eviews含定性自变量的回归模型具体步骤，那个模型方程最后的变量怎么输？因为是刚开始自学，比较弱 在eviews中怎么将其他解释变量分别导入初始回归模型Y(^...
\u8bf7\u95ee\u5982\u4f55\u7528eviews\u5efa\u7acb\u5747\u503c\u56de\u5f52\u65b9\u7a0bGlossary:
ls(least squares)\u6700\u5c0f\u4e8c\u4e58\u6cd5
R-sequared\u6837\u672c\u51b3\u5b9a\u7cfb\u6570\uff08R2\uff09\uff1a\u503c\u4e3a0-1\uff0c\u8d8a\u63a5\u8fd11\u8868\u793a\u62df\u5408\u8d8a\u597d\uff0c>0.8\u8ba4\u4e3a\u53ef\u4ee5\u63a5\u53d7\uff0c\u4f46\u662fR2\u968f\u56e0\u53d8\u91cf\u7684\u589e\u591a\u800c\u589e\u5927\uff0c\u89e3\u51b3\u8fd9\u4e2a\u95ee\u9898\u4f7f\u7528\u6765\u8c03\u6574
Adjust R-seqaured()
S.E of regression\u56de\u5f52\u6807\u51c6\u8bef\u5dee
Log likelihood\u5bf9\u6570\u4f3c\u7136\u6bd4\uff1a\u6b8b\u5dee\u8d8a\u5c0f\uff0cL\u503c\u8d8a\u5927\uff0c\u8d8a\u5927\u8bf4\u660e\u6a21\u578b\u8d8a\u6b63\u786e
Durbin-Watson stat\uff1aDW\u7edf\u8ba1\u91cf\uff0c0-4\u4e4b\u95f4
Mean dependent var\u56e0\u53d8\u91cf\u7684\u5747\u503c
S.D. dependent var\u56e0\u53d8\u91cf\u7684\u6807\u51c6\u5dee
Akaike info criterion\u8d64\u6c60\u4fe1\u606f\u91cf(AIC)\uff08\u8d8a\u5c0f\u8bf4\u660e\u6a21\u578b\u8d8a\u7cbe\u786e\uff09
Schwarz ctiterion:\u65bd\u74e6\u5179\u4fe1\u606f\u91cf\uff08SC\uff09\uff08\u8d8a\u5c0f\u8bf4\u660e\u6a21\u578b\u8d8a\u7cbe\u786e\uff09
Prob(F-statistic)\u76f8\u4f34\u6982\u7387
fitted(\u62df\u5408\u503c)
\u7ebf\u6027\u56de\u5f52\u7684\u57fa\u672c\u5047\u8bbe\uff1a
1.\u81ea\u53d8\u91cf\u4e4b\u95f4\u4e0d\u76f8\u5173
2.\u968f\u673a\u8bef\u5dee\u76f8\u4e92\u72ec\u7acb\uff0c\u4e14\u670d\u4ece\u671f\u671b\u4e3a0\uff0c\u6807\u51c6\u5dee\u4e3a\u03c3\u7684\u6b63\u6001\u5206\u5e03
3.\u6837\u672c\u4e2a\u6570\u591a\u4e8e\u53c2\u6570\u4e2a\u6570
\u5efa\u6a21\u65b9\u6cd5:
ls y c x1 x2 x3 ...
x1 x2 x3\u7684\u9009\u62e9\u5148\u505a\u5404\u5e8f\u5217\u4e4b\u95f4\u7684\u7b80\u5355\u76f8\u5173\u7cfb\u6570\u8ba1\u7b97\uff0c\u9009\u62e9\u540c\u56e0\u53d8\u91cf\u76f8\u5173\u7cfb\u6570\u5927\u800c\u81ea\u53d8\u91cf\u76f8\u5173\u7cfb\u6570\u5c0f\u7684\u4e00\u4e9b\u53d8\u91cf\u3002\u6a21\u578b\u7684\u5b9e\u9645\u4e1a\u52a1\u542b\u4e49\u4e5f\u6709\u6307\u5bfc\u610f\u4e49\uff0c\u6bd4\u5982m1\u540cgdp\u80af\u5b9a\u662f\u76f8\u5173\u7684\u3002
\u6a21\u578b\u7684\u5efa\u7acb\u662f\u7b80\u5355\u7684\uff0c\u590d\u6742\u7684\u662f\u6a21\u578b\u7684\u68c0\u9a8c\u3001\u8bc4\u4ef7\u548c\u4e4b\u540e\u7684\u8c03\u6574\u3001\u62e9\u4f18\u3002
\u6a21\u578b\u68c0\u9a8c\uff1a
1\uff09\u65b9\u7a0b\u663e\u8457\u6027\u68c0\u9a8c\uff08F\u68c0\u9a8c\uff09\uff1a\u6a21\u578b\u62df\u5408\u6837\u672c\u7684\u6548\u679c\uff0c\u5373\u9009\u62e9\u7684\u6240\u6709\u81ea\u53d8\u91cf\u5bf9\u56e0\u53d8\u91cf\u7684\u89e3\u91ca\u529b\u5ea6
F\u5927\u4e8e\u4e34\u754c\u503c\u5219\u8bf4\u660e\u62d2\u7edd0\u5047\u8bbe\u3002
Eviews\u7ed9\u51fa\u4e86\u62d2\u7edd0\u5047\u8bbe(\u6240\u6709\u7cfb\u7edf\u4e3a0\u7684\u5047\u8bbe)\u72af\u9519\u8bef(\u7b2c\u4e00\u7c7b\u9519\u8bef\u6216\u03b1\u9519\u8bef)\u7684\u6982\u7387(\u6536\u5c3e\u6982\u7387\u6216\u76f8\u4f34\u6982\u7387)p\u503c\uff0c\u82e5p\u5c0f\u4e8e\u7f6e\u4fe1\u5ea6(\u59820.05)\u5219\u53ef\u4ee5\u62d2\u7edd0\u5047\u8bbe\uff0c\u5373\u8ba4\u4e3a\u65b9\u7a0b\u663e\u8457\u6027\u660e\u663e\u3002
