liveBook · Manning

Nuisance function

As explained in Causal Inference for Data Science

A nuisance function is a secondary function needed to estimate a target causal parameter but not itself the primary parameter of interest.

A nuisance function supports estimation of a primary causal parameter without being the main quantity of interest. In causal inference, the propensity score is one example: it helps apply the adjustment formula, while the causal effect remains the target. section 8.1.3

Propensity score in adjustment

Suppose an analysis estimates a causal effect using the adjustment formula. The propensity score describes a function needed for that estimation, but attention remains on the causal parameter rather than on the propensity score itself. section 8.1.3

How Causal Inference for Data Science covers it

How deep it goes
Defines the role and gives a propensity-score example, but defers detailed score-function mathematics.
Examples
Uses the propensity score as a function required to apply the adjustment formula.
What you can do after
Apply it via DoubleML by distinguishing supporting functions from the primary causal parameter being estimated.
How it connects
Connects nuisance functions to propensity scores, adjustment formulas, score functions, and Double Machine Learning.
Cover of Causal Inference for Data Science
liveBookmanning.com
Read Causal Inference for Data Science on liveBook Get the book at manning.com

This explainer was generated by Manning's knowledge graph from the text of Causal Inference for Data Science. The section links point to the parts of the book it draws on.