Weighting regressions by propensity scores
Weighting regressions by propensity scores
复制标题
DOI：
10.1177/0193841x08317586
复制
发表时间：
2008-08-01
影响因子：
0.9
通讯作者：
Berk, Richard A.
中科院分区：
文献类型：
--
作者：
Freedman, David A.;Berk, Richard A.
回归可以通过倾向分数加权，以减少偏差。然而，加权可能会增加估计中的随机误差，并使估计的标准误差向下倾斜，即使在选择机制被很好地理解时也是如此。此外，在某些情况下，加权会增加估计的因果参数的偏差。如果研究人员有一个很好的因果模型，那么不加权重地拟合模型似乎更好。如果因果模型指定不当，则通过加权检索情况时可能会出现重大问题，尽管加权在某些情况下可能会有所帮助。
Regressions can be weighted by propensity scores in order to reduce bias. However, weighting is likely to increase random error in the estimates, and to bias the estimated standard errors downward, even when selection mechanisms are well understood. Moreover, in some cases, weighting will increase the bias in estimated causal parameters. If investigators have a good causal model, it seems better just to fit the model without weights. If the causal model is improperly specified, there can be significant problems in retrieving the situation by weighting, although weighting may help under some circumstances.