2\uff09\u56de\u5f52\u7cfb\u6570\u663e\u8457\u6027\u68c0\u9a8c\uff08t\u68c0\u9a8c\uff09\uff1a\u68c0\u9a8c\u6bcf\u4e00\u4e2a\u81ea\u53d8\u91cf\u7684\u5408\u7406\u6027
|t|\u5927\u4e8e\u4e34\u754c\u503c\u8868\u793a\u53ef\u62d2\u7edd\u7cfb\u6570\u4e3a0\u7684\u5047\u8bbe\uff0c\u5373\u7cfb\u6570\u5408\u7406\u3002t\u5206\u5e03\u7684\u81ea\u7531\u5ea6\u4e3an-p-1,n\u4e3a\u6837\u672c\u6570\uff0cp\u4e3a\u7cfb\u6570\u4f4d\u7f6e
3\uff09DW\u68c0\u9a8c\uff1a\u68c0\u9a8c\u6b8b\u5dee\u5e8f\u5217\u7684\u81ea\u76f8\u5173\u6027\uff0c\u68c0\u9a8c\u57fa\u672c\u5047\u8bbe2\uff08\u968f\u673a\u8bef\u5dee\u76f8\u4e92\u72ec\u7acb\uff09
\u6b8b\u5dee\uff1a\u6a21\u578b\u8ba1\u7b97\u503c\u4e0e\u8d44\u6599\u5b9e\u6d4b\u503c\u4e4b\u5dee\u4e3a\u6b8b\u5dee
0<=dw<=dl \u6b8b\u5dee\u5e8f\u5217\u6b63\u76f8\u5173\uff0cdu<dw<4-du \u65e0\u81ea\u76f8\u5173\uff0c 4-dl<dw<=4\u8d1f\u76f8\u5173 \uff0c\u82e5\u4e0d\u5728\u4ee5\u4e0a3\u4e2a\u533a\u95f4\u5219\u68c0\u9a8c\u5931\u8d25\uff0c\u65e0\u6cd5\u5224\u65ad
demo\u4e2d\u7684dw=0.141430 \uff0cdl=1.73369,du=1.7786,\u6240\u4ee5\u5b58\u5728\u6b63\u76f8\u5173
\u6a21\u578b\u8bc4\u4ef7
\u76ee\u7684\uff1a\u4e0d\u540c\u6a21\u578b\u4e2d\u62e9\u4f18
1\uff09\u6837\u672c\u51b3\u5b9a\u7cfb\u6570R-squared\u53ca\u4fee\u6b63\u7684R-squared
R-squared=SSR/SST \u8868\u793a\u603b\u79bb\u5dee\u5e73\u65b9\u548c\u4e2d\u7531\u56de\u5f52\u65b9\u7a0b\u53ef\u4ee5\u89e3\u91ca\u90e8\u5206\u7684\u6bd4\u4f8b\uff0c\u6bd4\u4f8b\u8d8a\u5927\u8bf4\u660e\u56de\u5f52\u65b9\u7a0b\u53ef\u4ee5\u89e3\u91ca\u7684\u90e8\u5206\u8d8a\u591a\u3002
Adjust R-seqaured=1-(n-1)/(n-k)(1-R2)
2\uff09\u5bf9\u6570\u4f3c\u7136\u503c(Log Likelihood,\u7b80\u8bb0\u4e3aL)
\u6b8b\u5dee\u8d8a\u5c0f\uff0cL\u8d8a\u5927
3\uff09AIC\u51c6\u5219
AIC= -2L/n+2k/n, \u5176\u4e2dL\u4e3a log likelihood,n\u4e3a\u6837\u672c\u603b\u91cf\uff0ck\u4e3a\u53c2\u6570\u4e2a\u6570\u3002
AIC\u53ef\u8ba4\u4e3a\u662f\u53cd\u5411\u4fee\u6b63\u7684L\uff0cAIC\u8d8a\u5c0f\u8bf4\u660e\u6a21\u578b\u8d8a\u7cbe\u786e\u3002
4\uff09SC\u51c6\u5219
SC= -2L/n + k*ln(n)/n
\u7528\u6cd5\u540cAIC\u975e\u5e38\u63a5\u8fd1
\u9884\u6d4bforecast
root mean sequared error(RMSE)\u5747\u65b9\u6839\u8bef\u5dee
Mean Absolute Error(MAE)\u5e73\u5747\u7edd\u5bf9\u8bef\u5dee
\u8fd9\u4e24\u4e2a\u53d8\u91cf\u53d6\u51b3\u4e8e\u56e0\u53d8\u91cf\u7684\u7edd\u5bf9\u503c\uff0c
MAPE(Mean Abs. Percent Error)\u5e73\u5747\u7edd\u5bf9\u767e\u5206\u8bef\u5dee\uff0c\u4e00\u822c\u7684\u8ba4\u4e3aMAPE<10\u5219\u8ba4\u4e3a\u9884\u6d4b\u7cbe\u5ea6\u8f83\u9ad8
Theil Inequality Coefficient\uff08\u5e0c\u5c14\u4e0d\u7b49\u7cfb\u6570\uff09\u503c\u4e3a0-1\uff0c\u8d8a\u5c0f\u8868\u793a\u62df\u5408\u503c\u548c\u771f\u5b9e\u503c\u5dee\u5f02\u8d8a\u5c0f\u3002
\u504f\u5dee\u7387(bias Proportion)\uff0cbp\uff0c\u53cd\u6620\u9884\u6d4b\u503c\u548c\u771f\u5b9e\u503c\u5747\u503c\u95f4\u7684\u5dee\u5f02
