公卫百科  > 所属分类  >  Stata   
[0] 评论[0] 编辑

reghdfe

reghdfe 有效解决数据众多时加入固定效应的问题 Linear and instrumental-variable/GMM regression absorbing multiple levels of fixed effects

公卫家园


    reghdfe is a generalization of areg (and xtreg,fe, xtivreg,fe) for  multiple levels of fixed effects (including heterogeneous slopes),
    alternative estimators (2sls, gmm2s, liml), and additional robust standard  errors (multi-way clustering, HAC standard errors, etc).
公卫考场
    Additional features include:

       a)  A novel and robust algorithm to efficiently absorb the fixed  effects (extending the work of Guimaraes and Portugal, 2010).
       b)  Coded in Mata, which in most scenarios makes it even faster than areg and xtreg for a single fixed effect (see benchmarks on the Github page).
       c)  Can save the point estimates of the fixed effects (caveat emptor: the fixed effects may not be identified, see the references).
       d)  Calculates the degrees-of-freedom lost due to the fixed effects  (note: beyond two levels of fixed effects, this is still an open
           problem, but we provide a conservative approximation).
       e)  Iteratively removes singleton groups by default, to avoid biasing the standard errors (see ancillary document).
公卫考场
安装:ssc install reghdfe
教程:http://scorreia.com/reghdfe.
作者:
Sergio Correia,  Fuqua School of Business, Duke University
sergio.correia@duke.edu


附件列表


0

词条内容仅供参考,如果您需要解决具体问题
(尤其在法律、医学等领域),建议您咨询相关领域专业人士。

如果您认为本词条还有待完善,请 编辑

上一篇 qreg2    下一篇 rangerun

标签

暂无标签

参考资料

[1].  A simple feasible procedure to fit models with high-dimensional fixed effects   http://www.stata-journal.com/article.html?article=st0212

同义词

暂无同义词