Autonomy

Aldrich, John

doi:10.1093/oxfordjournals.oep.a041889

Cited by 153 publications

(93 citation statements)

References 0 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The role of invariance in causal inference has received some attention in the literature (2,(32)(33)(34). To the best of our knowledge, however, the work in ref.…”

Section: Causal Inference Based On Invariance Across Experimentsmentioning

confidence: 99%

Methods for causal inference from gene perturbation experiments and validation

Meinshausen

Hauser

Mooij

et al. 2016

Proc. Natl. Acad. Sci. U.S.A.

120

114

View full text Add to dashboard Cite

Inferring causal effects from observational and interventional data is a highly desirable but ambitious goal. Many of the computational and statistical methods are plagued by fundamental identifiability issues, instability, and unreliable performance, especially for largescale systems with many measured variables. We present software and provide some validation of a recently developed methodology based on an invariance principle, called invariant causal prediction (ICP). The ICP method quantifies confidence probabilities for inferring causal structures and thus leads to more reliable and confirmatory statements for causal relations and predictions of external intervention effects. We validate the ICP method and some other procedures using large-scale genome-wide gene perturbation experiments in Saccharomyces cerevisiae. The results suggest that prediction and prioritization of future experimental interventions, such as gene deletions, can be improved by using our statistical inference techniques.interventional-observational data | invariant causal prediction | genome database validation | graphical models I n this article, we discuss statistical methods for causal inference from perturbation experiments. As this is a rather general topic, we focus on the following problem: based on data from observational and perturbation settings, we want to predict the effect and outcome of an unseen and new intervention or perturbation. Taking applications in genomics as an example, a typical task is as follows: based on observational data from wild-type organisms and interventional data from gene knockout or knockdown experiments, we want to predict the effect of a new gene knockout or knockdown on a phenotype of interest. For example, the organism is the model plant Arabidopsis thaliana, the gene knockouts correspond to mutant plants, and the phenotype of interest is the time it takes until the plant is flowering (1).From a methodological viewpoint, the prediction of unseen future interventions belongs to the area of causal inference where one aims to quantify presence and strength of causal effects among various variables. Loosely speaking, a causal effect is the effect of an external intervention (or say the response to a "What if I do?" question). The corresponding theory, e.g., using Pearl's do-operator (2), provides a link between causal effects and perturbations or randomized experiments. We mostly assume here that all of the variables in the causal model (for inferring causal effects) are observed: the case with hidden variables is mentioned only briefly in a later section, although it is an important theme in causal inference (due to the problem of hidden confounding variables) (cf. refs. 2 and 3).A popular and powerful route for causal modeling is given by structural equation models (SEMs) (2, 4). We consider a set of random variables X 1 , . . . , X p , X p+1 , and we often denote by Y = X 1 , emphasizing that Y is our response variable of interest (e.g., a phenotype of interest). The main building blocks of a SEM...

show abstract

“…The role of invariance in causal inference has received some attention in the literature (2,(32)(33)(34). To the best of our knowledge, however, the work in ref.…”

Section: Causal Inference Based On Invariance Across Experimentsmentioning

confidence: 99%

Methods for causal inference from gene perturbation experiments and validation

Meinshausen

Hauser

Mooij

et al. 2016

Proc. Natl. Acad. Sci. U.S.A.

120

114

View full text Add to dashboard Cite

show abstract

“…Yet, right before saying this, he uses parameter variation to argue that failures of faithfulness will be rare. He relies on Aldrich's (1989) notion of autonomy-the idea that particular structural equations in a causal model are invariant to changes in other structural equations. He writes that autonomy entails that the parameters in the equations:…”

