1. scalar t=@qtdist(0.05,5)

没错,在這裡 5 ,指的就是T-DIST. DOF

2. scalar g=@qged(0.05,1.5)

在這裡 1.5 ,指的是GED PARAMETER

若还有疑问请参考EViews 5 Command Ref page-554

至于scalar请参考EViews 5 Command Ref page-410

3.另看了你的附件,作者实证时,有不同的样本量比较,

所以GED parameter不同,当然分位数不同.

[此贴子已经被作者于2007-5-18 7:46:22编辑过]

1.@qtdist(p,v)

p is probability

v is Degree of Freedom 也就是shape parameter

当v>=30时, 趋近于normal dist.

2.@qged(p,r)

p is probability

r is GED parameter 也就是shape parameter

当r=2时,是normal dist.

3.另hull的书是英文第五版的电子书

兄弟，现在我想要问的是自由度怎么确定啊

我知道的t-distribution pdf 有v自由度参数.

ged distribution pdf 有r 形状参数.

况且e-views @qged(p,r)已说明的很清楚,

只要 p and r 就可以算出分位数了.

(r你应该自己在程序中估计出来了)

还不够清楚?

[此贴子已经被作者于2007-5-20 7:51:29编辑过]

那我该怎么将多scalar t=@qdist（p，r）加到你给我的那个程序中去呢？谢了

这是你给我的程序：' Program to estimate a GARCH(1,1)-t model on the series fa.

'%path = @runpath+"../data/"
'cd %path
load jjsj
series d1 = 0
smpl @first @first
d1 = 1
smpl @all

'get starting values from Gaussian ARCH
equation eq1
eq1.arch fa c
show eq1.output
'declare and innitialize parameters
coef(1) mu = eq1.c(1)
coef(1) omega = eq1.c(2)
coef(1) alpha =eq1.c(3)
coef(1) beta =eq1.c(4)
coef(1) tdf=3

' Define pi
!pi=@acos(-1)

'set up GARCH(1,1)-t likelihood
logl ll_l
ll_l.append @logl logl
ll_l.append res=fa-mu(1)
ll_l.append sig2 =@recode(d1=1,omega(1)/(1-alpha(1)-beta(1)),omega(1)+alpha(1)*res(-1)^2+beta(1)*sig2(-1))
ll_l.append z =res^2/sig2/(tdf(1)-2)+1
ll_l.append logl = @gammalog((tdf(1)+1)/2)-@gammalog(tdf(1)/2)-log(!pi)/2-log(tdf(1)-2)/2-log(sig2)/2 - (tdf(1)+1)*log(z)/2

'estimate and display output
ll_l.ml(showopts,m=1000,c=1e-5)
show ll_l.output

那我该怎么将多scalar t=@qdist（p，r）加到你给我的那个程序中去呢？才能得直接出分位数呢？谢了

下面这几句话是什么意思呢？

series d1 = 0
smpl @first @first
d1 = 1
smpl @all

序列d1=0是什么意思呢？@first 又是什么函数呢？是不是在定义样本初值？为什么又让他们等于0又等于1呢？

[此贴子已经被作者于2007-5-18 16:57:59编辑过]

1.在程序最后面,加入这一行

scalar quantile=@qtdist(0.05,tdf(1))

2.series d1 = 0

smpl @first @first

d1 = 1

smpl @all

就是建立一个series d1,第一个obs是1,余是0

1

0

0

若想學e-views编程,多看多翻EViews 5 Command Ref

好太感谢你拉 TDF是自由度吗，程序算出的结果quantile=-1.87014518238是分位数值吗,在这个程序里coef(1) tdf=3是什么意思呢？是建立长度为一的系数向量吗？为什么要让tdf=3呢？我现在已经补装上了ref文件，正在看，如果有什么问题希望你能进一步指教！别嫌我麻烦啊 呵呵

[此贴子已经被作者于2007-5-19 15:31:22编辑过]

差不多搞定了

这是我应用你先前给我的程序改过来的针对基金裕华的估计程序：

' Program to estimate a GARCH(1,1)-t model on the series yuhua.

