- 阅读权限
- 255
- 威望
- 0 级
- 论坛币
- 906 个
- 通用积分
- 0.1500
- 学术水平
- 0 点
- 热心指数
- 0 点
- 信用等级
- 0 点
- 经验
- 30 点
- 帖子
- 1
- 精华
- 0
- 在线时间
- 28 小时
- 注册时间
- 2021-11-11
- 最后登录
- 2024-5-16
初中生
还不是VIP/贵宾
- 威望
- 0 级
- 论坛币
- 906 个
- 通用积分
- 0.1500
- 学术水平
- 0 点
- 热心指数
- 0 点
- 信用等级
- 0 点
- 经验
- 30 点
- 帖子
- 1
- 精华
- 0
- 在线时间
- 28 小时
- 注册时间
- 2021-11-11
- 最后登录
- 2024-5-16
|
80论坛币
多层回归是以lnhi为因变量,第一层为家庭层面变量,第二层为社区层面变量.
随机变量为第一层家庭层面变量的三个变量employment0,contract0,ms0.
第一层与第二层的交互项为infrahea infranyou lnrentpro.
通过以下公式
. xtmixed lnhi ae hoff ahh as welfare nprechildren0 nyouth0 health0 hukou0 province0 contract0 ms0 education0 employment0 foreignen0 lnrentmonth infra outsiderrate citycentre infrahea infranyou lnrentpro ||community: employment0 contract0 ms0 ,covariance(unstructured)mle variance nostderr
得到结果如下
Performing EM optimization:
Performing gradient-based optimization:
Iteration 0: log likelihood = -3938.9421
Iteration 1: log likelihood = -3918.8907
Iteration 2: log likelihood = -3916.683
Iteration 3: log likelihood = -3916.1721
Iteration 4: log likelihood = -3916.1621
Iteration 5: log likelihood = -3916.162
Mixed-effects ML regression Number of obs = 4,960
Group variable: community Number of groups = 777
Obs per group:
min = 1
avg = 6.4
max = 23
Wald chi2(22) = 965.77
Log likelihood = -3916.162 Prob > chi2 = 0.0000
-------------------------------------------------------------------------------
lnhi | Coef. Std. Err. z P>|z| [95% Conf. Interval]
--------------+----------------------------------------------------------------
ae | -.1352636 .0145054 -9.33 0.000 -.1636937 -.1068334
hoff | .0254234 .0168387 1.51 0.131 -.0075798 .0584267
ahh | -.031284 .0045458 -6.88 0.000 -.0401935 -.0223744
as | .000301 .0000427 7.04 0.000 .0002173 .0003848
welfare | .1636618 .0223649 7.32 0.000 .1198273 .2074962
nprechildren0 | -.0615714 .0243786 -2.53 0.012 -.1093525 -.0137902
nyouth0 | .1832795 .0894212 2.05 0.040 .0080171 .3585419
health0 | -.2402865 .1709696 -1.41 0.160 -.5753808 .0948077
hukou0 | -.0487206 .0529253 -0.92 0.357 -.1524522 .055011
province0 | 1.366377 .2541377 5.38 0.000 .8682765 1.864478
contract0 | -.037752 .0234495 -1.61 0.107 -.0837122 .0082081
ms0 | -.2265804 .0359663 -6.30 0.000 -.297073 -.1560878
education0 | -.217519 .094689 -2.30 0.022 -.403106 -.0319319
employment0 | -.3222104 .0464335 -6.94 0.000 -.4132185 -.2312024
foreignen0 | -.0407325 .0335906 -1.21 0.225 -.106569 .0251039
lnrentmonth | .3385035 .0209773 16.14 0.000 .2973887 .3796183
infra | .2711109 .1203626 2.25 0.024 .0352045 .5070174
outsiderrate | .4134183 .0819529 5.04 0.000 .2527936 .5740429
citycentre | -.0873414 .0258826 -3.37 0.001 -.1380703 -.0366125
infrahea | .0636582 .2165111 0.29 0.769 -.3606958 .4880122
infranyou | -.1888744 .1137035 -1.66 0.097 -.4117292 .0339805
lnrentpro | -.2343589 .0404085 -5.80 0.000 -.313558 -.1551598
_cons | 8.606703 .2044827 42.09 0.000 8.205924 9.007482
-------------------------------------------------------------------------------
------------------------------------------------------------------------------
Random-effects Parameters | Estimate Std. Err. [95% Conf. Interval]
-----------------------------+------------------------------------------------
community: Unstructured |
var(employ~0) | .1042985 . . .
var(contra~0) | .0232955 . . .
var(ms0) | .0615176 . . .
var(_cons) | .0809399 . . .
cov(employ~0,contra~0) | .0229407 . . .
cov(employ~0,ms0) | .0040406 . . .
cov(employ~0,_cons) | -.011397 . . .
cov(contra~0,ms0) | .003976 . . .
cov(contra~0,_cons) | -.0168323 . . .
cov(ms0,_cons) | -.010932 . . .
-----------------------------+------------------------------------------------
var(Residual) | .232012 . . .
------------------------------------------------------------------------------
LR test vs. linear model: chi2(10) = 541.39 Prob > chi2 = 0.0000
Note: LR test is conservative and provided only for reference.
.
想要预测出家庭层面,社区层面以及家庭和社区层面的误差项的残差
然而直接使用predict u0 u1,reffects指令一直报错.
望大神提供帮助。
|
|