Instrumental variables and GMM: Estimation and testing

被引：1252

作者：

Baum, Christopher F. ^{[1
]}

Schaffer, Mark E. ^{[2
,3
]}

Stillman, Steven ^{[4
]}

机构：

[1] Boston Coll, Econ, Chestnut Hill, MA 02167 USA

[2] Heriot Watt Univ, Econ, Edinburgh, Midlothian, Scotland

[3] Heriot Watt Univ, CERT, Edinburgh, Midlothian, Scotland

[4] New Zealand Dept Labour, Labour Market Policy Grp, Wellington, New Zealand

来源：

STATA JOURNAL | 2003年 / 3卷 / 01期

关键词：

st0030; instrumental variables; generalized method of moments; endogeneity; heteroskedasticity; overidentifying restrictions; clustering; intra-group correlation;

D O I：

10.1177/1536867X0300300101

中图分类号：

O1 [数学]; C [社会科学总论];

学科分类号：

03 ; 0303 ; 0701 ; 070101 ;

摘要：

We discuss instrumental variables (IV) estimation in the broader context of the generalized method of moments (GMM), and describe an extended IV estimation routine that provides GMM estimates as well as additional diagnostic tests. Stand-alone test procedures for heteroskedasticity, overidentification, and endogeneity in the IV context are also described.

引用

页码：1 / 31

页数：31

共 45 条

[1]

Ahn S. C., 1995, ROBUST TESTS MODEL S

[2]

[Anonymous], 1988, MISSPECIFICATION TES, DOI [10.1017/CCOL0521266165, DOI 10.1017/CCOL0521266165]

[3]

ARELLANO M, 1987, OXFORD B ECON STAT, V49, P431

[4]

BASMANN RL, 1960, J AM STAT ASSOC, V55, P650