Matches in SemOpenAlex for { <https://semopenalex.org/work/W2947446253> ?p ?o ?g. }
- W2947446253 abstract "When pre-processing observational data via matching, we seek to approximate each unit with maximally similar peers that had an alternative treatment status--essentially replicating a randomized block design. However, as one considers a growing number of continuous features, a curse of dimensionality applies making asymptotically valid inference impossible (Abadie and Imbens, 2006). The alternative of ignoring plausibly relevant features is certainly no better, and the resulting trade-off substantially limits the application of matching methods to wide datasets. Instead, Li and Fu (2017) recasts the problem of matching in a metric learning framework that maps features to a low-dimensional space that facilitates closer matches while still capturing important aspects of unit-level heterogeneity. However, that method lacks key theoretical guarantees and can produce inconsistent estimates in cases of heterogeneous treatment effects. Motivated by straightforward extension of existing results in the matching literature, we present alternative techniques that learn latent matching features through either MLPs or through siamese neural networks trained on a carefully selected loss function. We benchmark the resulting alternative methods in simulations as well as against two experimental data sets--including the canonical NSW worker training program data set--and find superior performance of the neural-net-based methods." @default.
- W2947446253 created "2019-06-07" @default.
- W2947446253 creator A5017946397 @default.
- W2947446253 creator A5073201338 @default.
- W2947446253 creator A5086971492 @default.
- W2947446253 date "2019-05-28" @default.
- W2947446253 modified "2023-09-27" @default.
- W2947446253 title "Matching on What Matters: A Pseudo-Metric Learning Approach to Matching Estimation in High Dimensions." @default.
- W2947446253 cites W1949591461 @default.
- W2947446253 cites W1977193486 @default.
- W2947446253 cites W2003477935 @default.
- W2947446253 cites W2006290997 @default.
- W2947446253 cites W2028040032 @default.
- W2947446253 cites W2030614017 @default.
- W2947446253 cites W2064903582 @default.
- W2947446253 cites W2100495367 @default.
- W2947446253 cites W2103496339 @default.
- W2947446253 cites W2120224267 @default.
- W2947446253 cites W2139577967 @default.
- W2947446253 cites W2171443468 @default.
- W2947446253 cites W2208550830 @default.
- W2947446253 cites W2325939864 @default.
- W2947446253 cites W2584924584 @default.
- W2947446253 cites W2752690044 @default.
- W2947446253 cites W2952808479 @default.
- W2947446253 cites W2964271126 @default.
- W2947446253 cites W3119268664 @default.
- W2947446253 cites W3122542817 @default.
- W2947446253 cites W3122948292 @default.
- W2947446253 cites W3125108970 @default.
- W2947446253 hasPublicationYear "2019" @default.
- W2947446253 type Work @default.
- W2947446253 sameAs 2947446253 @default.
- W2947446253 citedByCount "0" @default.
- W2947446253 crossrefType "posted-content" @default.
- W2947446253 hasAuthorship W2947446253A5017946397 @default.
- W2947446253 hasAuthorship W2947446253A5073201338 @default.
- W2947446253 hasAuthorship W2947446253A5086971492 @default.
- W2947446253 hasConcept C105795698 @default.
- W2947446253 hasConcept C111030470 @default.
- W2947446253 hasConcept C119857082 @default.
- W2947446253 hasConcept C13280743 @default.
- W2947446253 hasConcept C14036430 @default.
- W2947446253 hasConcept C154945302 @default.
- W2947446253 hasConcept C162324750 @default.
- W2947446253 hasConcept C165064840 @default.
- W2947446253 hasConcept C176217482 @default.
- W2947446253 hasConcept C177264268 @default.
- W2947446253 hasConcept C185798385 @default.
- W2947446253 hasConcept C199360897 @default.
- W2947446253 hasConcept C202444582 @default.
- W2947446253 hasConcept C205649164 @default.
- W2947446253 hasConcept C21547014 @default.
- W2947446253 hasConcept C2776214188 @default.
- W2947446253 hasConcept C33676613 @default.
- W2947446253 hasConcept C33923547 @default.
- W2947446253 hasConcept C41008148 @default.
- W2947446253 hasConcept C50644808 @default.
- W2947446253 hasConcept C78458016 @default.
- W2947446253 hasConcept C86803240 @default.
- W2947446253 hasConceptScore W2947446253C105795698 @default.
- W2947446253 hasConceptScore W2947446253C111030470 @default.
- W2947446253 hasConceptScore W2947446253C119857082 @default.
- W2947446253 hasConceptScore W2947446253C13280743 @default.
- W2947446253 hasConceptScore W2947446253C14036430 @default.
- W2947446253 hasConceptScore W2947446253C154945302 @default.
- W2947446253 hasConceptScore W2947446253C162324750 @default.
- W2947446253 hasConceptScore W2947446253C165064840 @default.
- W2947446253 hasConceptScore W2947446253C176217482 @default.
- W2947446253 hasConceptScore W2947446253C177264268 @default.
- W2947446253 hasConceptScore W2947446253C185798385 @default.
- W2947446253 hasConceptScore W2947446253C199360897 @default.
- W2947446253 hasConceptScore W2947446253C202444582 @default.
- W2947446253 hasConceptScore W2947446253C205649164 @default.
- W2947446253 hasConceptScore W2947446253C21547014 @default.
- W2947446253 hasConceptScore W2947446253C2776214188 @default.
- W2947446253 hasConceptScore W2947446253C33676613 @default.
- W2947446253 hasConceptScore W2947446253C33923547 @default.
- W2947446253 hasConceptScore W2947446253C41008148 @default.
- W2947446253 hasConceptScore W2947446253C50644808 @default.
- W2947446253 hasConceptScore W2947446253C78458016 @default.
- W2947446253 hasConceptScore W2947446253C86803240 @default.
- W2947446253 hasLocation W29474462531 @default.
- W2947446253 hasOpenAccess W2947446253 @default.
- W2947446253 hasPrimaryLocation W29474462531 @default.
- W2947446253 hasRelatedWork W1960700909 @default.
- W2947446253 hasRelatedWork W2098708428 @default.
- W2947446253 hasRelatedWork W2416947134 @default.
- W2947446253 hasRelatedWork W2734979634 @default.
- W2947446253 hasRelatedWork W2770992186 @default.
- W2947446253 hasRelatedWork W2787551658 @default.
- W2947446253 hasRelatedWork W2894867725 @default.
- W2947446253 hasRelatedWork W2903782687 @default.
- W2947446253 hasRelatedWork W2949750828 @default.
- W2947446253 hasRelatedWork W2950515451 @default.
- W2947446253 hasRelatedWork W2985663642 @default.
- W2947446253 hasRelatedWork W3004625735 @default.
- W2947446253 hasRelatedWork W3035717263 @default.
- W2947446253 hasRelatedWork W3046618572 @default.
- W2947446253 hasRelatedWork W3049667903 @default.