Abstract
The problem of assessing the effect of a treatment on a marker in observational studies raises the difficulty that attribution of the treatment may depend on the observed marker values. As an example, we focus on the analysis of the effect of a HAART on CD4 counts, where attribution of the treatment may depend on the observed marker values. This problem has been treated using marginal structural models relying on the counterfactual/potential response formalism. Another approach to causality is based on dynamical models, and causal influence has been formalized in the framework of the Doob–Meyer decomposition of stochastic processes. Causal inference however needs assumptions that we detail in this paper and we call this approach to causality the “stochastic system” approach. First we treat this problem in discrete time, then in continuous time. This approach allows incorporating biological knowledge naturally. When working in continuous time, the mechanistic approach involves distinguishing the model for the system and the model for the observations. Indeed, biological systems live in continuous time, and mechanisms can be expressed in the form of a system of differential equations, while observations are taken at discrete times. Inference in mechanistic models is challenging, particularly from a numerical point of view, but these models can yield much richer and reliable results.
Similar content being viewed by others
References
Aalen OO (1987) Dynamic modelling and causality. Scand Actuar J 1987(3–4):177–190
Aalen OO, Røysland K, Gran JM, Ledergerber B (2012) Causality, mediation and time: a dynamic viewpoint. J R Stat Soc: Ser A (Stat Soc) 175(4):831–861
Andersen P, Borgan O, Gill R, Keiding N (1993) Statistical models based on counting processes. Springer, New York
Arjas E (2012) Causal inference from observational data: a bayesian predictive approach. In: Berzuini C, Dawid P, Bernadinelli L (eds) Causality: statistical perspectives and applications, p 71–84
Arjas E, Parner J (2004) Causal reasoning from longitudinal data*. Scand J Stat 31(2):171–187
Cole S, Hernán M, Anastos K, Jamieson B, Robins J (2007) Determining the effect of highly active antiretroviral therapy on changes in human immunodeficiency virus type 1 rna viral load using a marginal structural left-censored mean model. Am J Epidemiol 166(2):219–227
Cole SR, Hernán MA, Margolick JB, Cohen MH, Robins JM (2005) Marginal structural models for estimating the effect of highly active antiretroviral therapy initiation on CD4 cell count. Am J Epidemiol 162(5):471–478
Cole SR, Jacobson LP, Tien PC, Kingsley L, Chmiel JS, Anastos K (2010) Using marginal structural measurement-error models to estimate the long-term effect of antiretroviral therapy on incident AIDS or death. Am J Epidemiol 171(1):113–122. doi:10.1093/aje/kwp329
Commenges D, Gégout-Petit A (2009) A general dynamical statistical model with causal interpretation. J R Stat Soc Ser B (Stat Methodol) 71(3):719–736
Commenges D, Joly P, Gégout-Petit A, Liquet B (2007) Choice between semi-parametric estimators of markov and non-markov multi-state models from coarsened observations. Scand J Stat 34(1):33–52
Delattre M, Genon-Catalot V, Samson A (2013) Maximum likelihood estimation for stochastic differential equations with random effects. Scand J Stat 40(2):322–343
Didelez V (2008) Graphical models for marked point processes based on local independence. J R Stat Soc Ser B (Stat Methodol) 70(1):245–264
Eichler M, Didelez V (2010) On Granger causality and the effect of interventions in time series. Lifetime Data Anal 16:3–32
Gégout-Petit A, Commenges D (2010) A general definition of influence between stochastic processes. Lifetime Data Anal 16(1):33–44
Goldstein M et al (2006) Subjective bayesian analysis: principles and practice. Bayesian Anal 1(3):403–420
