How deeply does Causal Inference for Data Science cover inverse propensity weighting?

Connects weighting to the adjustment formula and mentions implementations, while deferring the full derivation as optional.

Inverse propensity weighting

As explained in Causal Inference for Data Science

Inverse probability weighting estimates causal effects by weighting observations by the inverse probability of receiving their observed treatment.

Inverse propensity weighting estimates an average treatment effect by reweighting each observation according to the inverse probability of receiving its observed treatment. It turns propensity scores into a way to calculate causal effects rather than merely describe treatment assignment. section 5.3.4

The method connects propensity scores to the adjustment formula: patients with their treatment probabilities represented by scores can support an unbiased causal-effect estimate when relevant confounders are not missing. section 5.3.4

Use it with these conditions and distinctions:

Check the positivity assumption before using the calculated scores. section 5.3.4
Treat the method as an alternative relationship between propensity scores and the adjustment formula, alongside other numerical implementations. section 5.3.4
Recognize that unbiasedness still depends on not omitting relevant confounders. section 5.3.4

Table 5.2 Available data with propensity scores calculated

O	T	C ₁	…	C_p	S
o ₁	t ¹	c ¹ ₁	…	c ¹ _p	s ₁
…	…	…	…	…	…
O _n	t ⁿ	c ⁿ ₁	…	c ⁿ _p	s _n

Inspect patient-level treatment, outcome, confounder, and propensity-score data before applying the weighting approach. section 5.3.4

How Causal Inference for Data Science covers it

Cover of Causal Inference for Data Science

liveBook manning.com

Read Causal Inference for Data Science on liveBook Get the book at manning.com

Related concepts

propensity scoreuses · A propensity score is the estimated conditional probability that a unit receives a particular treatment or action given observed covariates or context.
counterfactual reasoningused by · Counterfactual reasoning examines hypothetical outcomes under conditions, actions, or policies different from those that actually occurred.
probability theoryuses · Probability theory is the branch of mathematics that formalizes uncertainty and analyzes random events and outcomes using probability measures.
propensity score methodused by · A propensity-score method is a causal-inference technique that estimates treatment effects by matching, weighting, stratifying, or otherwise adjusting units according to their observed treatment probabilities.
resultuses · A result is an actual or possible outcome, state, or consequence of an event, action, decision, or process.

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.