covariates
Control variables included in a regression to adjust for confounding factors; changing them can shift estimated magnitudes.
As defined in David Autor on Trade, China, and U.S. Labor Markets
Where it comes up · 4
- Susan Athey on Machine Learning, Big Data, and Causation5 claims
- Brian Nosek on Truth, Science, and Academic Incentives2 claims
- Conversations with Tyler - Arthur Brooks1 claim
- David Autor on Trade, China, and U.S. Labor Markets1 claim
Most important claims · 9 of 9Search all claims for “covariates” →
- Even without conscious fraud, researchers make many analysis decisions (which participants to exclude, which covariates to include) and are subtly influenced to choose those that make results look better; these unconstrained choices leverage chance to produce favorable results, which is why a constrained replication using the same fixed choices often fails to reproduce the original effect.Brian Nosek on Truth, Science, and Academic Incentives
- For causal inference, you must distinguish the treatment variable (the minimum wage, the drug) from the control covariates and model them differently: apply machine learning to flexibly select controls, but give a causal interpretation only to the treatment variable, since data-mined controls are uninterpretable proxies that capture correlated information parsimoniously.Susan Athey on Machine Learning, Big Data, and Causation
- High-dimensional statistics, colloquially machine learning, is effective precisely when you have more covariates than observations, enabling data-driven model selection that replaces the subjective, artistic process of hand-picking a few proxy variables.Susan Athey on Machine Learning, Big Data, and Causation
- Having two camps with opposing perspectives jointly agree on an analysis script before running it surfaces exactly where they differ—on which control variables and data exclusions to use—revealing that the real substance of scientific debate often lies in how you reach the outcome rather than in the outcome itself.Brian Nosek on Truth, Science, and Academic Incentives
- The most trenchant criticism of the research is that it measures concentrated relative losses well but cannot equally measure the diffuse gains (e.g. jobs indirectly created in Silicon Valley), so the loss estimates may be conservative relative effects mislabeled as absolute; Autor concedes this but argues that even accounting for the missing gains, the episode was still strongly redistributive because the gains accrue to entirely different people.David Autor on Trade, China, and U.S. Labor Markets
- In regression analysis of charitable giving with covariates including political ideology, religious behavior, income, and demographics, the large and highly significant coefficient is religious activity, not politics—so conservatives gave more in 2006-2008 mainly because they were more religious, and as the conservative wing becomes more secular this giving gap is disappearing.Conversations with Tyler - Arthur Brooks
- Variables selected by machine learning regularization cannot be given a causal interpretation because the method finds a parsimonious proxy among many highly correlated covariates; causal interpretations should only be given to the policy variable of interest, which is what should have been the focus all along.Susan Athey on Machine Learning, Big Data, and Causation
- Machine learning (high-dimensional statistics) lets researchers specify a very large list of possible covariates—potentially more variables than observations—and use the data itself to determine which ones matter, replacing the subjective 'art form' of choosing one or two theoretical proxies.Susan Athey on Machine Learning, Big Data, and Causation
- The starting point for causal inference is to treat the causal variable of interest (e.g., minimum wage, the drug) differently from all the control covariates: use machine learning to data-mine the covariates but model the treatment variable carefully and separately, rather than putting everything into one regression with the same statistical treatment.Susan Athey on Machine Learning, Big Data, and Causation