\u65b9\u5dee\u7387(variance Proportion)\uff0cvp\uff0c\u53cd\u6620\u9884\u6d4b\u503c\u548c\u771f\u5b9e\u503c\u6807\u51c6\u5dee\u7684\u5dee\u5f02
\u534f\u53d8\u7387(covariance Proportion)\uff0ccp\uff0c\u53cd\u6620\u4e86\u5269\u4f59\u7684\u8bef\u5dee
\u4ee5\u4e0a\u4e09\u9879\u76f8\u52a0\u7b49\u4e8e1\u3002
\u9884\u6d4b\u6bd4\u8f83\u7406\u60f3\u662fbp,vp\u6bd4\u8f83\u5c0f\uff0c\u503c\u96c6\u4e2d\u5728cp\u4e0a\u3002
eviews\u4e0d\u80fd\u76f4\u63a5\u8ba1\u7b97\u51fa\u9884\u6d4b\u503c\u7684\u7f6e\u4fe1\u533a\u95f4\uff0c\u9700\u8981\u901a\u8fc7\u7f6e\u4fe1\u533a\u95f4\u7684\u4e0a\u4e0b\u9650\u516c\u5f0f\u6765\u8ba1\u7b97\u3002\u5982\u4f55\u64cd\u4f5c\uff1f
\u5176\u4ed6
1)Chow\u68c0\u9a8c
chow's breakpoint\u68c0\u9a8c
\u96f6\u5047\u8bbe\u662f\uff1a\u4e24\u4e2a\u5b50\u6837\u672c\u62df\u5408\u7684\u65b9\u7a0b\u65e0\u663e\u8457\u5dee\u5f02\u3002\u6709\u5dee\u5f02\u5219\u8bf4\u660e\u5173\u7cfb\u4e2d\u7ed3\u6784\u53d1\u751f\u6539\u53d8
demo\u4e2d
Chow Breakpoint Test: 1977Q1
F-statistic 2.95511837136742 Prob. F(3,174) 0.0339915698953355
Log likelihood ratio 8.94507926849178 Prob. Chi-Square(3) 0.0300300700620291
p\u503c<0.05\uff0c\u53ef\u62d2\u7edd0\u5047\u8bbe\uff0c\u5373\u8ba4\u4e3a\u5404\u4e2a\u56e0\u7d20\u7684\u5f71\u54cd\u5f3a\u5f31\u53d1\u751f\u4e86\u6539\u53d8\u3002
\u95ee\u9898\u662f\u5982\u4f55\u624d\u80fd\u51c6\u786e\u7684\u627e\u5230\u8fd9\u4e2a\u6216\u8fd9\u51e0\u4e2a\u65ad\u70b9\uff1f\u76ee\u524d\u7684\u65b9\u6cd5\u662f\u627e\u6b8b\u5dee\u6269\u5927\u8d85\u51fa\u8fb9\u7ebf\u7684\u90a3\u4e2a\u70b9\uff0c\u4f46\u8fd9\u662f\u4e0d\u51c6\u786e\u7684\uff0c\u5728demo\u4e2d1975Q2\u7684\u6b8b\u5dee\u8d85\u51fa\uff0c\u4f46\u662fchow's breakpoint\u68c0\u9a8c\u7684\u4e24\u4e2ap\u503c\u90fd\u63a5\u8fd10.2\uff0c1976Q3\u5f00\u59cb\u4e24\u4e2ap\u503c\u624d\u5c0f\u4e8e0.05\uff0c\u5e76\u4e14\u6709\u9010\u6e10\u51cf\u5c0f\u4e4b\u52bf\u3002
chow's forecast\u68c0\u9a8c
\u7528\u65ad\u70b9\u9694\u65ad\u6837\u672c\uff0c\u7528\u4e4b\u524d\u7684\u6837\u672c\u5efa\u7acb\u56de\u5f52\u6a21\u578b\uff0c\u7136\u540e\u7528\u8fd9\u4e2a\u6a21\u578b\u5bf9\u540e\u4e00\u6bb5\u8fdb\u884c\u9884\u6d4b\uff0c\u68c0\u9a8c\u8fd9\u4e2a\u6a21\u578b\u5bf9\u540e\u7eed\u6837\u672c\u7684\u62df\u5408\u7a0b\u5ea6\u3002
0\u5047\u8bbe\u662f\uff1a\u6a21\u578b\u4e0e\u540e\u6bb5\u6837\u672c\u65e0\u663e\u8457\u5dee\u5f02
demo\u4e2d\u76841976Q4\u4f5c\u4e3abreak point,\u5f97\u5230\u4e24\u4e2ap\u503c\u4e3a0\uff0c\u5373\u8ba4\u4e3a\u4e24\u6bb5\u6837\u672c\u7684\u7cfb\u6570\u5e94\u8be5\u662f\u4e0d\u540c\u7684\u3002
2\uff09\u81ea\u53d8\u91cf\u7684\u9009\u62e9
testadd\u68c0\u9a8c\uff1a
\u64cd\u4f5c\u65b9\u6cd5\u662f: eqation name.testadd ser1 ser2 ...
0\u5047\u8bbe\uff1a\u5e94\u8be5\u5c06\u8be5\u53d8\u91cf\u5f15\u5165\u65b9\u7a0b
\u68c0\u9a8c\u7edf\u8ba1\u91cf\uff1awald,LR
\u7ed3\u679c\uff1a\u901a\u8fc7\u4e24\u4e2ap\u503c(Prob. F,Prob Chi-sequare)\u770b\u662f\u5426\u62d2\u7edd\u539f\u5047\u8bbe
testdrop\u68c0\u9a8c\uff1a
\u64cd\u4f5c\u65b9\u6cd5\u662f: eqation name.testdrop ser1 ser2 ...