Section: Coincidental Failures Of Faithfulnessmentioning

confidence: 99%

Faithfulness, Coordination and Causal Coincidences

Weinberger

2017

Erkenn

View full text Add to dashboard Cite

Within the causal modeling literature, debates about the Causal Faithfulness Condition (CFC) have concerned whether it is probable that the parameters in causal models will have values such that distinct causal paths will cancel. As the parameters in a model are fixed by the probability distribution over its variables, it is initially puzzling what it means to assign probabilities to these parameters. I propose that to assign a probability to a parameter in a model is to treat that parameter as a function of a variable in an augmented model. By combining this proposal with widely adopted principles regarding which variables must be included in a model, I argue that the various proposed counterexamples to CFC involving coordinated parameters are not genuine counterexamples. I then consider the cases in which CFC fails due not to coordination, but by coincidence, and propose explanatory and predictive bases for ruling out such coincidences without presuming that they are improbable. The aim of the proposed defenses is not to show that CFC never fails, but rather to argue that its use in a particular context may be defended using general modeling assumptions rather than by relying on claims about how often it fails.

show abstract

“…Correspondingly, [4] is an equality of RVs. By assumption, all RVs live on the same underlying probability space.…”

Section: Half-sibling Regressionmentioning

confidence: 99%

“…By assumption, all RVs live on the same underlying probability space. If we perform the associated random experiment, we obtain values for X and N, and [4] tells us that, if we substitute them into m and f, respectively, we get the same value with probability 1. Eq.…”

Section: Half-sibling Regressionmentioning

confidence: 99%

Modeling confounding by half-sibling regression

Schölkopf

Hogg

Wang

et al. 2016

Proc. Natl. Acad. Sci. U.S.A.

View full text Add to dashboard Cite

We describe a method for removing the effect of confounders to reconstruct a latent quantity of interest. The method, referred to as "half-sibling regression," is inspired by recent work in causal inference using additive noise models. We provide a theoretical justification, discussing both independent and identically distributed as well as time series data, respectively, and illustrate the potential of the method in a challenging astronomy application.machine learning | causal inference | astronomy | exoplanet detection | systematic error modeling W e assay a method for removing the effect of confounding noise, based on a hypothetical underlying causal structure. The method does not infer causal structures; rather, it is influenced by a recent thrust to try to understand how causal structures facilitate machine learning tasks (1).Causal graphical models as pioneered by (2, 3) are joint probability distributions over a set of variables X 1 , . . . , X n , along with directed graphs (usually, acyclicity is assumed) with vertices X i , and arrows indicating direct causal influences. By the causal Markov assumption, each vertex X i is independent of its nondescendants, given its parents.There is an alternative view of causal models, which does not start from a joint distribution. Instead, it assumes a set of jointly independent noise variables, one for each vertex, and a "structural equation" for each variable that describes how the latter is computed by evaluating a deterministic function of its noise variable and its parents (2, 4, 5). This view, referred to as a functional causal model (or nonlinear structural equation model), leads to the same class of joint distributions over all variables (2, 6), and we may thus choose either representation.The functional point of view is useful in that it often makes it easier to come up with assumptions on the causal mechanisms that are at work, i.e., on the functions associated with the variables. For instance, it was recently shown (7) that assuming nonlinear functions with additive noise renders the two-variable case identifiable (i.e., a case where conditional independence tests do not provide any information, and it was thus previously believed that it is impossible to infer the structure of the graph based on observational data).In this work we start from the functional point of view and assume the underlying causal graph shown in Fig. 1. In the present paper, N, Q, X, Y are random variables (RVs) defined on the same underlying probability space. We do not require the ranges of the RVs to be R, and, in particular, they may be vectorial; we use n, q, x, y as placeholders for the values these variables can take. All equalities regarding RVs should be interpreted to hold with probability one. We further (implicitly) assume the existence of conditional expectations.Note that, although the causal motivation was helpful for our work, one can also view Fig. 1 as a directed acyclic graph (DAG) without causal interpretation, i.e., as a directed graphical model. We need Q and X...

show abstract

Autonomy

Cited by 153 publications

References 0 publications

Methods for causal inference from gene perturbation experiments and validation

Methods for causal inference from gene perturbation experiments and validation

Faithfulness, Coordination and Causal Coincidences

Modeling confounding by half-sibling regression

Contact Info

Product

Resources

About