Erratum and discussion of propensity score reweighting c ©

@inproceedings{Nichols2008ErratumAD,
  title={Erratum and discussion of propensity score reweighting c ©},
  author={Austin Lee Nichols},
  year={2008}
}
Nichols (2007) described estimating the probability an observation receives a binary “treatment” as a function of observable variables X (using e.g. logit or probit), and using the estimated probabilities of treatment or “propensity scores” λ̂ to reweight the data (as an alternative to matching). Section 3.4 neglects to mention that the weights λ̂/ ( 1− λ̂ ) should only be applied to the control group in order to make the mean of each variable in the matrix X (i.e. those variables included in… CONTINUE READING

From This Paper

Topics from this paper.
8 Citations
13 References
Similar Papers

Citations

Publications citing this paper.

References

Publications referenced by this paper.
Showing 1-10 of 13 references

A Stata package for the estimation of the doseresponse function through adjustment for the generalized propensity score

  • Bia, Michela, Alessandra Mattei.
  • The Stata Journal, 8(3): 354-373.
  • 2008

A new framework for managing and analyzing multiply imputed data

  • Carlin, B John, John C. Galati, Patrick Royston
  • in Stata The Stata Journal,
  • 2008

A new framework for managing and analyzing multiply imputed data in

  • John. DiNardo
  • Stata The Stata Journal
  • 2008

Changes in the characteristics of American youth: Implications for adult outcomes

  • Altonji, G. Joseph, Prashant Bharadwaj, Fabian Lange.
  • Yale University Working Paper
  • 2008

Similar Papers

Loading similar papers…