0\u5047\u8bbe\uff1a\u5e94\u8be5\u5c06\u8be5\u53d8\u91cf\u5254\u9664
\u68c0\u9a8c\u7edf\u8ba1\u91cf\uff1awald,LR
\u7ed3\u679c\uff1a\u901a\u8fc7\u4e24\u4e2ap\u503c(Prob. F,Prob Chi-sequare)\u770b\u662f\u5426\u62d2\u7edd\u539f\u5047\u8bbe
\u542b\u5b9a\u6027\u53d8\u91cf\u7684\u56de\u5f52\u6a21\u578b
\u5206\u4e3a\uff1a\u81ea\u53d8\u91cf\u542b\u5b9a\u6027\u53d8\u91cf\uff0c\u56e0\u53d8\u91cf\u542b\u5b9a\u6027\u53d8\u91cf\u3002\u540e\u4e00\u79cd\u60c5\u51b5\u8f83\u4e3a\u590d\u6742
\u5efa\u7acbdummy \u53d8\u91cf(\u540d\u4e49\u53d8\u91cf)\uff1a\u7528D\u8868\u793a
\u5f53\u53d8\u91cf\u6709m\u79cd\u60c5\u51b5\u65f6\uff0c\u9700\u8981\u5f15\u5165m-1\u4e2adummy\u53d8\u91cf
\u5904\u7406\u529e\u6cd5\uff1a\u628a\u5b9a\u6027\u53d8\u91cf\u5b9a\u4e49\u62100.1.2\u7b49\u6570\u503c\u540e\u548c\u4e00\u822c\u53d8\u91cf\u540c\u6837\u5904\u7406
\u5e38\u89c1\u95ee\u9898\u53ca\u5bf9\u7b56
1\uff09\u591a\u91cd\u5171\u7ebf\u6027\uff08multicollinearity\uff09:
p\u4e2a\u56de\u5f52\u53d8\u91cf\u4e4b\u95f4\u5b58\u5728\u4e25\u683c\u6216\u8fd1\u4f3c\u7684\u7ebf\u6027\u5173\u7cfb
\u8bca\u65ad\u65b9\u6cd5\uff1a
1.\u5982\u679c\u6a21\u578b\u7684R-sequared\u5f88\u5927\uff0cF\u68c0\u9a8c\u901a\u8fc7\uff0c\u4f46\u662f\u67d0\u4e9b\u7cfb\u7edf\u7684t\u68c0\u9a8c\u6ca1\u901a\u8fc7
2.\u67d0\u4e9b\u81ea\u53d8\u91cf\u7cfb\u6570\u4e4b\u95f4\u7684\u7b80\u5355\u76f8\u5173\u7cfb\u6570\u5f88\u5927
3.\u56de\u5f52\u7cfb\u6570\u7b26\u53f7\u4e0e\u7b80\u5355\u76f8\u5173\u7cfb\u7edf\u7b26\u53f7\u76f8\u53cd
\u4ee5\u4e0a3\u6761\u53d1\u751f\u90fd\u6709\u7406\u7531\u6000\u7591\u5b58\u5728\u591a\u91cd\u5171\u7ebf\u6027
\u65b9\u5dee\u6269\u5927\u56e0\u5b50(variance inflation factor VIFj)\u662f\u8bca\u65ad\u591a\u91cd\u5171\u7ebf\u6027\u7684\u5e38\u7528\u624b\u6bb5\u3002
VIFj\u4e3a\u77e9\u9635(X\u2019 X)-1\u7b2cj\u4e2a\u5bf9\u89d2\u5143\u7d20cjj=1/(1-R2j)(j=1,2\u2026,p)
\u5176\u4e2dR2j\u4e3a\u4ee5\u4f5c\u4e3acj\u56e0\u53d8\u91cf\uff0c\u5176\u4f59p-1\u4e2a\u81ea\u53d8\u91cf\u4f5c\u4e3a\u81ea\u53d8\u91cf\u5efa\u7acb\u591a\u5143\u56de\u5f52\u6a21\u578b\u6240\u5f97\u7684\u6837\u672c\u51b3\u5b9a\u7cfb\u6570\uff0c\u6240\u4ee5R2j\u8d8a\u5927\u5219\u8bf4\u660e\u81ea\u53d8\u91cf\u4e4b\u95f4\u81ea\u76f8\u5173\u6027\u8d8a\u5927\uff0c\u6b64\u65f6\u4e5f\u8d8a\u5927\uff0c\u53ef\u4ee5\u8ba4\u4e3aVIFj>10(R2j>0.9)\u5219\u5b58\u5728\u591a\u91cd\u5171\u7ebf\u6027\u3002
\u8fd8\u53ef\u4ee5\u4f7f\u7528VIFj\u7684\u5e73\u5747\u6570\u4f5c\u4e3a\u5224\u65ad\u6807\u51c6\uff0c\u5982\u679cavg(VIFj)\u8fdc\u5927\u4e8e10\u5219\u8ba4\u4e3a\u5b58\u5728\u591a\u91cd\u5171\u7ebf\u6027\u3002
eviews\u91cc\u5982\u4f55\u4f7f\u7528VIF\u6cd5\uff1f--\u5efa\u7acb\u65b9\u7a0b\uff0c\u7136\u540e\u624b\u5de5\u5efa\u7acbscalar vif\u3002demo\u4e2dGDP\u548cPR\u7684vif\u4e3a66\uff0c\u5b58\u5728\u591a\u91cd\u5171\u7ebf\u6027? \u53ea\u6709\u4e00\u4e2a\u81ea\u53d8\u91cf\u7684\u65b9\u7a0b\u662f\u5426\u4f1a\u5931\u6548?\u6b64\u65f6dw\u503c\u53ea\u67090.01\u8fdc\u5c0f\u4e8edl\uff0c\u8bf4\u660eGDP\u8fdc\u8fdc\u4e0d\u662fPR\u80fd\u51b3\u5b9a\u7684\u3002\u7ed3\u5408testdrop\u5c06PR\u53bb\u9664\uff0c\u4e24\u4e2ap\u503c\u4e3a0\uff0c\u8bf4\u660e\u4e0d\u80fd\u628aPR\u53bb\u9664\u3002
