Causal inference using invariant prediction: identification and confidence intervals

نویسندگان

  • Jonas Peters
  • Peter Bühlmann
  • Nicolai Meinshausen
چکیده

What is the difference of a prediction that is made with a causal model and a non-causal model? Suppose we intervene on the predictor variables or change the whole environment. The predictions from a causal model will in general work as well under interventions as for observational data. In contrast, predictions from a non-causal model can potentially be very wrong if we actively intervene on variables. Here, we propose to exploit this invariance of a prediction under a causal model for causal inference: given different experimental settings (for example various interventions) we collect all models that do show invariance in their predictive accuracy across settings and interventions. The causal model will be a member of this set of models with high probability. This approach yields valid confidence intervals for the causal relationships in quite general scenarios. We examine the example of structural equation models in more detail and provide sufficient assumptions under which the set of causal predictors becomes identifiable. We further investigate robustness properties of our approach under model misspecification and discuss possible extensions. The empirical properties are studied for various data sets, including large-scale gene perturbation experiments.

برای دانلود متن کامل این مقاله و بیش از 32 میلیون مقاله دیگر ابتدا ثبت نام کنید

ثبت نام

اگر عضو سایت هستید لطفا وارد حساب کاربری خود شوید

منابع مشابه

Comments on “Causal inference using invariant prediction: identification and confidence intervals” by Peters, Bühlmann and Meinshausen

I consider that the genuine fundamental problem of causal inference is the need for (partially untestable) invariance assumptions to operationalize interventions, and I thank the authors for emphasizing the role of invariances in a stimulating paper. I would like to make some brief comments on how the ideas introduced here can also be helpful in the context of measurement problems. Much of the ...

متن کامل

Causal Inference for Binary Data with Interference

Joseph Rigdon: Causal Inference for Binary Data with Interference (Under the direction of Michael Hudgens) Developing methods to quantify the effects of interventions to prevent infectious diseases in the presence of interference is the overall objective of this research. Interference is present when an individual’s outcome is affected by the treatment of any other individuals under study. Firs...

متن کامل

Methods for causal inference from gene perturbation experiments and validation.

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 large-scale systems with many measured variables. We present software and provide some validation of a recently developed methodol...

متن کامل

Inference on Pr(X > Y ) Based on Record Values From the Power Hazard Rate Distribution

In this article, we consider the problem of estimating the stress-strength reliability $Pr (X > Y)$ based on upper record values when $X$ and $Y$ are two independent but not identically distributed random variables from the power hazard rate distribution with common scale parameter $k$. When the parameter $k$ is known, the maximum likelihood estimator (MLE), the approximate Bayes estimator and ...

متن کامل

Causal Inference with Interference

LAN LIU: Causal Inference with Interference (Under the direction of Dr. Michael G. Hudgens) Recently, increasing attention has focused on making causal inference when interference is possible, i.e., when the potential outcomes of one individual may be affected by the treatment (or exposure) of other individuals. For example, in infectious diseases, whether one individual becomes infected may de...

متن کامل

ذخیره در منابع من


  با ذخیره ی این منبع در منابع من، دسترسی به آن را برای استفاده های بعدی آسان تر کنید

برای دانلود متن کامل این مقاله و بیش از 32 میلیون مقاله دیگر ابتدا ثبت نام کنید

ثبت نام

اگر عضو سایت هستید لطفا وارد حساب کاربری خود شوید

عنوان ژورنال:

دوره   شماره 

صفحات  -

تاریخ انتشار 2015