Time-varying parameters;
Linear model;
Gretl;
SERIES MODELS;
SPECIFICATION;
INFERENCE;
D O I:
10.1007/s00180-023-01452-3
中图分类号:
O21 [概率论与数理统计];
C8 [统计学];
学科分类号:
020208 ;
070103 ;
0714 ;
摘要:
Estimation of linear models with time-varying parameters can be accomplished in a variety of ways, each making different assumptions, with varying degrees of accuracy and computational complexity. In this paper, we compare different gretl packages by means of simulated and real data focusing on both statistical and computational aspects. Our findings show that all the estimators provide similar results under ideal conditions, but the practitioner's choice could be far from obvious.
机构:
Fudan Univ, Sch Econ, Shanghai, Peoples R China
Shanghai Inst Int Finance & Econ, Shanghai, Peoples R ChinaFudan Univ, Sch Econ, Shanghai, Peoples R China
Fu, Zhonghao
Su, Liangjun
论文数: 0引用数: 0
h-index: 0
机构:
Tsinghua Univ, Sch Econ & Management, Beijing, Peoples R ChinaFudan Univ, Sch Econ, Shanghai, Peoples R China
Su, Liangjun
Wang, Xia
论文数: 0引用数: 0
h-index: 0
机构:
Renmin Univ China, Sch Econ, Beijing 100872, Peoples R ChinaFudan Univ, Sch Econ, Shanghai, Peoples R China
机构:
Pontifical Catholic Univ Rio de Janeiro, Elect Engn Dept, BR-22451900 Rio De Janeiro, BrazilPontifical Catholic Univ Rio de Janeiro, Elect Engn Dept, BR-22451900 Rio De Janeiro, Brazil
Hoeltgebaum, Henrique
论文数: 引用数:
h-index:
机构:
Fernandes, Cristiano
Street, Alexandre
论文数: 0引用数: 0
h-index: 0
机构:
Pontifical Catholic Univ Rio de Janeiro, Elect Engn Dept, BR-22451900 Rio De Janeiro, BrazilPontifical Catholic Univ Rio de Janeiro, Elect Engn Dept, BR-22451900 Rio De Janeiro, Brazil