Estimation of a Semiparametric Natural Direct Effect Model Incorporating Baseline Covariates
Establishing cause-effect relationships is a standard goal of empirical science. Once the presence of a causal relationship is established, the precise causal mechanism involved becomes a topic of interest. A particularly popular type of mechanism analysis concerns questions of mediation, that is to what extent an effect is direct, and to what extent it is mediated by a third variable. A semiparametric theory has recently been proposed which allows multiply robust estimation of direct and mediated marginal effect functionals in observational studies (Tchetgen Tchetgen & Shpitser, 2012). In this paper we extend the new theory to handle parametric models of natural direct and indirect effects within levels of pre-exposure variables with an identity or log link function, where the model for the observed data likelihood is otherwise unrestricted. We show that estimation is generally not feasible in this model because of the curse of dimensionality associated with the required estimation of auxiliary conditional densities or expectations, given high-dimensional covariates. Thus, we consider multiply robust estimation and propose a more general model which assumes that a subset but not all of several working models holds.
Medienart: |
Artikel |
---|
Erscheinungsjahr: |
2014 |
---|---|
Erschienen: |
2014 |
Enthalten in: |
Zur Gesamtaufnahme - volume:101 |
---|---|
Enthalten in: |
Biometrika - 101(2014), 4 vom: 20. Dez., Seite 849-864 |
Sprache: |
Englisch |
---|
Beteiligte Personen: |
Tchetgen Tchetgen, E J [VerfasserIn] |
---|
Themen: |
Journal Article |
---|
Anmerkungen: |
Date Revised 22.03.2024 published: Print Citation Status PubMed-not-MEDLINE |
---|
Förderinstitution / Projekttitel: |
|
---|
PPN (Katalog-ID): |
NLM248234919 |
---|
LEADER | 01000caa a22002652 4500 | ||
---|---|---|---|
001 | NLM248234919 | ||
003 | DE-627 | ||
005 | 20240322235443.0 | ||
007 | tu | ||
008 | 231224s2014 xx ||||| 00| ||eng c | ||
028 | 5 | 2 | |a pubmed24n1341.xml |
035 | |a (DE-627)NLM248234919 | ||
035 | |a (NLM)25892739 | ||
040 | |a DE-627 |b ger |c DE-627 |e rakwb | ||
041 | |a eng | ||
100 | 1 | |a Tchetgen Tchetgen, E J |e verfasserin |4 aut | |
245 | 1 | 0 | |a Estimation of a Semiparametric Natural Direct Effect Model Incorporating Baseline Covariates |
264 | 1 | |c 2014 | |
336 | |a Text |b txt |2 rdacontent | ||
337 | |a ohne Hilfsmittel zu benutzen |b n |2 rdamedia | ||
338 | |a Band |b nc |2 rdacarrier | ||
500 | |a Date Revised 22.03.2024 | ||
500 | |a published: Print | ||
500 | |a Citation Status PubMed-not-MEDLINE | ||
520 | |a Establishing cause-effect relationships is a standard goal of empirical science. Once the presence of a causal relationship is established, the precise causal mechanism involved becomes a topic of interest. A particularly popular type of mechanism analysis concerns questions of mediation, that is to what extent an effect is direct, and to what extent it is mediated by a third variable. A semiparametric theory has recently been proposed which allows multiply robust estimation of direct and mediated marginal effect functionals in observational studies (Tchetgen Tchetgen & Shpitser, 2012). In this paper we extend the new theory to handle parametric models of natural direct and indirect effects within levels of pre-exposure variables with an identity or log link function, where the model for the observed data likelihood is otherwise unrestricted. We show that estimation is generally not feasible in this model because of the curse of dimensionality associated with the required estimation of auxiliary conditional densities or expectations, given high-dimensional covariates. Thus, we consider multiply robust estimation and propose a more general model which assumes that a subset but not all of several working models holds | ||
650 | 4 | |a Journal Article | |
650 | 4 | |a Local Efficiency | |
650 | 4 | |a Mediation | |
650 | 4 | |a Multiple Robustness | |
650 | 4 | |a Natural Direct Effect | |
650 | 4 | |a Natural Indirect Effect | |
700 | 1 | |a Shpitser, I |e verfasserin |4 aut | |
773 | 0 | 8 | |i Enthalten in |t Biometrika |d 1945 |g 101(2014), 4 vom: 20. Dez., Seite 849-864 |w (DE-627)NLM048403121 |x 0006-3444 |7 nnns |
773 | 1 | 8 | |g volume:101 |g year:2014 |g number:4 |g day:20 |g month:12 |g pages:849-864 |
912 | |a GBV_USEFLAG_A | ||
912 | |a GBV_NLM | ||
951 | |a AR | ||
952 | |d 101 |j 2014 |e 4 |b 20 |c 12 |h 849-864 |