\u5728eviews\u4e2d\u5f53\u81ea\u53d8\u91cf\u5b58\u5728\u4e25\u91cd\u7684\u591a\u91cd\u5171\u7ebf\u6027\u65f6\u5c06\u4e0d\u80fd\u7ed9\u51fa\u53c2\u6570\u4f30\u8ba1\u503c\uff0c\u800c\u4f1a\u62a5\u9519\uff1anearly singular matrix
\u591a\u91cd\u5171\u7ebf\u6027\u7684\u5904\u7406\uff1a
1.\u5254\u9664\u81ea\u53d8\u91cf\uff0c\u9009\u62e9\u901a\u8fc7testdrop\u5b9e\u9a8c\uff0c\u5e76\u4e14vif\u503c\u6700\u5927\u7684\u90a3\u4e2a
2.\u5dee\u5206\u6cd5\uff0c\u5728\u5efa\u7acb\u65b9\u7a0b\u65f6\u586b\u5165 ls m1-m1(-1) c gdp-gdp(-1) pr-pr(-1)\u3002m1(-1)\u8868\u793a\u4e0a\u4e00\u4e2am1
\u5dee\u5206\u6cd5\u5e38\u5e38\u4f1a\u4e22\u5931\u4e00\u4e9b\u4fe1\u606f\uff0c\u4f7f\u7528\u65f6\u5e94\u8c28\u614e\u3002 demo\u4e2d\u5f97\u5230\u7684\u6a21\u578b\uff0cc \u7684p\u503c0.11, pr-pr(-1)\u7684p\u503c\u4e3a0.60\uff0c\u8bf4\u660e\u53c2\u6570\u65e0\u6548\u3002
2\uff09\u5f02\u65b9\u5dee\u6027\uff08Herteroskedasticity\uff09
\u5373\u968f\u673a\u8bef\u5dee\u9879\u4e0d\u6ee1\u8db3\u57fa\u672c\u5047\u8bbe\u7684\u540c\u65b9\u5dee\u6027,\u5f02\u65b9\u5dee\u6027\u8bf4\u660e\u968f\u673a\u8bef\u5dee\u4e2d\u6709\u4e9b\u9879\u5bf9\u56e0\u53d8\u91cf\u7684\u5f71\u54cd\u662f\u4e0d\u540c\u4e8e\u5176\u4ed6\u9879\u7684\u3002
\u4e00\u822c\u5730\uff0c\u622a\u9762\u6570\u636e\u505a\u6837\u672c\u65f6\u51fa\u73b0\u5f02\u65b9\u5dee\u6027\u7684\u53ef\u80fd\u8f83\u5927\uff0c\u6216\u8005\u8bf4\u90fd\u5b58\u5728\u5f02\u65b9\u5dee\u6027
\u82e5\u5b58\u5728\u5f02\u65b9\u5dee\u6027\uff0c\u7528OLS\u4f30\u8ba1\u51fa\u6765\u7684\u53c2\u6570\uff0c\u53ef\u80fd\u5bfc\u81f4\u4f30\u8ba1\u503c\u867d\u7136\u662f\u65e0\u504f\u7684\uff0c\u4f46\u4e0d\u662f\u6709\u6548\u7684\u3002
\uff08\u622a\u9762\u6570\u636e\u5c31\u662f\u540c\u4e00\u65f6\u95f4\u70b9\u4e0a\u5404\u4e2a\u4e3b\u4f53\u7684\u6570\u636e\uff0c\u6bd4\u59822007\u5e74\u5404\u7701\u7684GDP\u6570\u636e\u653e\u5728\u4e00\u8d77\u5c31\u662f\u4e00\u7ec4\u622a\u9762\u6570\u636e
\u4e0e\u4e4b\u76f8\u5bf9\u7684\u662f\u65f6\u95f4\u5e8f\u5217\u6570\u636e \u5982\u6cb3\u5317\u7701\u4ece00\u5e74\u523007\u5e74\u7684\u6570\u636e\u5c31\u662f\u4e00\u7ec4\u65f6\u95f4\u5e8f\u5217\u6570\u636e
\u4e24\u8005\u7efc\u5408\u53eb\u9762\u677f\u6570\u636e \uff09
00\u5e74\u523007\u5e74\u5404\u7701\u7684\u6570\u636e\u7efc\u5408\u5728\u4e00\u8d77\u5c31\u53eb\u9762\u677f\u6570\u636e
\u8bca\u65ad\u65b9\u6cd5\uff1a
1.\u56fe\u793a\u6cd5\uff0c\u4ee5\u56e0\u53d8\u91cf\u4f5c\u4e3a\u6a2a\u5750\u6807\uff0c\u4ee5\u6b8b\u5dee\u9879\u4e3a\u7eb5\u5750\u6807\uff0c\u6839\u636e\u6563\u70b9\u56fe\u5224\u65ad\u662f\u5426\u5b58\u5728\u76f8\u5173\u6027\u3002
(\u9009\u62e9\u4e24\u4e2a\u5e8f\u5217\u4f5c\u4e3agroup\u6253\u5f00\uff0c\u5148\u9009\u4e2d\u7684\u5e8f\u5217\u5c06\u4f5c\u4e3agroup\u7684\u7eb5\u5750\u6807)
2.\u6208\u91cc\u745f(Glejser)\u68c0\u9a8c\uff1a
??
