[求助] Monte Carlo Simulation of Regression Models in stata

是 否 +2 论坛币

k人 参与回答

经管之家送您一份

应届毕业生专属福利!

求职就业群

赵安豆老师微信：zhaoandou666

经管之家联合CDA

送您一个全额奖学金名额~ !

立即领取

感谢您参与论坛问题回答

经管之家送您两个论坛币！

+2 论坛币

那位大侠有STATA里面怎么做回归模型的MONTE CARLO SIMULATION 的资料？ 多谢了

扫码加我 拉你入群

请注明：姓名-公司-职位

以便审核进群资格，未注明则拒绝

分享0 收藏1 回帖

关键词：Monte Carlo regression Simulation regressio ulation Monte Carlo models Simulation regression

gtoooooooooood

In the first example, the two independent variables are from an existing dataset and the dependent variable is generated based on the two independent variables plus some random error. The dependent variable is then regressed on the two independent variables.

* Set up the steps you want to repeat for the simulation in a program
program define myprog1
        * drop all variables to create an empty dataset, do not use clear
        drop _all
        * get dataset
        use http://www.ats.ucla.edu/stat/stata/faq/hsb2
        * keep the independent variables (IVs)
        keep write math
        * gen dependent variable (DV) with set relationship to IVs + random error
        gen y = 7.541 + .3283*math + .5196*write + 7.281 * invnormal(uniform())
        * run the desired command
        reg y write math
end

* use the simulate command to rerun myprog1 1000 times
* collect the betas (_b) and standard errors (_se) from the regression each time
* You'll probably want to set reps(10) for testing, then set it higher for the simulation.
simulate _b _se, reps(1000): myprog1
The second example is similar to the first, except that the data are random draws from a normal distribution with a given correlational structure using the command drawnorm. Covariances can also be used by specifying the cov() option instead of corr(). If no correlation or covariance structure is specified, the variables generated will be orthogonal. The code below also specifies means and standard deviations for the variables, but this is not strictly necessary.

* Set up the steps you want to repeat for the simulation in a program
program define myprog2
        * drop all variables to create an empty dataset, do not use clear
        drop _all
        * create a vector that contains the equivalent of a lower triangular correlation matrix
        matrix c = (1, 0.5968, 1, 0.6623, 0.6174, 1)
        * create a vector that contains the means of the variables
        matrix m = (52.23,52.775,52.645)
        * create a vector that contains the standard deviations
        matrix sd = (10.25,9.47,9.36)
        * draw a sample of 1000 cases from a normal distribution with specified correlation structure
        * and specified means and standard deviations
        drawnorm x1 x2 y, n(1000) corr(c) cstorage(lower) means(m) sds(sd)
        * run the desired command
        reg y x1 x2
end
* use the simulate command to rerun myprog2 1000 times
* collect the betas (_b) and standard errors (_se) from the regression each time
* You'll probably want to set reps(10) for testing, then set it higher for the simulation.
simulate _b _se, reps(1000): myprog2

3# dxystata

多谢多谢。要好好学习。

请问这可以用在 penal data 上吗？

同问

thanks

记录，学习！