CMP: Stata module to implement conditional (recursive) mixed process estimator
CMP: Stata module to implement conditional (recursive) mixed process estimator
复制标题
DOI：
--
复制
发表时间：
2007
期刊：
影响因子：
--
通讯作者：
G. David Roodman
中科院分区：
文献类型：
--
作者：
G. David Roodman
CMP估计多方程、混合过程模型，可能具有分层随机效应。“混合过程”是指不同的方程可以有不同种类的因变量。可供选择的有：连续(如OLS)、托比特(左、右或双审查)、概率、有序概率或分数概率。“有条件的”是指模型可以根据观察结果而变化。对于与之无关的观察，可以省略一个等式--比方说，如果一个城市没有提供工人再培训计划，那么就不能在那里对吸纳的决定因素进行建模。或者，因变量的类型可能因观察而不同。一个方程中的因变量可以出现在另一个方程的右侧。如果这种依赖关系如观察到的那样依赖于被审查的变量，那么这种依赖关系必须具有递归结构，这意味着它们将方程分成几个阶段。如果相依性依赖于(潜在的)线性因变量，它们在结构上可以是递归的或同时的。因此，CMP可以适用于许多SUR、联立方程组和IV模型。因此，CMP的建模框架包含官方Stata命令probit、ivprobit、Treatreg、biprobit、etrachic、oprobit、mprobit、asmprobit、asroprobit、Tobit、ivtobit、cnreg、intreg、truncreg、heckman、herkprob、xtreg、xtprobit、xttobit、xtintreg，原则上甚至回归、保证和reg3。它超越了它们，在模型构建方面提供了更大的灵活性。该例程在Stata 10或更高版本下运行，在Stata 11.2或更高版本下运行得更快。
cmp estimates multi-equation, mixed process models, potentially with hierarchical random effects. "Mixed process" means that different equations can have different kinds of dependent variables. The choices are: continuous (like OLS), tobit (left-, right-, or bi-censored), probit, ordered probit or fractional probit. "Conditional" means that the model can vary by observation. An equation can be dropped for observations for which it is not relevant--if, say, a worker retraining program is not offered in a city then the determinants of uptake cannot be modeled there. Or the type of dependent variable can vary by observation. A dependent variable in one equation can appear on the right side of another equation. Such dependencies must have a recursive structure if the dependencies are on censored variables as observed, meaning that they split the equations into stages. If the dependencies are on (latent) linear dependent variables, they can be recursive or simultaneous in structure. So cmp can fit many SUR, simultaneous equation, and IV models. cmp's modeling framework therefore embraces those of the official Stata commands probit, ivprobit, treatreg, biprobit, tetrachoric, oprobit, mprobit, asmprobit, asroprobit, tobit, ivtobit, cnreg, intreg, truncreg, heckman, heckprob, xtreg, xtprobit, xttobit, xtintreg, in principle even regress, sureg, and reg3. It goes beyond them in offering far more flexibility in model construction. The routine runs under Stata 10 or later, faster under Stata 11.2 or later.