Granger CWJ (1969) Investigating causal relations by econometric models and cross-spectral methods. Econometrica 37(3):424
Guedj J, Thiébaut R, Commenges D (2007) Maximum likelihood estimation in dynamical models of HIV. Biometrics 63(4):1198–1206
Hernán MA, Brumback Ba, Robins JM (2002) Estimating the causal effect of zidovudine on CD4 count with a marginal structural model for repeated measures. Stat Med 21:1689–1709
Parner J, Arjas E (1999) Causal reasoning from longitudinal data. Rolf Nevanlinna Inst., University of Helsinki, Helsinki
Pearl J (2000) Causality: models, reasoning, and inference. MIT press, Cambridge
Picchini U, Gaetano A, Ditlevsen S (2010) Stochastic differential mixed-effects models. Scand J Stat 37(1):67–90
Prague M, Commenges D, Drylewicz J, Thiébaut R (2012) Treatment monitoring of hiv-infected patients based on mechanistic models. Biometrics 68:902–911
Prague M, Commenges D, Guedj J, Drylewicz J, Thiébaut R (2013) NIMROD: a program for inference via normal approximation of the posterior in models with random effects based on ordinary differential equations. Comput Methods Progr Biomed 111:447–458
Roberts GO, Stramer O (2001) On inference for partially observed nonlinear diffusion models using the metropolis-hastings algorithm. Biometrika 88(3):603–621
Robins J (1994) Correcting for non-compliance in randomized trials using structural nested mean models. Commun Stat-Theory Methods 23(8):2379–2412
Robins JM, Hernán MA, Brumback B (2000) Marginal structural models and causal inference in epidemiology. Epidemiology (Cambridge, Mass) 11(5):550–560
Røysland K (2011) A martingale approach to continuous-time marginal structural models. Bernoulli 17(3):895–915
Schweder T (1970) Composable markov processes. J Appl Prob 7(2):400–410
Williams D (1991) Probability with martingales. Cambridge University Press, Cambridge
Wu H (2005) Statistical methods for HIV dynamic studies in AIDS clinical trials. Stat Methods Med Res 14(2):171–192
Acknowledgments
We thank Mélanie Prague and Rodolphe Thiébaut for helpful exchanges on the topic of this paper.
Author information
Authors and Affiliations
Corresponding author
Appendix
Appendix
1.1 Proof of Lemma 1
The proof can be made by induction. The result holds for \(t=1\) since \(f^1_{\bar{V}_{0}|\bar{A}_{0},\bar{Y}_{0}}=f^2_{\bar{V}_{0}|\bar{A}_{0},\bar{Y}_{0}}=f_{V_0}\). Assuming \(f^1_{\bar{V}_{t-1}|\bar{A}_{t-1},\bar{Y}_{t-1}}=f^2_{\bar{V}_{t-1}|\bar{A}_{t-1},\bar{Y}_{t-1}}\), we prove that we have \(f^1_{\bar{V}_{t}|\bar{A}_{t},\bar{Y}_{t}}=f^2_{V_{t}|\bar{A}_{t},\bar{Y}_{t}}\).
We have first that \(f^1_{\bar{V}_{t}|\bar{A}_{t},\bar{Y}_{t}}= f^1_{V_t|\bar{V}_{t-1}} f^1_{\bar{V}_{t-1}|\bar{A}_{t},\bar{Y}_{t}}\) (because and ). Using the decomposition \((\bar{A}_{t},\bar{Y}_{t})=(Y_t,A_t,\bar{A}_{t-1},\bar{Y}_{t-1})\) and letting all densities conditioned on \((\bar{A}_{t-1},\bar{Y}_{t-1})\), we have from Bayes theorem:
Next, we have \(f^1_{Y_t,A_t|\bar{A}_{t-1},\bar{V}_{t-1},\bar{Y}_{t-1}}=f^1_{A_t|\bar{A}_{t-1},\bar{V}_{t-1},\bar{Y}_{t}}f^1_{Y_t|\bar{A}_{t-1},\bar{V}_{t-1},\bar{Y}_{t-1}}\). Because we have that \(A_t \perp \perp _{\bar{A}_{t-1},\bar{Y}_t} \bar{V}_{t-1}\). Thus \(f^1_{A_t|\bar{A}_{t-1},\bar{V}_{t-1},\bar{Y}_{t}}=f^1_{A_t|\bar{A}_{t-1},\bar{Y}_{t-1}}\). Since this term does not depend on \(\bar{v}_{t-1}\) it can be taken out of the integral in the denominator and deleted from numerator and denominator. It is easy to see that all the other terms are equal under \({\mathrm{P}}^1\) and \({\mathrm{P}}^2\) using the assumptions of the Lemma and our inductive assumption. Hence the Lemma.
Rights and permissions
About this article
Cite this article
Commenges, D., Gégout-Petit, A. The stochastic system approach for estimating dynamic treatments effect. Lifetime Data Anal 21, 561–578 (2015). https://doi.org/10.1007/s10985-015-9322-3
Received:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s10985-015-9322-3