模型估计的问题??

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

STEADY:  The Jacobian contains Inf or NaN. The problem arises from:

STEADY:  Derivative of Equation 22 with respect to Variable c  (initial value of c: 0)
STEADY:  Derivative of Equation 13 with respect to Variable w  (initial value of w: 0)
STEADY:  Derivative of Equation 20 with respect to Variable L  (initial value of L: 0)
STEADY:  Derivative of Equation 13 with respect to Variable rK  (initial value of rK: 0)
STEADY:  Derivative of Equation 20 with respect to Variable k  (initial value of k: 0)
STEADY:  Derivative of Equation 20 with respect to Variable U  (initial value of U: 0)
STEADY:  Derivative of Equation 22 with respect to Variable i  (initial value of i: 0)
STEADY:  Derivative of Equation 20 with respect to Variable epsilon_X  (initial value of epsilon_X: 0)
STEADY:  Derivative of Equation 21 with respect to Variable epsilon_X  (initial value of epsilon_X: 0)
STEADY:  Derivative of Equation 1 with respect to Variable epsilon_V  (initial value of epsilon_V: 0)
STEADY:  Derivative of Equation 20 with respect to Variable epsilon_V  (initial value of epsilon_V: 0)
STEADY:  Derivative of Equation 21 with respect to Variable epsilon_V  (initial value of epsilon_V: 0)

STEADY:  The problem most often occurs, because a variable with
STEADY:  exponent smaller than 1 has been initialized to 0. Taking the derivative
STEADY:  and evaluating it at the steady state then results in a division by 0.
Error using dynare_solve (line 60)
An element of the Jacobian is not finite or NaN

Error in evaluate_steady_state (line 66)
            [ys,check] = dynare_solve([M.fname '_static'],...

Error in dynare_estimation_init (line 490)
[oo_.steady_state, params] =
evaluate_steady_state(oo_.steady_state,M,options_,oo_,steadystate_check_flag);

Error in dynare_estimation_1 (line 81)
[dataset_,xparam1, hh, M_, options_, oo_, estim_params_,bayestopt_] = dynare_estimation_init(var_list_,
dname, [], M_, options_, oo_, estim_params_, bayestopt_);

Error in dynare_estimation (line 89)
    dynare_estimation_1(var_list,dname);

Error in model (line 483)
dynare_estimation(var_list_);

Error in dynare (line 180)
evalin('base',fname) ;
第一次遇到这种错误...哪位高人给解释解释到底哪里出问题了>?什么情况叫做雅可比矩阵里面的某一个元素是无限或者不存在???

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：模型估计 Derivative Estimation Evaluating Valuating initial problem respect arises 模型

STEADY:  The problem most often occurs, because a variable with
STEADY:  exponent smaller than 1 has been initialized to 0. Taking the derivative
STEADY:  and evaluating it at the steady state then results in a division by 0.

是不是你的初始值设定有很多零啊？如果是，你将初始值设定为例如0.00001等试试。

Jacobian在这里指（Dynare方程组）的导数的数值一阶或二阶估计。
错误说明这个导数值不存在。有两点可能的原因：
一是model方程组设置有错，解出来的（方程组导数）解析解有错误，代入稳态值时求不出数值解。
二是模型校准有错，导致分母为零的情况发生。

楼主应该是用loglinear方法做的，所以稳态值为0是对的，第二种可能不大会发生。
所以建议逐行检查模型方程组。

楼上的说得好

楼主，我最近学习Dynare，在运行Dynare User Guide 55页上的 .mod文件时也遇到了跟你一样的情况，在网上看了好多也没找到解决方法，反复的检查模型好像也没有问题。不知道你这个问题解决了没有？能告诉我一下具体是怎么回事，怎么解决吗？谢谢了！

xuezheliu 发表于 2014-7-27 10:43
楼主，我最近学习Dynare，在运行Dynare User Guide 55页上的 .mod文件时也遇到了跟你一样的情况，在网上看了 ...

我也是有一个方城市这个问题，你解决了吗?