'%path = @runpath+"../yuhua/"
'cd %yuhua
load jjsj
series d1 = 0
smpl @first @first
d1 = 1
smpl @all

'get starting values from Gaussian ARCH
equation eq1
eq1.arch yuhuat c
show eq1.output
'declare and innitialize parameters
coef(1) mu = eq1.c(1)
coef(1) omega = eq1.c(2)
coef(1) alpha =eq1.c(3)
coef(1) beta =eq1.c(4)
coef(1) tdf=3
!pi=@acos(-1)

'set up GARCH(1,1)-t likelihood
logl ll_l
ll_l.append @logl logl
ll_l.append res=yuhuat-mu(1)
ll_l.append sig2 =@recode(d1=1,omega(1)/(1-alpha(1)-beta(1)),omega(1)+alpha(1)*res(-1)^2+beta(1)*sig2(-1))
ll_l.append z =res^2/sig2/(tdf(1)-2)+1
ll_l.append logl = @gammalog((tdf(1)+1)/2)-@gammalog(tdf(1)/2)-log(!pi)/2-log(tdf(1)-2)/2-log(sig2)/2 - (tdf(1)+1)*log(z)/2

'estimate and display output
ll_l.ml(showopts,m=1000,c=1e-5)
show ll_l.output
scalar quantile=@qtdist(0.95,tdf(1))

程序执行出来的结果分别如下：Dependent Variable: YUHUAT
Method: ML - ARCH (Marquardt) - Normal distribution
Date: 05/19/07 Time: 17:10
Sample: 1 199
Included observations: 199
Convergence achieved after 76 iterations
Variance backcast: ON
GARCH = C(2) + C(3)*RESID(-1)^2 + C(4)*GARCH(-1)

Coefficient Std. Error z-Statistic Prob.

C 0.171256 0.145458 1.177360 0.2391

Variance Equation

C 1.336620 0.632853 2.112056 0.0347
RESID(-1)^2 0.288061 0.105933 2.719274 0.0065
GARCH(-1) 0.490229 0.167354 2.929295 0.0034

R-squared -0.012324 Mean dependent var 0.438428
Adjusted R-squared -0.027899 S.D. dependent var 2.412696
S.E. of regression 2.446119 Akaike info criterion 4.493790
Sum squared resid 1166.783 Schwarz criterion 4.559987
Log likelihood -443.1321 Durbin-Watson stat 1.836723

LogL: LL_L
Method: Maximum Likelihood (Marquardt)
Date: 05/19/07 Time: 17:10
Sample: 1 199
Included observations: 199
Evaluation order: By observation
Estimation settings: tol= 1.0e-05, derivs=accurate numeric
Initial Values: MU(1)=0.17126, OMEGA(1)=1.33662, ALPHA(1)=0.2880
6, BETA(1)=0.49023, TDF(1)=3.00000
Convergence achieved after 23 iterations

Coefficient Std. Error z-Statistic Prob.

MU(1) 0.179415 0.149171 1.202750 0.2291
OMEGA(1) 1.275241 0.781697 1.631376 0.1028
ALPHA(1) 0.296658 0.134556 2.204720 0.0275
BETA(1) 0.516720 0.201011 2.570609 0.0102
TDF(1) 9.226873 9.278601 0.994425 0.3200

Log likelihood -442.3448 Akaike info criterion 4.495928
Avg. log likelihood -2.222838 Schwarz criterion 4.578674
Number of Coefs. 5 Hannan-Quinn criter. 4.529417

结果应该上半部分是残差服从正态分布下的结果吧，下半部分是残差服从t分布的结果吧，另外我把你这里的 quantile=@qtdist(0.05,tdf(1))里的0.05改成了0.95，分位数计算结果为scarlar quantile=1.827994，不知对否？

[此贴子已经被作者于2007-5-19 17:15:49编辑过]

这是我针对广义误差分布编制的程序：

' Program to estimate a GARCH(1,1)-generalized error distributed model on the series yuhua.

'%path = @runpath+"../yuhua/"
'cd %yuhua
load jjsj
series d1 = 0
smpl @first @first
d1 = 1
smpl @all

'get starting values from Gaussian ARCH
equation eq1
eq1.arch yuhuat c
show eq1.output
'declare and innitialize parameters
coef(1) mu = eq1.c(1)
coef(1) omega = eq1.c(2)
coef(1) alpha =eq1.c(3)
coef(1) beta =eq1.c(4)
coef(1) nu(1)=2

'set presample values of expressions in logl
smpl s0
series sig = omega(1)
series res =0
logl ll_l
ll_l.append @logl logl
ll_l.append @logl logll
ll_l.append loggaml=@gammalog(1/mu(1))
ll_l.append loglam=-log(2)/nu(1)+0.5*(loggaml-@gammalog(3/nu(1)))

ll_l.append sig2=omega(1)+alpha(1)*res(-1)^2+beta(1)*sig2(-1)
ll_l.append res =y-mu(1)
ll_l.append z=res/@sqrt(sig2)
ll_l.append logll =log(nu(1))-loglam-(1+1/nu(1))*log(2)-loggaml-
0.5*@abs(z/exp(loglam))^nu(1)-0.5*log(sig2)
' estimate and display output
smpl sl
ll l.ml(showopts,m=1000,c=1e-5)
show ll l.output
scalar quantie=@qged(0.95,r)

运行结果如下：

Date: 05/19/07 Time: 18:01
Sample: 1 199
Included observations: 199
Convergence achieved after 76 iterations
Variance backcast: ON
GARCH = C(2) + C(3)*RESID(-1)^2 + C(4)*GARCH(-1)

Coefficient Std. Error z-Statistic Prob.