3.\u6000\u7279(White)\u68c0\u9a8c:
\u7528e2\u4f5c\u4e3a\u56e0\u53d8\u91cf\uff0c\u539f\u5148\u7684\u81ea\u53d8\u91cf\u53ca\u81ea\u53d8\u91cf\u7684\u5e73\u65b9(\u8fd8\u53ef\u4ee5\u52a0\u4e0a\u5404\u81ea\u53d8\u91cf\u4e4b\u95f4\u7684\u76f8\u4e92\u4e58\u79ef)\u4f5c\u4e3a\u81ea\u53d8\u91cf \u5efa\u7acb\u6a21\u578b\u3002
\u6000\u7279\u68c0\u9a8c\u7684\u7edf\u8ba1\u91cf\u4e3a\uff1am=n*R2(n\u662f\u6837\u672c\u5bb9\u91cf\uff0cR2\u662f\u65b0\u6a21\u578b\u7684\u62df\u5408\u4f18\u5ea6), m~ \u03c72(k) k\u4e3a\u65b0\u6a21\u578b\u9664\u5e38\u6570\u9879\u4e4b\u5916\u7684\u81ea\u53d8\u91cf\u4e2a\u6570
\u96f6\u5047\u8bbe\uff1a\u6a21\u578b\u4e0d\u5b58\u5728\u5f02\u65b9\u5dee\u6027
\u64cd\u4f5c\uff1a\u5728\u4f30\u8ba1\u51fa\u6765\u7684\u65b9\u7a0b\u4e2d\uff0cview-residual tests-White Herteroskedasticity(no cross/cross) \u5206\u522b\u4e3a\u662f\u5426\u542b\u81ea\u53d8\u91cf\u4ea4\u53c9\u9879
demo\u4e2d\u7684\u4e24\u4e2ap\u503c\u4e3a0\uff0c\u6240\u4ee5\u62d2\u7edd\u96f6\u5047\u8bbe\uff0c\u8ba4\u4e3a\u5b58\u5728\u4e25\u91cd\u7684\u5f02\u65b9\u5dee\u6027\u3002
\u5f02\u65b9\u5dee\u6027\u7684\u5904\u7406\uff1a
1.\u52a0\u6743\u6700\u5c0f\u4e8c\u4e58\u6cd5(WLS weighted least sequare)\u3002
\u6700\u5e38\u7528\u7684\u65b9\u6cd5\uff0c\u4e00\u822c\u7528\u4e8e\u5f02\u65b9\u5dee\u5f62\u5f0f\u53ef\u77e5\u7684\u60c5\u51b5\u3002\u57fa\u672c\u601d\u8def\u662f\u8d4b\u4e88\u6b8b\u5dee\u7684\u6bcf\u4e2a\u89c2\u6d4b\u503c\u4e0d\u540c\u7684\u6743\u6570\uff0c\u4ece\u800c\u4f7f\u6a21\u578b\u7684\u968f\u673a\u8bef\u5dee\u9879\u5177\u6709\u76f8\u540c\u7684\u65b9\u5dee\u3002
2.\u81ea\u76f8\u5173\u76f8\u5bb9\u534f\u65b9\u5dee(Heteroskedasticity and antocorrelation consistent convariances HAC)
\u7528\u4e8e\u5f02\u65b9\u5dee\u6027\u5f62\u5f0f\u672a\u77e5\u65f6\u3002\u5728\u5efa\u6a21\u65f6\u5728options\u4e2d\u9009\u62e9Heteroskedasticity consistent convariances \u518d\u4ecewhite,newey-west\u4e2d\u9009\u62e9\u4e00\u79cd\u3002
HAC\u4e0d\u6539\u53d8\u53c2\u6570\u7684\u70b9\u4f30\u8ba1\uff0c\u6539\u53d8\u7684\u77e5\u8bc6\u4f30\u8ba1\u6807\u51c6\u5dee\u3002\u5982\u4f55\u6539\u53d8\u6807\u51c6\u5dee\uff1f
3\uff09\u81ea\u76f8\u5173\u6027
\u6b8b\u5dee\u9879\u4e0d\u6ee1\u8db3\u76f8\u4e92\u72ec\u7acb\u7684\u5047\u8bbe\u3002\u4e00\u822c\u7684\uff0c\u7ecf\u6d4e\u65f6\u95f4\u5e8f\u5217\u4e2d\u81ea\u76f8\u5173\u73b0\u8c61\u8f83\u4e3a\u5e38\u89c1\uff0c\u8fd9\u4e3b\u8981\u662f\u7ecf\u6d4e\u53d8\u91cf\u7684\u6ede\u540e\u6027\u5e26\u6765\u7684\u3002
\u81ea\u76f8\u5173\u6027\u5c06\u5bfc\u81f4\u53c2\u6570\u4f30\u8ba1\u503c\u867d\u7136\u662f\u65e0\u504f\u7684\uff0c\u4f46\u4e0d\u662f\u6709\u6548\u7684\u3002
\u8bca\u65ad\u65b9\u6cd5\uff1a
1.\u7ed8\u5236\u6b8b\u5dee\u5e8f\u5217\u56fe\u3002\u5982\u679c\u5e8f\u5217\u56fe\u6210\u952f\u9f7f\u5f62\u6216\u5faa\u73af\u72b6\u7684\u53d8\u5316\uff0c\u53ef\u4ee5\u5224\u5b9a\u5b58\u5728\u81ea\u76f8\u5173
2.\u56de\u5f52\u68c0\u9a8c\u6cd5\uff1a
\u4ee5\u6b8b\u5deee(t)\u4e3a\u88ab\u89e3\u91ca\u53d8\u91cf\uff0c\u4ee5\u5404\u79cd\u53ef\u80fd\u7684\u76f8\u5173\u53d8\u91cf\uff0c\u5982 e(t-1) e(t-2)\u4f5c\u4e3a\u81ea\u53d8\u91cf\uff0c\u9009\u62e9\u663e\u8457\u7684\u6700\u4f18\u62df\u5408\u6a21\u578b\u4f5c\u4e3a\u81ea\u76f8\u5173\u7684\u5f62\u5f0f\u3002
demo\u4e2d\u4ee5 ls residm1 c residm1(-1) residm1(-2)\u540e \u53d1\u73b0c\u7684p\u503c\u4e3a0.54\uff0c\u505atestdrop\u5b9e\u9a8c\uff0c\u4e24\u4e2ap\u503c\u90fd>0.5 \u53ef\u4ee5\u5c06c\u5254\u9664\u3002\u5254\u9664c\u540e\uff1a
Dependent Variable: RESIDM1
Method: Least Squares
Date: 12/29/07 Time: 11:26
Sample (adjusted): 1952Q3 1996Q4
Included observations: 178 after adjustments
Variable Coefficient Std. Error t-Statistic Prob.
