题主今天打算用RD回归研究一下南北方城市空气质量的差别,我用的命令是
rd avaqi north distance,z0(0) mbw(50 100 200)
avaqi是地级市空气质量均值,north是处理变量,distance代笔地级城市到南北回归线的距离,在分界线以北距离取正值,此时north取值为1,在分界线以南距离取负值且north为0,我回归出来的结果是这样子的,
rd aqiav north juli ,z0 str mbw(50 100 200) GR B OX
Three variables specified; jump in treatment
at Z=0 will be estimated. Local Wald Estimate
is the ratio of jump in outcome to jump in treatment.
Assignment variable Z is juli
Treatment variable X_T is north
Outcome variable y is aqiav
no observations
我觉得是因为距离变量以米为单位太大了,于是把该变量除以100000,重新回归,结果就变成了这个样子
. rd aqiav north juli2 ,z0(0) str mbw(50 100 200) GR B OX
Three variables specified; jump in treatment
at Z=0 will be estimated. Local Wald Estimate
is the ratio of jump in outcome to jump in treatment.
Assignment variable Z is juli2
Treatment variable X_T is north
Outcome variable y is aqiav
(196 missing values generated)
(196 missing values generated)
(196 missing values generated)
Estimating for bandwidth 3.62935727502711
A predicted value of treatment at cutoff lies outside feasible range;
switching to local mean smoothing for treatment discontinuity.
score variables for model __00000P contain missing values
不死心的我drop掉缺失值,结果变成这样子
. rd aqiav north juli2 ,z0(0) str mbw(50 100 200) GR B OX
Three variables specified; jump in treatment
at Z=0 will be estimated. Local Wald Estimate
is the ratio of jump in outcome to jump in treatment.
Assignment variable Z is juli2
Treatment variable X_T is north
Outcome variable y is aqiav
(82 missing values generated)
(82 missing values generated)
(82 missing values generated)
Estimating for bandwidth 3.629357275027114
score variables for model __00000P contain missing values
r(322);
求问大神这个错误提示是代表什么意思呢?
我不懂模型是哪里设定错误了,小博士第一篇论文,还望大伙多多帮忙,感激不尽!