C 0.171256 0.145458 1.177360 0.2391

Variance Equation

C 1.336620 0.632853 2.112056 0.0347
RESID(-1)^2 0.288061 0.105933 2.719274 0.0065
GARCH(-1) 0.490229 0.167354 2.929295 0.0034

R-squared -0.012324 Mean dependent var 0.438428
Adjusted R-squared -0.027899 S.D. dependent var 2.412696
S.E. of regression 2.446119 Akaike info criterion 4.493790
Sum squared resid 1166.783 Schwarz criterion 4.559987
Log likelihood -443.1321 Durbin-Watson stat 1.836723

并出现以下问题：

另外我该怎么将@qged这个函数加入到程序中去，在程序中最后一行加入scalar quantie=@qged(0.95,r),但这个r我不知道怎么定义，请指教

[此贴子已经被作者于2007-5-19 18:15:52编辑过]

[此贴子已经被作者于2007-5-19 18:14:02编辑过]

1.EViews 5 Command Ref在

C:\Program Files\EViews5\Docs

2.程序修改如附件

jjsj_garchged

[此贴子已经被作者于2007-5-24 7:39:29编辑过]

再次表示感谢！这段时间辛苦你了！

[此贴子已经被作者于2007-5-20 9:51:05编辑过]

在对第三只基金基金同智做回归时碰到这样的问题：

这是我改过的程序：

' Program to estimate a GARCH(1,1)-t model on the series tongzhi.

'%path = @runpath+"../tongzhi/"
'cd %tongzhi
load tongzhi
series d1 = 0
smpl @first @first
d1 = 1
smpl @all

'get starting values from Gaussian ARCH
equation eq1
eq1.arch tongzhi c
show eq1.output
'declare and innitialize parameters
coef(1) mu = eq1.c(1)
coef(1) omega = eq1.c(2)
coef(1) alpha =eq1.c(3)
coef(1) beta =eq1.c(4)
coef(1) tdf=3
!pi=@acos(-1)

'set up GARCH(1,1)-t likelihood
logl ll_l
ll_l.append @logl logl
ll_l.append res=tongzhi-mu(1)
ll_l.append sig2 =@recode(d1=1,omega(1)/(1-alpha(1)-beta(1)),omega(1)+alpha(1)*res(-1)^2+beta(1)*sig2(-1))
ll_l.append z =res^2/sig2/(tdf(1)-2)+1
ll_l.append logl = @gammalog((tdf(1)+1)/2)-@gammalog(tdf(1)/2)-log(!pi)/2-log(tdf(1)-2)/2-log(sig2)/2 - (tdf(1)+1)*log(z)/2

'estimate and display output
ll_l.ml(showopts,m=1000,c=1e-5)
show ll_l.output
scalar quantiletongzhi1=@qtdist(0.95,tdf(1))
scalar quantiletongzhi2=@qtdist(0.99,tdf(1))
这是数据：

118560.rar
大小:(173.05 KB)

 马上下载

本附件包括：

• 毕业论文数据 未定.xls

程序是执行了

可是要注意的是,估计的系数都不显着.

118634.rar
大小:(628 Bytes)

 马上下载

本附件包括：

• tongzhi_garcht.prg

[此贴子已经被作者于2007-5-21 9:57:18编辑过]

LogL: LL_L
Method: Maximum Likelihood (Marquardt)
Date: 05/21/07 Time: 10:32
Sample: 1 199
Included observations: 199
Evaluation order: By observation
Estimation settings: tol= 1.0e-05, derivs=accurate numeric
Initial Values: MU(1)=0.00349, OMEGA(1)=0.00017, ALPHA(1)=0.1633
4, BETA(1)=0.54009, TDF(1)=3.00000
Convergence not achieved after 1000 iterations

Coefficient Std. Error z-Statistic Prob.

MU(1) 0.003982 0.001546 2.575188 0.0100
OMEGA(1) 0.000170 0.000133 1.279660 0.2007
ALPHA(1) 0.191334 0.126748 1.509568 0.1312
BETA(1) 0.530678 0.283426 1.872372 0.0612
TDF(1) 6.072787 3.228616 1.880926 0.0600

Log likelihood 471.9555 Akaike info criterion -4.693020
Avg. log likelihood 2.371636 Schwarz criterion -4.610274
Number of Coefs. 5 Hannan-Quinn criter. -4.659530

Convergence not achieved after 1000 iterations 这句话是怎么回事？我该怎么处理呢

[此贴子已经被作者于2007-5-21 17:22:30编辑过]

LogL: LL_LL
Method: Maximum Likelihood (Marquardt)
Date: 05/21/07 Time: 17:16
Sample: 1 199
Included observations: 199
Evaluation order: By observation
Estimation settings: tol= 1.0e-05, derivs=accurate numeric
Initial Values: NU(1)=2.00000, MU(1)=0.00118, OMEGA(1)=0.00242,
ALPHA(1)=-0.00926, BETA(1)=0.58666
Convergence achieved after 2 iterations
WARNING: Singular covariance - coefficients are not unique

Coefficient Std. Error z-Statistic Prob.

