Bounding Causal Effects in Ecological Inference Problems

2015 ◽  
Author(s):  
Alejandro Corvalan ◽  
Emerson Melo ◽  
Robert P Sherman ◽  
Matthew Shum
Keyword(s):  
Causal Effects ◽  
Ecological Inference ◽  
Inference Problems

Bounding Causal Effects in Ecological Inference Problems

2016 ◽  
Vol 5 (3) ◽  
pp. 555-565
Author(s):  
Alejandro Corvalan ◽  
Emerson Melo ◽  
Robert Sherman ◽  
Matt Shum
Keyword(s):  
Voter Turnout ◽  
Causal Effect ◽  
Data Sources ◽  
Causal Effects ◽  
Ecological Inference ◽  
Ecological Data ◽  
Causal Inferences ◽  
Inference Problems ◽  
Electoral Law ◽  
Made In

This note illustrates a new method for making causal inferences with ecological data. We show how to combine aggregate outcomes with individual demographics from separate data sources to make causal inferences about individual behavior. In addressing such problems, even under the selection on observables assumption often made in the treatment effects literature, it is not possible to identify causal effects of interest. However, recent results from the partial identification literature provide sharp bounds on these causal effects. We apply these bounds to data from Chilean mayoral elections that straddle a 2012 change in Chilean electoral law from compulsory to voluntary voting. Aggregate voting outcomes are combined with individual demographic information from separate data sources to determine the causal effect of the change in the law on voter turnout. The bounds analysis reveals that voluntary voting decreased expected voter turnout, and that other causal effects are overstated if the bounds analysis is ignored.

Iterative Approaches to R × C Ecological Inference Problems: Where They Can Go Wrong and One Quick Fix

2004 ◽  
Vol 12 (2) ◽  
pp. 143-159 ◽  
Author(s):  
Karen E. Ferree
Keyword(s):  
South Africa ◽  
South African ◽  
Original Data ◽  
Aggregation Bias ◽  
Iterative Approach ◽  
South African Context ◽  
Ecological Inference ◽  
Inference Problems ◽  
African Context

This article argues that a key step in King's iterative approach to R × C ecological inference problems—the aggregation of groups into broad conglomerate categories—can introduce problems of aggregation bias and multimodality into data, inducing model violations. As a result, iterative EI estimates can be considerably biased, even when the original data conform to the assumptions of the model. I demonstrate this problem intuitively and through simulations, show the conditions under which it is likely to arise, and illustrate it with the example of Coloured voting during the 1994 elections in South Africa. I then propose an easy fix to the problem, demonstrating the usefulness of the fix both through simulations and in the specific South African context.

scholarly journals Entropy-Based Solutions for Ecological Inference Problems: A Composite Estimator

Entropy ◽  
2020 ◽  
Vol 22 (7) ◽  
pp. 781
Author(s):  
Rosa Bernardini Papalia ◽  
Esteban Fernandez Vazquez
Keyword(s):  
A Priori ◽  
Adjustment Problem ◽  
Ecological Inference ◽  
Estimation Techniques ◽  
Generalized Maximum Entropy ◽  
Inference Problems ◽  
Alternative Approach ◽  
Target Matrix ◽  
Composite Estimator ◽  
Priori Information

Information-based estimation techniques are becoming more popular in the field of Ecological Inference. Within this branch of estimation techniques, two alternative approaches can be pointed out. The first one is the Generalized Maximum Entropy (GME) approach based on a matrix adjustment problem where the only observable information is given by the margins of the target matrix. An alternative approach is based on a distributionally weighted regression (DWR) equation. These two approaches have been studied so far as completely different streams, even when there are clear connections between them. In this paper we present these connections explicitly. More specifically, we show that under certain conditions the generalized cross-entropy (GCE) solution for a matrix adjustment problem and the GME estimator of a DWR equation differ only in terms of the a priori information considered. Then, we move a step forward and propose a composite estimator that combines the two priors considered in both approaches. Finally, we present a numerical experiment and an empirical application based on Spanish data for the 2010 year.

Exploring a causal model in observational cohort data: The role of parents and peers in shaping substance use trajectories

2020 ◽  
Author(s):  
Christopher Greenwood ◽  
George Joseph Youssef ◽  
Primrose Letcher ◽  
Elizabeth Spry ◽  
Lauryn Hagg ◽  
...  
Keyword(s):  
Substance Use ◽  
Cannabis Use ◽  
Causal Effects ◽  
Deviant Peers ◽  
Adolescent Relationships ◽  
Cohort Data ◽  
Observational Cohort ◽  
Peer Affiliations ◽  
Role Of Parents ◽  
Adolescent Relationship

Aims: To explore the process of applying counterfactual thinking in examining causal predictors of substance use trajectories in observational cohort data. Specifically, we examine the extent to which quality of the parent-adolescent relationship and affiliations with deviant peers are causally related to trajectories of alcohol, tobacco, and cannabis use across adolescence and into young adulthood. Methods: Data were drawn from the Australian Temperament Project, a population-based cohort study that has followed a sample of young Australians from infancy to adulthood since 1983. Parent-adolescent relationship quality and deviant peer affiliations were assessed at age 13-14 years. Latent curve models were fitted for past month alcohol, tobacco, and cannabis use (n = 1,590) from age 15-16 to 27-28 years (5 waves). Confounding factors were selected in line with the counterfactual framework. Results: Following confounder adjustment, higher quality parent-adolescent relationships were associated with lower baseline cannabis use, but not alcohol or tobacco use trajectories. In contrast, affiliations with deviant peers were associated with higher baseline binge drinking, tobacco, and cannabis use, and an earlier peak in the cannabis use trajectory. Conclusions: Confounding adjustments weakened several estimated associations and the interpretation of such associations as causal is not without limitations. Nevertheless, findings suggested causal effects of both parent-adolescent relationships and deviant peer affiliations on the trajectory of substance use. Causal effects were however more pervasive (i.e., more substance types) and protracted for deviant peer affiliations. The current study encourages the exploration of causal relationships in observational cohort data, when relevant limitations are transparently acknowledged.

Sign in / Sign up

Export Citation Format

Share Document