous Markov chains based on censored observations. Scandinavian Journal of Statistics5: 141–150.
AndersenP. K.KleinJ. P.2007. Regression analysis for multistate models based on a pseudo-value approach, with applications to bone marrow transplantation studies. Scandinavian Journal of Statistics34: 3–16. https://doi.org/10.1111/j.1467-9469.2006.00526.x.
4.
AndersenP. K.KleinJ. P.RosthøjS.2003. Generalised linear models for correlated pseudo-observations, with applications to multi-state models. Biometrika90: 15–27. https://doi.org/10.1093/biomet/90.1.15.
5.
AndersenP. K.Pohar PermeM.2010. Pseudo-observations in survival analysis. Statistical Methods in Medical Research19: 71–99. https://doi.org/10.1177/0962280209105020.
6.
BinderN.GerdsT. A.AndersenP. K.2014. Pseudo-observations for competing risks with covariate dependent censoring. Lifetime Data Analysis20: 303–315. https://doi.org/10.1007/s10985-013-9247-7.
7.
CrowtherM. J.LambertP.2016. multistate: Stata module to perform multistate survival analysis. Statistical Software Components S458207, Department of Economics, Boston College. https://ideas.repec.org/c/boc/bocode/s458207.html.
8.
DattaS.SattenG. A.2001. Validity of the Aalen–Johansen estimators of stage occupation probabilities and Nelson–Aalen estimators of integrated transition hazards for non-Markov models. Statistics and Probability Letters55: 403–411. https://doi.org/10.1016/S0167-7152(01)00155-9.
9.
DattaS.SattenG. A.2002. Estimation of integrated transition hazards and stage occupation probabilities for non-Markov systems under dependent censoring. Biometrics58: 792–802. https://doi.org/10.1111/j.0006-341x.2002.00792.x.
10.
GillR. D.JohansenS.1990. A survey of product-integration with a view toward application in survival analysis. Annals of Statistics18: 1501–1555. https://doi.org/10.1214/aos/1176347865.
11.
GrandM. K.PutterH.2016. Regression models for expected length of stay. Statistics in Medicine35: 1178–1192. https://doi.org/10.1002/sim.6771.
12.
GrandM. K.PutterH.AllignolA.AndersenP. K.2019. A note on pseudoobservations and left-truncation. Biometrical Journal61: 290–298. https://doi.org/10.1002/bimj.201700274.
13.
GrawF.GerdsT. A.SchumacherM.2009. On pseudo-values for regression analysis in competing risks models. Lifetime Data Analysis15: 241–255. https://doi.org/10.1007/s10985-008-9107-z.
14.
JacobsenM.MartinussenT.2016. A note on the large sample properties of estimators based on generalized linear models for correlated pseudo-observations. Scandinavian Journal of Statistics43: 845–862. https://doi.org/10.1111/sjos.12212.
MaltzahnN.HoffR.AalenO. O.MehlumI. S.PutterH.GranJ. M.2020. A hybrid landmark Aalen–Johansen estimator for transition probabilities in partially non-Markov multi-state models. ArXiv Working Paper No. arXiv:2007.00974. https://arxiv.org/abs/2007.00974.
17.
NiesslA.AllignolA.MüllerC.BeyersmannJ.2020. Estimating state occupation and transition probabilities in non-Markov multi-state models subject to both random left-truncation and right-censoring. ArXiv Working Paper No. arXiv:2004.06514. https://arxiv.org/abs/2004.06514.
OvergaardM.AndersenP. K.ParnerE. T.2015. Regression analysis of censored data using pseudo-observations: An update. Stata Journal15: 809–821. https://doi.org/10.1177/1536867X1501500313.
20.
OvergaardM.ParnerE. T.PedersenJ.2017. Asymptotic theory of generalized estimating equations based on jack-knife pseudo-observations. Annals of Statistics45: 1988–2015. https://doi.org/10.1214/16-AOS1516.
21.
OvergaardM.ParnerE. T.PedersenJ.2018. Estimating the variance in a pseudo-observation scheme with competing risks. Scandinavian Journal of Statistics45: 923–940. https://doi.org/10.1111/sjos.12328.
22.
OvergaardM.ParnerE. T.PedersenJ.2019. Pseudo-observations under covariate-dependent censoring. Journal of Statistical Planning and Inference202: 112–122. https://doi.org/10.1016/j.jspi.2019.02.003.
ScheikeT. H.ZhangM.-J.2007. Direct modelling of regression effects for transition probabilities in multistate models. Scandinavian Journal of Statistics34: 17–32. https://doi.org/10.1111/j.1467-9469.2006.00544.x.
25.
ScheikeT. H.ZhangM.-J.GerdsT. A.2008. Predicting cumulative incidence probability by direct binomial regression. Biometrika95: 205–220. https://doi.org/10.1093/biomet/asm096.
26.
SpitoniC.LammensV.PutterH.2018. Prediction errors for state occupation and transition probabilities in multi-state models. Biometrical Journal60: 34–48. https://doi.org/10.1002/bimj.201600191.
27.
van HouwelingenH. C.PutterH.2008. Dynamic predicting by landmarking as an alternative for multi-state modeling: An application to acute lymphoid leukemia data. Lifetime Data Analysis14: 447–463. https://doi.org/10.1007/s10985-008-9099-8.
Supplementary Material
Please find the following supplemental material available below.
For Open Access articles published under a Creative Commons License, all supplemental material carries the same license as the article it is associated with.
For non-Open Access articles published, all supplemental material carries a non-exclusive license, and permission requests for re-use of supplemental material or any part of supplemental material shall be sent directly to the copyright owner as specified in the copyright notice associated with the article.