RESIDM1(-1) 1.215361 0.077011 15.78173 0.0000
RESIDM1(-2) -0.271664 0.078272 -3.470763 0.0007
R-squared 0.868569 Mean dependent var 0.011855
Adjusted R-squared 0.867823 S.D. dependent var 26.91138
S.E. of regression 9.783961 Akaike info criterion 7.410538
Sum squared resid 16847.76 Schwarz criterion 7.446289
Log likelihood -657.5379 Durbin-Watson stat 2.057531
\u6a21\u578b\u7684r-sequared\u7a0d\u5c0f\uff0c\u53c2\u6570\u5f88\u663e\u8457\uff0cdw\u663e\u793a\u4e3a\u65e0\u81ea\u76f8\u5173\u3002
\u4f46\u662f\u5e38\u6570c\u80fd\u5254\u9664\u5417\uff1f\u5254\u9664\u540e\u6a21\u578b\u6ca1\u6709f-statistic\u548c\u5bf9\u5e94p\u503c\uff0c\u539f\u7406\u4f55\u5728\uff1f
3.DW\u68c0\u9a8c\u6cd5
\u7528\u4e8e\u5c0f\u6837\u672c\u7684\u4e00\u9636\u81ea\u76f8\u5173\u60c5\u51b5\uff0c\u7f3a\u70b9\uff1a\u5f53\u56de\u5f52\u65b9\u7a0b\u53f3\u8fb9\u5b58\u5728\u56e0\u53d8\u91cf\u7684\u6ede\u540e\u9879\u5982m1(t-i) (i=1,2,...)\u65f6\uff0c\u68c0\u9a8c\u5931\u8d25\u3002
\u89e3\u51b3\u529e\u6cd5\uff1a
1.\u5dee\u5206\u6cd5
\u7528\u589e\u91cf\u6570\u636e\u4ee3\u66ff\u539f\u6765\u7684\u6837\u672c\u6570\u636e\uff0c\u8f83\u597d\u7684\u514b\u670d\u4e86\u81ea\u76f8\u5173\uff0c\u4f46\u662f\u6539\u53d8\u4e86\u539f\u65b9\u7a0b\u7684\u5f62\u5f0f\uff0c\u610f\u4e49\u4e0d\u5927\u3002
2.Cochrane-Orcutt\u8fed\u4ee3\u6cd5
\u4e0d\u80fd\u6709\u5e38\u6570\u9879!\u9a8c\u8bc1\u4e86\u56de\u5f52\u68c0\u9a8c\u7684\u4e2d\u7684\u505a\u6cd5\u3002
\u60a8\u597d\uff0c\u73b0\u5728\u4f60\u4f1a\u4e86\u5417\uff0c\u6211\u9047\u5230\u540c\u6837\u95ee\u9898 \u4e0d\u4f1a
你把定性变量序列按照常规变量的方式输入在workfile中，然后在输入估计参数时正常调用就行了。比如自变量x1 x2 因变量y,在估计时输入参数y c x1 x2得到结果。绛旓細宀鍥炲綊鏄竴绉嶄笓鐢ㄤ簬鍏辩嚎鎬ф暟鎹垎鏋愮殑鏈夊亸浼拌鍥炲綊鏂规硶锛岄氳繃鏀惧純鏈灏忎簩涔樻硶鐨勬棤鍋忔э紝浠ユ崯澶遍儴鍒嗕俊鎭侀檷浣庣簿搴︿负浠ｄ环鑾峰緱鍥炲綊绯绘暟锛屽鐥呮佹暟鎹殑鎷熷悎瑕佸己浜庢渶灏忎簩涔樻硶銆傦紙浠ヤ笂浠嬬粛鏉ヨ嚜鐧剧锛夊墠闈粙缁嶄簡鍩烘湰鐨勬搷浣滃拰濡備綍浣跨敤Eviews 7鍋氳嚜鐩稿叧闂鐨勬楠岋紝浠婂ぉ鎴戜滑灏辨潵浠嬬粛宀洖褰掔殑鍋氭硶銆備篃璁镐細鏈変笉瓒筹紝...
绛旓細寤烘ā鐨勬椂鍊欙紝涓よ呮湁鍖哄埆銆備絾濡傛灉宸茬粡鍒颁簡鐢eviews鍋鍥炲綊鐨勯樁娈碉紝閭ｈ繖涓や釜鎸囩殑鏄悓涓涓剰鎬濄
绛旓細缁撴灉涓嶉敊锛屽ぇ澶氭暟鑷彉閲閫氳繃鏄捐憲鎬ф楠屻傛嫙鍚堜紭搴︿笉澶珮锛0.51锛屼絾瀵逛簬鎴潰鏁版嵁锛岃繕绠椾笉閿欑殑銆傚叾瀹冪粏鑺傦紝鍝笉鏄庣櫧闂摢鍎裤
绛旓細绗1绔 EViews杞欢浣跨敤鍒濇1.1 宸ヤ綔鏂囦欢鍙婂缓绔1.2 搴忓垪瀵硅薄鐨勫熀鏈搷浣1.3 鏁版嵁鍒嗘瀽鐨勫父鐢ㄦ搷浣1.4 搴忓垪鐨勬弿杩扮粺璁″垎鏋愮2绔 绾挎у洖褰掑垎鏋2.1 绾挎у洖褰掓杩2.2 甯歌妫楠2.3 寤烘ā鍩烘湰姝ラ鍜Eviews鎿嶄綔2.4 鑷彉閲忕殑閫夋嫨2.5 棰勬祴2.6 鍚畾鎬ц嚜鍙橀噺鐨勫洖褰妯″瀷绗3绔 绾挎у洖褰掗棶棰樹笌闈炵嚎鎬у洖褰掑垎鏋3.1...
