[答疑解惑] 关于PSTR程序运行结果 [推广有奖]

0关注
1粉丝

已卖：4份资源

硕士生

28%

还不是VIP/贵宾

威望: 0 级
论坛币: 1 个
通用积分: 0.0022
学术水平: 0 点
热心指数: 0 点
信用等级: 0 点
经验: 740 点
帖子: 11
精华: 0
在线时间: 301 小时
注册时间: 2005-1-4
最后登录: 2019-11-1

楼主

穷的只剩钱 发表于 2017-12-18 11:12:34 |AI写论文

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

尝试使用matlab程序的PSTR模型，跑回归后发现：
***********************
*** LINEARITY Tests ***
***********************

H0: Linear Model H1: PSTR model with at least one Threshold Variable (r=1)

   Wald Tests (LM):       W = 36.631 pvalue = 0.000

   Fisher Tests (LMF):    F = 3.761 pvalue = 0.000

   LRT Tests (LRT):       LRT = 36.829 pvalue = 0.000

**************************************************************************
*** TESTING THE NUMBER OF REGIMES: TESTS OF NO REMAINING NON-LINEARITY ***
**************************************************************************

  Initial Conditions : Assumed Number of Thresholds r = 1 Number of Regressions = 270
Initial Conditions on (c,gamma)
3.5000 9.3399

  Estimation of the Model with r = 1 and m = 1 : Convergence = 1 RSS = 83.473
  RSS under H1 = 82.732

  Initial Conditions : Assumed Number of Thresholds r = 2 Number of Regressions = 270
Initial Conditions on (c,gamma)
3.2631 0.2000 9.3025 10.7293

  Estimation of the Model with r = 2 and m = 1 : Convergence = 1 RSS = 82.634

WARNING: At least one estimated Location Parameter is outside the trimming for a PTR model

The location Parameter should range from  8.9409  to  10.8456 in a PTR model

  RSS under H1 = 82.513

H0: PSTR with r = 1  against  H1: PSTR with at least r = 2

   Wald Tests (LM):       W = 30.224 pvalue = 0.000

   Fisher Tests (LMF):    F = 3.079 pvalue = 0.001

   LRT Tests (LRT):       LRT = 30.359 pvalue = 0.000

H0: PSTR with r = 2  against  H1: PSTR with at least r = 3

   Wald Tests (LM):       W = 4.974 pvalue = 0.837

   Fisher Tests (LMF):    F = 0.501 pvalue = 0.874

   LRT Tests (LRT):       LRT = 4.977 pvalue = 0.836

Given the choices of rmax = 2 and m = 1, the OPTIMAL (LMF criterion) NUMBER OF THRESHOLD FUNCTIONS is r = 2

**************************************
*** FINAL ESTIMATION OF PSTR MODEL ***
**************************************

Final Estimation of the Model with r = 2 and m = 1 by NLS ***

Initial Conditions on (gamma,c) :
2.0731 0.1333 9.3398  165.2791

WARNING FINAL ESTIMATION: At least one estimated Location Parameter is outside the trimming for a PTR model

The location Parameter must range from  8.9409  to  10.8456 for a PTR model

  RSS = 82.634    Convergence = 1

  AIC = -3.692    BIC = -3.636

Estimated slope parameter of the transition function (one for for each transition function)
2.0731 0.1333

Estimated location parameters (per column for each transition function)
9.3398  172.5100

Estimated slope parameters (per column for each transition function)
1.0e+09 *

-0.0000 -0.0000 0.4856
0.0000 0.0000 -1.1008
-0.0000 -0.0000 0.7093
-0.0000 0.0000 -0.4028
-0.0000 -0.0000 1.3101
-0.0000 -0.0000 4.1347
0.0000 0.0000 -2.2320
0.0000 0.0000 -2.9966
0.0000 0.0000 -0.0917

Standard Errors of estimated slope parameters corrected fo heteroskedasticity (per column for each transition function)
1.0e+09 *

0.0000 0.0000 0.8123
0.0000 0.0000 0.3191
0.0000 0.0000 3.7675
0.0000 0.0000 1.4672
0.0000 0.0000 0.3778
0.0000 0.0000 2.9993
0.0000 0.0000 2.5672
0.0000 0.0000 1.0218
0.0000 0.0000 0.1119

t-statistics based on corrected standard errors (per column for each transition function)
-0.3842 -1.5858 0.5977
2.8897 4.4044 -3.4491
-0.3607 -0.2216 0.1883
-0.1145 0.9227 -0.2745
-4.1213 -2.2890 3.4678
-0.9447 -2.3204 1.3785
0.7282 0.3204 -0.8694
2.0980 2.4253 -2.9325
0.4222 2.3120 -0.8196

OUPUT: Individual Elasticities for each explicative variable (first column is the cross section identifier) are available in the excel

后面的斜率参数与标准误有很多0值，请问这是怎么回事？