RATS使用求助

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

各位大侠，我在使用RATS，遇到些问题，请教各位

我提并的程序

************************
* This program performs Smooth GARCH(1,1) Estimation
************************
all 330
open data on.xls
data(org=obs,format=xls) / ir
table / ir
set h = 0.0
*list of parameters to be estimated
nonlin mu gamma p1 p2 a0 a1 a2 b0 b1 b2
frml at = ir(t) - mu - p1*ir(t-1) - p2*ir(t-2)
frml var1 =  a0+a1*at(t-1)**2+a2*h(t-1)
frml var2 = b0+b1*at(t-1)**2+b2*h(t-1)
frml gvar = var1(t)+var2(t)/(1.0+exp(-at(t-1)*gamma))
frml garchlog = -0.5*log(h(t)=gvar(t))-0.5*at(t)**2/h(t)
smpl 8 330
compute  p1 = 1.2, p2 = -0.3, a0 = -23.3, a1 = -11.6, a2 = -4.97
compute  b0 = 46.6, b1 = 24.5, b2 = 10.5, mu = 1.5, gamma=0.02

maximize(method=bhhh,recursive,iterations=100000) garchlog

运行RATS程序，总是提示以下信息（能给出估计结果）。不太明白是什么意思？好象与初值的选择有关系，如何改进呢？

MAXIMIZE - Estimation by BHHH
NO CONVERGENCE IN 48 ITERATIONS
LAST CRITERION WAS  0.0000000
SUBITERATIONS LIMIT EXCEEDED. ESTIMATION POSSIBLY HAS STALLED OR MACHINE ROUNDOFF IS MAKING FURTHER PROGRESS DIFFICULT.
TRY HIGHER SUBITERATIONS LIMIT, TIGHTER CVCRIT, DIFFERENT SETTING FOR EXACTLINE OR ALPHA ON NLPAR.
RESTARTING ESTIMATION FROM LAST ESTIMATES OR DIFFERENT INITIAL GUESSES MIGHT ALSO WORK

扫码加我 拉你入群

请注明：姓名-公司-职位

以便审核进群资格，未注明则拒绝

分享0 收藏0 回帖

关键词：Rats Convergence iterations Estimation parameters Rats

好象是没有收敛，得出的结果无效。