The Difference Between Causal Analysis and Predictive Models
Response to “Comment on Young and Holsteen (2017)”
Bibliographic Data
| ID | 11610733 |
|---|---|
| Authors | Cristobal Young (Stanford University, Stanford, CA, USA, corresponding author) |
| Year | 2018 |
| Volume | 48 |
| Issue | 2 |
| Pages | 431-447 |
| Publication date | 2018-07-09 |
| Peer Reviewed | Yes |
| Open Access | Yes |
| Type | ARTICLE |
| Venue | Sociological Methods & Research (JOURNAL) |
| Journal identifiers | ISSN: 0049-1241 • E-ISSN: 1552-8294 |
| Publisher | SAGE Publishing (PUBLISHER • US) |
| DOI | 10.1177/0049124118782542 |
| OpenAlex | W2882605002 |
| Language | EN |
| Citations received | 5 |
| References cited | 27 |
The commenter’s proposal may be a reasonable method for addressing uncertainty in predictive modeling, where the goal is to predict y. In a treatment effects framework, where the goal is causal inference by conditioning-on-observables, the commenter’s proposal is deeply flawed. The proposal (1) ignores the definition of omitted-variable bias, thus systematically omitting critical kinds of controls; (2) assumes for convenience there are no bad controls in the model space, thus waving off the premise of model uncertainty; and (3) deletes virtually all alternative models to select a single model with the highest R 2 . Rather than showing what model assumptions are necessary to support one’s preferred results, this proposal favors biased parameter estimates and deletes alternative results before anyone has a chance to see them. In a treatment effects framework, this is not model robustness analysis but simply biased model selection
Causal inference · Causal model · Econometrics · Epistemology · Inference · Model selection · Observable · Premise · Robustness (evolution · Statistics · Advanced Causal Inference Techniques · Artificial Intelligence · Computer Science · Health Systems, Economic Evaluations, Quality of Life · Mathematics · Statistical Methods and Inference
Theory and methods of the multiverse
A Multiversal Model of Vibration of Effects of the Equitable and Sustainable Well-Being (BES) on Fertility
Incorporating Machine Learning into Sociological Model-Building
Methodological Uncertainty and Multi-Strategy Analysis
Subjective social class has a bad name, but predicts life chances well
To Explain or to Predict?
Inference on Treatment Effects after Selection among High-Dimensional Controls
Illustrating bias due to conditioning on a collider
Prediction and explanation in social systems
Multicollinearity and Model Misspecification
The Phantom Menace
The Educational Consequences of Teen Childbearing
Endogenous Selection Bias
How Conditioning on Posttreatment Variables Can Ruin Your Experiment and What to Do about It
We Ran 9 Billion Regressions
The Scientific Model of Causality
Economic Globalization and the Welfare State in Affluent Democracies, 1975-2001
Model Uncertainty in Sociological Research
Machine Learning
Explaining Causal Findings Without Bias
Model Uncertainty and the Crisis in Science
Model Uncertainty and Robustness
Diversity in Everyday Research Practice
| Unique citing works | 5 |
|---|---|
| Citations per year | 0,83 |
| Citation span | 2020 - 2024 (5) |
| Citation velocity | recent |
| Highly cited | No |
| Citation types | Neutral: 5 |