| 1. |
- Gorbach, Tetiana, 1991-, et al.
(författare)
-
A Hierarchical Bayesian Mixture Model Approach for Analysis of Resting-State Functional Brain Connectivity : An Alternative to Thresholding
- 2020
-
Ingår i: Brain Connectivity. - : Mary Ann Liebert. - 2158-0014 .- 2158-0022. ; 10:5, s. 202-211
-
Tidskriftsartikel (refereegranskat)abstract
- This article proposes a Bayesian hierarchical mixture model to analyze functional brain connectivity where mixture components represent "positively connected" and "non-connected" brain regions. Such an approach provides a data-informed separation of reliable and spurious connections in contrast to arbitrary thresholding of a connectivity matrix. The hierarchical structure of the model allows simultaneous inferences for the entire population as well as for each individual subject. A new connectivity measure, the posterior probability of a given pair of brain regions of a specific subject to be connected given the observed correlation of regions' activity, can be computed from the model fit. The posterior probability reflects the connectivity of a pair of regions relative to the overall connectivity pattern of an individual, which is overlooked in traditional correlation analyses. This article demonstrates that using the posterior probability might diminish the effect of spurious connections on inferences, which is present when a correlation is used as a connectivity measure. In addition, simulation analyses reveal that the sparsification of the connectivity matrix using the posterior probabilities might outperform the absolute thresholding based on correlations. Therefore, we suggest that posterior probability might be a beneficial measure of connectivity compared with the correlation. The applicability of the introduced method is exemplified by a study of functional resting-state brain connectivity in older adults.
|
|
| 2. |
- Gorbach, Tetiana, 1991-, et al.
(författare)
-
Contrasting Identifying Assumptions of Average Causal Effects : Robustness and Semiparametric Efficiency
- 2023
-
Ingår i: Journal of machine learning research. - : Microtome Publishing. - 1532-4435 .- 1533-7928. ; 24:197, s. 1-65
-
Tidskriftsartikel (refereegranskat)abstract
- Semiparametric inference on average causal effects from observational data is based on assumptions yielding identification of the effects. In practice, several distinct identifying assumptions may be plausible; an analyst has to make a delicate choice between these models. In this paper, we study three identifying assumptions based on the potential outcome framework: the back-door assumption, which uses pre-treatment covariates, the front-door assumption, which uses mediators, and the two-door assumption using pre-treatment covariates and mediators simultaneously. We provide the efficient influence functions and the corresponding semiparametric efficiency bounds that hold under these assumptions, and their combinations. We demonstrate that neither of the identification models provides uniformly the most efficient estimation and give conditions under which some bounds are lower than others. We show when semiparametric estimating equation estimators based on influence functions attain the bounds, and study the robustness of the estimators to misspecification of the nuisance models. The theory is complemented with simulation experiments on the finite sample behavior of the estimators. The results obtained are relevant for an analyst facing a choice between several plausible identifying assumptions and corresponding estimators. Our results show that this choice implies a trade-off between efficiency and robustness to misspecification of the nuisance models.
|
|
| 3. |
- Gorbach, Tetiana, 1991-
(författare)
-
Methods for longitudinal brain imaging studies with dropout
- 2019
-
Doktorsavhandling (övrigt vetenskapligt/konstnärligt)abstract
- One of the challenges in aging research is to understand the brain mechanisms that underlie cognitive development in older adults. Such aging processes are investigated in longitudinal studies, where the within-individual changes over time are observed. However, several methodological issues exist in longitudinal analyses. One of them is loss of participants to follow-up, which occurs when individuals drop out from the study. Such dropout should be taken into account for valid conclusions from longitudinal investigations, and this is the focus of this thesis. The developed methods are used to explore brain aging and its relation to cognition within the Betula longitudinal study of aging.Papers I and II consider the association between changes in brain structure and cognition. In the first paper, regression analysis is used to establish the statistical significance of brain-cognition associations while accounting for dropout. Paper II develops interval estimators directly for an association as measured by partial correlation, when some data are missing. The estimators of Paper II may be used in longitudinal as well as cross-sectional studies and are not limited to brain imaging. Papers III and IV study functional brain connectivity, which is the statistical dependency between the functions of distinct brain regions. Typically, only brain regions with associations stronger than a predefined threshold are considered connected. However, the threshold is often arbitrarily set and does not reflect the individual differences in the overall connectivity patterns. Paper III proposes a mixture model for brain connectivity without explicit thresholding of associations and suggests an alternative connectivity measure. Paper IV extends the mixture modeling of Paper III to a longitudinal setting with dropout and investigates the impact of ignoring the dropout mechanism on the quality of the inferences made on longitudinal connectivity changes.
|
|
| 4. |
- Moosavi, Niloofar, et al.
(författare)
-
A note on sensitivity analysis for post-machine learning causal inference
-
Annan publikation (övrigt vetenskapligt/konstnärligt)abstract
- In Moosavi et al. (2022) a sensitivity analysis method to unobserved confounding was proposed when estimating an average causal effect with a double robust estimator in high dimensional situations. For this purpose, it was assumed that linear models could sparselyapproximate the nuisance functions (treatment assignment and outcome models). In this note, we relax these assumptions making the sensitivity analysis more generally applicable, for instance when nuisance functions are (weakly) consistently estimated with machine learning algorithms. Simulations and a case study illustrate the performance and use of the method.
|
|
| 5. |
- Moosavi, Niloofar, et al.
(författare)
-
Valid causal inference: model selection and sensitivity to unobserved confounding in high-dimensional settings
-
Annan publikation (övrigt vetenskapligt/konstnärligt)abstract
- Recently, various methods have been proposed to estimate causal effects with confidence intervals that are uniformly valid over a set of data generating processes, when high-dimensional nuisance models are estimated by post-model selection or machine learning estimators. These methods typically require that all the confounders are observed to ensure identification of the effects. We contribute by showing how valid semiparametric inference can be obtained in the presence of unobserved confounders and high-dimensional nuisance models. We propose uncertainty intervals which allow for unobserved confounding, and show that the resulting inference is valid when the amount of unobserved confounding is small relative to the sample size; the latter is formalized in terms of convergence rates. Simulation experiments illustrate the finite sample properties of the proposed intervals and investigate an alternative procedure that improves the empirical coverage of the intervals when the amount of unobserved confounding is large.
|
|