绛旓細eviews鍥炲綊f鍊兼槸鐢ㄦ潵璇勪及鍥炲綊鐨勪竴绉嶇粺璁℃寚鏍囷紝瀹冨彲浠ュ弽鏄犲洖褰掔殑鎷熷悎鑳藉姏銆備竴鑸潵璇达紝f鍊艰秺澶э紝鍥炲綊鐨勬嫙鍚堣兘鍔涜秺寮猴紝鎷熷悎绋嬪害瓒婇珮銆備笉鍚岀殑搴旂敤鍦烘櫙闇瑕佸悎閫傜殑f鍊硷紝涓鑸潵璇达紝濡傛灉f鍊间綆浜2锛屽氨琛ㄦ槑鍥炲綊鐨勬嫙鍚堣兘鍔涜緝寮憋紝濡傛灉f鍊奸珮浜4锛屽氨琛ㄦ槑鎷熷悎鑳藉姏杈冨己銆傛澶栵紝f鍊煎彈鍒鍥炲綊鐨勮嚜鍙橀噺鐨鏁伴噺鐨勫奖鍝嶏紝鑷彉閲忚秺澶...
绛旓細鐪嬫潵瀛﹁繖涓笉灏戝晩锛岃〃涓婇潰鐨勪笉鐢ㄨВ閲婁簡鍚э紝鍥犲彉閲忋佹渶灏忎簩涔樻硶銆佹牱鏈暟鍜岃娴嬪笺侰浠ｈ〃甯告暟椤癸紝涓嬮潰涓や釜鏄鑷彉閲銆傚悗闈竴鏍忔槸绯绘暟锛岀劧鍚庢槸鏍囧噯璇拰T缁熻閲忥紝浠庢渶鍚庝竴鏍忕殑P鍊煎彲浠ョ湅鍑哄悇鑷彉閲忛兘瀵瑰洜鍙橀噺鏈夋樉钁楀奖鍝嶃備笅闈²鏄ā鍨嬫嫙鍚堝害鎸囨爣锛屾帴杩100/100锛屽啀鐪嬩笅闈㈢殑璋冩暣鍚庣殑R²渚濈劧濡傛...
绛旓細浣犲仛鍥炲綊鐢ㄧ殑鑷彉閲閲岄潰鏈変竴涓槸瀛楃鍙橀噺锛屼絾鏄浣犵敤浣滀簡铏氭嫙鍙橀噺锛eviews涓嶈兘澶勭悊浠ュ瓧绗﹀瀷鍙橀噺涓鸿嚜鍙橀噺锛堟垨鍥犲彉閲忥級鐨勫洖褰鏂圭▼锛屾墍浠ヤ綘闇瑕佽浆鎹竴涓嬶紝eviews鎻愮ず浣犱娇鐢ˊexpand鍑芥暟 浠庢埅鍥句笂鐪嬩綘鐢ㄧ殑搴旇鏄痚views5.x鐗堟湰锛屽叿浣撴潵璇达紝浣犲彉閲弝鏄瓧绗﹀彉閲忥紙浠庢埅鍥剧殑y鐨刬con鍙互鐪嬪嚭锛夛紝涓嶅Θ鍋囪浣犵敤y涓...
绛旓細浣犲彲浠ュ厛閫氳繃绠鍗曠浉鍏崇湅涓涓嬶紝鑷彉閲涔嬮棿鐨勭浉鍏虫у浣曪紝濡傛灉鐩稿叧鎬ч潪甯稿ぇ锛岄偅鑷劧浼氬鑷鍥炲綊鍒嗘瀽鍑虹幇寮傚父銆傝澶勭悊鍏辩嚎鎬х殑璇濓紝涓绉嶇畝鍗曠矖鏆寸殑鏂瑰紡鏄妸鏈夐潪甯告樉钁楃浉鍏崇殑涓涓彉閲忓幓鎺夛紝涓嶆槸寰堢瀛︼紱鍙︿竴绉嶇瀛︾殑鏂规硶鏄 閲囩敤宀洖褰 鎴栬 鍏堝鑷彉閲忚繘琛屼富鎴愬垎鍒嗘瀽锛屼箣鍚庣敤涓绘垚鍒嗚繘琛屽洖褰 ...
绛旓細鎵浠鍙橀噺鍥炲綊瀵规牱鏈殑鎷熷悎绋嬪害杈冮珮 3 妫楠屾槸鍚﹀瓨鍦ㄨ嚜鐩稿叧鎬 鐪婦urbin-waston stat 鍊 DW 搴斿睘浜0~4涔嬮棿锛屾暟鍊艰秺灏忚鏄庢ā鍨嬮殢鏈鸿宸」鑷浉鍏冲害瓒婂皬銆傚弽涔嬪垯瓒婂ぇ銆侱W=0.731701 鍦0~4涔嬮棿銆備笖鍏跺艰緝灏忥紝鍥犳鑷浉鍏抽兘杈冨皬 4 妫楠屾槸鍚﹀瓨鍦ㄥ紓鏂瑰樊鎬 锛堣繖闇瑕佸湪eviews閲鍦ㄨ繘琛岃绠 銆傛湁鍥惧舰娉曘...
绛旓細鍙互浣跨敤EViews涓殑鍥炲綊鍒嗘瀽鍔熻兘鏉ュ垎鏋愬瀹跺叕鍙稿涓彉閲忎笌鏌愪釜閲忎箣闂淬佸骞撮棿鐨勬暟鎹殑鐩稿叧鎬с傞鍏堬紝灏嗗瀹跺叕鍙稿骞寸殑x鍜寉鏁版嵁瀵煎叆EViews涓紝鐒跺悗鍦‥Views涓缃洖褰掓ā鍨嬶紝灏唜1,x2,x3绛夊涓彉閲忎綔涓鑷彉閲锛寉浣滀负鍥犲彉閲忥紝杩愯鍥炲綊鍒嗘瀽锛屽氨鍙互寰楀埌澶氬鍏徃澶氫釜鍙橀噺涓庢煇涓噺涔嬮棿銆佸骞撮棿鐨勬暟鎹殑鐩稿叧鎬...
