The Long Campaign for the Causal Interpretation (1952–1960). Brazil, Israel, and the U.K.

Abstract A growing number of studies use data before and after treatment initiation in groups exposed to different treatment strategies to estimate “causal effects” using a ratio measure called the prior event rate ratio (PERR). Here, we offer a causal interpretation for PERR and its additive scale analog, the prior event rate difference (PERD). We show that causal interpretation of these measures requires untestable rate-change assumptions about the relationship between 1) the change of the counterfactual rate before and after treatment initiation in the treated group under hypothetical intervention to implement the control strategy; and 2) the change of the factual rate before and after treatment initiation in the control group. The rate-change assumption is on the multiplicative scale for PERR but on the additive scale for PERD; the 2 assumptions hold simultaneously under testable, but unlikely, conditions. Even if investigators can pick the most appropriate scale, the relevant rate-change assumption might not hold exactly, so we describe sensitivity analysis methods to examine how assumption violations of different magnitudes would affect study results. We illustrate the methods using data from a published study of proton pump inhibitors and pneumonia.

Download Full-text

Some Common Pitfalls in Causal Analysis of Categorical Data

Journal of Marketing Research ◽

10.1177/002224378201900408 ◽

1982 ◽

Vol 19 (4) ◽

pp. 461-471 ◽

Cited By ~ 15

Author(s):

Jay Magidson

Keyword(s):

Categorical Data ◽

Causal Analysis ◽

Statistical Technique ◽

Omitted Variables ◽

Causal Interpretation ◽

Linear Modeling ◽

Chi Square ◽

Interaction Detection ◽

Biasing Effects ◽

Log Linear

Examples of some common pitfalls in the analysis of categorical data are discussed in the context of causal interpretation of the results. Though no statistical technique can replace theory, the author shows that log-linear modeling and chi square automatic interaction detection can provide researchers with powerful tools for gaining valuable causal insights into their data. Examples include the biasing effects of omitted variables, omitted interactions, improper contrast coding, and misspecification of the structure of an hypothesized interaction.

Download Full-text

Measuring Subgroup Preferences in Conjoint Experiments

Political Analysis ◽

10.1017/pan.2019.30 ◽

2019 ◽

Vol 28 (2) ◽

pp. 207-221 ◽

Cited By ~ 33

Author(s):

Thomas J. Leeper ◽

Sara B. Hobolt ◽

James Tilley

Keyword(s):

Conjoint Analysis ◽

Best Practice ◽

Causal Interpretation ◽

Reference Category ◽

Subgroup Differences ◽

Political Preferences ◽

Randomized Design ◽

Marginal Means ◽

Arbitrary Sign ◽

Multidimensional Objects

Conjoint analysis is a common tool for studying political preferences. The method disentangles patterns in respondents’ favorability toward complex, multidimensional objects, such as candidates or policies. Most conjoints rely upon a fully randomized design to generate average marginal component effects (AMCEs). They measure the degree to which a given value of a conjoint profile feature increases, or decreases, respondents’ support for the overall profile relative to a baseline, averaging across all respondents and other features. While the AMCE has a clear causal interpretation (about the effect of features), most published conjoint analyses also use AMCEs to describe levels of favorability. This often means comparing AMCEs among respondent subgroups. We show that using conditional AMCEs to describe the degree of subgroup agreement can be misleading as regression interactions are sensitive to the reference category used in the analysis. This leads to inferences about subgroup differences in preferences that have arbitrary sign, size, and significance. We demonstrate the problem using examples drawn from published articles and provide suggestions for improved reporting and interpretation using marginal means and an omnibus F-test. Given the accelerating use of these designs in political science, we offer advice for best practice in analysis and presentation of results.

Download Full-text

The Causal Interpretation of Language

The Principles of Linguistic Philosophy ◽

10.1007/978-1-349-25335-7_6 ◽

1997 ◽

pp. 111-128

Author(s):

F. Waismann

Keyword(s):

Causal Interpretation

Download Full-text

Keeping It in the Family: Lineage Organization and the Scope of Trust in Sub-Saharan Africa

The American Economic Review ◽

10.1257/aer.p20171088 ◽

2017 ◽

Vol 107 (5) ◽

pp. 565-571 ◽

Cited By ~ 14

Author(s):

Jacob Moscona ◽

Nathan Nunn ◽

James A. Robinson

Keyword(s):

Ethnic Groups ◽

Rural Areas ◽

Important Determinant ◽

Sub Saharan Africa ◽

Causal Interpretation ◽

Present Evidence ◽

Traditional Structure ◽

The Family ◽

Sub Saharan ◽

Limited Scope

We present evidence that the traditional structure of society is an important determinant of the scope of trust today. Within Africa, individuals belonging to ethnic groups that organized society using segmentary lineages exhibit a more limited scope of trust, measured by the gap between trust in relatives and trust in non-relatives. This trust gap arises because of lower levels of trust in non-relatives and not higher levels of trust in relatives. A causal interpretation of these correlations is supported by the fact that the effects are primarily found in rural areas where these forms of organization are still prevalent.

Download Full-text