NU(1) 0.906328 NA NA NA
MU(1) 0.012924 NA NA NA
OMEGA(1) -3.12E-05 NA NA NA
ALPHA(1) -0.002935 NA NA NA
BETA(1) 0.357079 NA NA NA

Log likelihood 342.3151 Akaike info criterion -3.390102
Avg. log likelihood 1.720177 Schwarz criterion -3.307356
Number of Coefs. 5 Hannan-Quinn criter. -3.356612

为什么有的基金数据比如基金科翔不能估计出来结果啊数据如下：

118777.rar
大小:(11.01 KB)

 马上下载

本附件包括：

• kexiang.wf1

[此贴子已经被作者于2007-5-21 21:06:43编辑过]

是不是初值出了问题啊

WARNING: Singular covariance - coefficients are not unique

单协方差系数不是唯一的，这是怎么回事啊呵呵真是有点晕了，前面都好好的，后面的好几个基金都出现童言的问题，这该怎么办啊？请大师指点

[此贴子已经被作者于2007-5-21 21:06:05编辑过]

你都不检验数据?

第103个样本你算对了吗?

log(1.2173)-log(1.2506)=?

程序中ll_l.ml(showopts,m=1000,c=1e-5)

可将c=1e-5改为c=1e-7做比较

hehe,不好意思，我看看

[此贴子已经被作者于2007-5-22 10:30:04编辑过]

基金科翔的确是我看错了。可是基金兴安的数据我检查了一遍，t分布下仍然没有结果，但ged分布下却有结果，也按照你的要求将此c=1e-5改成了c=1e-7可是结果仍然如下：

LogL: LL_L
Method: Maximum Likelihood (Marquardt)
Date: 05/22/07 Time: 10:32
Sample: 1 199
Included observations: 199
Evaluation order: By observation
Estimation settings: tol= 1.0e-07, derivs=accurate numeric
Initial Values: MU(1)=0.00085, OMEGA(1)=0.00010, ALPHA(1)=0.4825
5, BETA(1)=0.44058, TDF(1)=3.00000
Convergence achieved after 2 iterations
WARNING: Singular covariance - coefficients are not unique

Coefficient Std. Error z-Statistic Prob.

MU(1) 0.001307 NA NA NA
OMEGA(1) 0.000149 NA NA NA
ALPHA(1) 0.502401 NA NA NA
BETA(1) 0.541528 NA NA NA
TDF(1) 3.082311 NA NA NA

Log likelihood 464.8282 Akaike info criterion -4.621389
Avg. log likelihood 2.335820 Schwarz criterion -4.538643
Number of Coefs. 5 Hannan-Quinn criter. -4.587899

119012.rar
大小:(38.57 KB)

 马上下载

本附件包括：

• jjsj.xls

[此贴子已经被作者于2007-5-22 10:35:58编辑过]

基金金元、汉博也是同样的情况，t分布没有结果，而ged分布却是有结果。数据我已经检查过了，c也改过了，难道出了别的问题？

LogL: LL_L
Method: Maximum Likelihood (Marquardt)
Date: 05/21/07 Time: 21:01
Sample: 1 199
Included observations: 199
Evaluation order: By observation
Estimation settings: tol= 1.0e-05, derivs=accurate numeric
Initial Values: MU(1)=0.00251, OMEGA(1)=9.2e-05, ALPHA(1)=0.2798
0, BETA(1)=0.58117, TDF(1)=3.00000
Convergence achieved after 3 iterations
WARNING: Singular covariance - coefficients are not unique

Coefficient Std. Error z-Statistic Prob.

MU(1) 0.002925 NA NA NA
OMEGA(1) -0.000125 NA NA NA
ALPHA(1) 0.176879 NA NA NA
BETA(1) 0.812159 NA NA NA
TDF(1) 6.068057 NA NA NA

Log likelihood 462.9452 Akaike info criterion -4.602464
Avg. log likelihood 2.326358 Schwarz criterion -4.519718
Number of Coefs. 5 Hannan-Quinn criter. -4.568975

[此贴子已经被作者于2007-5-22 10:54:59编辑过]