门槛模型，输出结果，求指导-经管之家官网！

坛友互助群

扫码加入各岗位、行业、专业交流群

xthreg TC DT SI UL ECS PRS ,rx(ER) qx(lnGR) thnum(2) trim(0.01 0.01) bs(300 300)

Estimatingthethresholdparameters: 1st ......2nd ......Done

Boostrap for single threshold

.................................................. + 50

.................................................. +100

.................................................. +150

.................................................. +200

.................................................. +250

.................................................. +300

Boostrap for double threshold model:

.................................................. + 50

.................................................. +100

.................................................. +150

.................................................. +200

.................................................. +250

.................................................. +300

Threshold estimator (level = 95):

-----------------------------------------------------

model | Threshold Lower Upper

-----------+-----------------------------------------

Th-1 | -3.2145 -3.2315 -3.2139

Th-21 | -3.2145 -3.2315 -3.2139

Th-22 | -3.7573 -3.7645 -3.7519

-----------------------------------------------------

Threshold effect test (bootstrap = 300 300):

-------------------------------------------------------------------------------

Threshold | RSS MSE Fstat Prob Crit10 Crit5 Crit1

-----------+-------------------------------------------------------------------

Single | 3.7092 0.0128 51.260.010037.097941.423151.1566

Double | 3.2619 0.0112 39.770.040032.898237.338446.8497

-------------------------------------------------------------------------------

Fixed-effects (within) regression Number of obs = 300

Group variable: citte Number of groups = 30

R-sq:within= 0.5849 Obs per group: min = 10

between = 0.0405 avg = 10.0

overall = 0.0508 max = 10

F(8,262) = 46.15

corr(u_i, Xb)= -0.8261 Prob > F = 0.0000

------------------------------------------------------------------------------

TC | Coef. Std. Err. t P>|t| [95% Conf. Interval]

-------------+----------------------------------------------------------------

DT |-.3917677 .0803065 -4.88 0.000 -.549896 -.2336394

SI |-1.648938 .2346798 -7.03 0.000 -2.111037 -1.18684

UL | .0011034 .0008443 1.31 0.192 -.000559 .0027659

ECS |-.0578555 .0543573 -1.06 0.288 -.1648884 .0491773

PRS | .1358816 .0496148 2.74 0.007 .0381871 .2335762

|

_cat#c.ER |

0| 1.679299 .4796114 3.50 0.001 .7349157 2.623683

1| 3.050523 .4030889 7.57 0.000 2.256817 3.844229

2| 5.468224 .4601356 11.88 0.000 4.562189 6.374258

|

_cons | 1.617478 .1408524 11.48 0.000 1.340131 1.894824

-------------+----------------------------------------------------------------

sigma_u |.27148594

sigma_e |.11240627

rho |.85365762 (fraction of variance due to u_i)

------------------------------------------------------------------------------

F test that all u_i=0: F(29, 262) = 13.35 Prob > F = 0.00

写结论的时候，发现和自己以前认为的不一样。希望大家可以解答一下，谢谢了

扫码或添加微信号：坛友素质互助

「经管之家」APP：经管人学习、答疑、交友，就上经管之家！
免流量费下载资料----在经管之家app可以下载论坛上的所有资源，并且不额外收取下载高峰期的论坛币。
涵盖所有经管领域的优秀内容----覆盖经济、管理、金融投资、计量统计、数据分析、国贸、财会等专业的学习宝库，各类资料应有尽有。
来自五湖四海的经管达人----已经有上千万的经管人来到这里，你可以找到任何学科方向、有共同话题的朋友。
经管之家（原人大经济论坛），跨越高校的围墙，带你走进经管知识的新世界。
扫描下方二维码下载并注册APP