ratio:ratio 设置 DDL (2021) 中第一种方法的非参数估计中偏差/方差的比值 (the value of the bias/variance ratio) (更多细节请 DDL (2021) 的附录 C),默认值为 10。
. use "https://www.stata-press.com/data/r17/union.dta", clear . mfelogit union age black if (year <=78), id("idcode") time("year") method("quick")
Estimates of coefficients in the fixed effect logit model (CMLE) --------------------------------------------------- Point Est. Std. Err. p-value --------------------------------------------------- age .0254468 .0100241 .011131 --------------------------------------------------- Estimates of the Average Marginal Effects in the fixed effect logit model --------------------------------------------------- Estimate [95% Conf. Interval] --------------------------------------------------- age(Tinf) .0022199 .0003422 .0040976 --------------------------------------------------- Notes: Nb of observed individuals: 3167 Nb of discarded individuals: 828 Maximal number of observed periods: 6 The method used to compute AME/ATE is the quick method (i.e. the second method in DDL).
. mfelogit union age black if (year <=78), id("idcode") time("year") method("quick") listT("all")
Estimates of coefficients in the fixed effect logit model (CMLE) --------------------------------------------------- Point Est. Std. Err. p-value --------------------------------------------------- age .0254468 .0100241 .011131 --------------------------------------------------- Estimates of the Average Marginal Effects in the fixed effect logit model ---------------------------------------------------------------- Period Estimate [95% Conf. Interval] ---------------------------------------------------------------- age 1 .0020879 -.00034 .0045158 age 2 .002115 -.0002957 .0045256 age 3 .0018418 -.0001786 .0038622 age 4 .0013656 -.0002081 .0029394 age 5 .000772 -.0001361 .0016801 age 6 .0004178 -.0002116 .0010471 age(Average) . .0020913 .0010468 .0031358 ---------------------------------------------------------------- Notes: Nb of observed individuals: 3167 Nb of discarded individuals: 828 Maximal number of observed periods: 6 The method used to compute AME/ATE is the quick method (i.e. the second method in DDL).
4. 参考资料
Davezies L, D'Haultfoeuille X, Laage L. Identification and estimation of average marginal effects in fixed effects logit models[J]. arXiv preprint arXiv:2105.00879, 2021. -PDF-
5. 相关推文
Note:产生如下推文列表的 Stata 命令为: lianxh probit logit, m 安装最新版 lianxh 命令: ssc install lianxh, replace
专题:Stata命令
Stata新命令:面板-LogitFE-ProbitFE
专题:交乘项-调节-中介
Logit-Probit中的交乘项及边际效应图示
专题:Probit-Logit
全面解读Logit模型
Stata:面板混合选择模型-cmxtmixlogit
Logit-Probit:非线性模型中交互项的边际效应解读
秒懂小罗肥归:logit与mlogit详解
reg2logit:用OLS估计Logit模型参数
feologit:固定效应有序Logit模型
Stata:多元 Logit 模型详解 (mlogit)
Stata:Logit模型一文读懂
详解 Logit/Probit 模型中的 completely determined 问题
Stata:Logit 模型评介
二元选择模型:Probit 还是 Logit?
Stata:何时使用线性概率模型而非Logit?
Stata:嵌套 Logit 模型 (Nested Logit)
Stata:二元Probit模型
动态 Probit 模型及 Stata 实现
New! Stata 搜索神器:lianxh 和 songblGIF 动图介绍 搜: 推文、数据分享、期刊论文、重现代码 …… 👉 安装: . ssc install lianxh . ssc install songbl 👉 使用: . lianxh DID 倍分法 . songbl all