Causal inference from data. On some inadequacy problems of structures with hidden causes

PROBLEMS IN PROGRAMMING ◽

10.15407/pp2020.02-03.392 ◽

2020 ◽

pp. 392-406

Author(s):

O.S. Balabanov ◽

Keyword(s):

Causal Inference ◽

Hidden Variables ◽

Edge Orientation ◽

Model Adequacy ◽

Sample Bias ◽

Model Inadequacy

The reliability of causal inference from data (by independence-based methods) is analyzed. We uncover some mechanisms which may result in model inadequacy due to sample bias and hidden variables. We detect some specific problems in recognition of direction of influence when some causes are hidden. Incorrectness of known rule for edge orientation (under causal insufficiency) is revealed. We suggest the correction to the rule aiming to retain model adequacy.

Download Full-text

Checking Model Adequacy for Count Time Series by Using Pearson Residuals

Journal of Time Series Econometrics ◽

10.1515/jtse-2018-0018 ◽

2019 ◽

Vol 0 (0) ◽

Cited By ~ 2

Author(s):

Christian Weiß ◽

Lukas Scherer ◽

Boris Aleksandrov ◽

Martin Feld

Keyword(s):

Time Series ◽

Real Data ◽

Model Fit ◽

Time Series Models ◽

Theoretical Discussion ◽

Count Time Series ◽

Model Adequacy ◽

Pearson Residuals ◽

Model Inadequacy ◽

The U.S

Abstract After having fitted a model to a given count time series, one has to check the adequacy of this model fit. The (standardized) Pearson residuals, being easy to compute and interpret, are a popular diagnostic approach for this purpose. But which types of model inadequacy might be uncovered by which statistics based on the Pearson residuals? In view of being able to apply such statistics in practice, it is also crucial to ask for the properties of these statistics under model adequacy. We look for answers to these questions by means of a comprehensive simulation study, which considers diverse types of count time series models and inadequacy scenarios. We illustrate our findings with two real-data examples about strikes in the U.S., and about corporate insolvencies in the districts of Rhineland–Palatinate. We conclude with a theoretical discussion of Pearson residuals.

Download Full-text

Beyond metaphors and semantics: A framework for causal inference in neuroscience

Behavioral and Brain Sciences ◽

10.1017/s0140525x19001389 ◽

2019 ◽

Vol 42 ◽

Author(s):

Roberto A. Gulli

Keyword(s):

Causal Inference ◽

Causal Power

Abstract The long-enduring coding metaphor is deemed problematic because it imbues correlational evidence with causal power. In neuroscience, most research is correlational or conditionally correlational; this research, in aggregate, informs causal inference. Rather than prescribing semantics used in correlational studies, it would be useful for neuroscientists to focus on a constructive syntax to guide principled causal inference.

Download Full-text