A Weak Instrument F-Test in Linear IV Models with Multiple Endogenous Variables

Eleanor Sanderson, Frank Windmeijer

Research output: Contribution to journalArticle (Academic Journal)peer-review

311 Citations (Scopus)
3320 Downloads (Pure)


We consider testing for weak instruments in a model with multiple endogenous variables. Unlike Stock and Yogo (2005), who considered a weak instruments problem where the rank of the matrix of reduced form parameters is near zero, here we consider a weak instruments problem of a near rank reduction of one in the matrix of reduced form parameters. For example, in a two-variable model, we consider weak instrument asymptotics of the form π1=δπ2+c/n where π1π1 and π2π2 are the parameters in the two reduced-form equations, cc is a vector of constants and nn is the sample size. We investigate the use of a conditional first-stage FF-statistic along the lines of the proposal by Angrist and Pischke (2009) and show that, unless δ=0δ=0, the variance in the denominator of their FF-statistic needs to be adjusted in order to get a correct asymptotic distribution when testing the hypothesis H0:π1=δπ2H0:π1=δπ2. We show that a corrected conditional FF-statistic is equivalent to the Cragg and Donald (1993) minimum eigenvalue rank test statistic, and is informative about the maximum total relative bias of the 2SLS estimator and the Wald tests size distortions. When δ=0δ=0 in the two-variable model, or when there are more than two endogenous variables, further information over and above the Cragg–Donald statistic can be obtained about the nature of the weak instrument problem by computing the conditional first-stage FF-statistics.
Original languageEnglish
Pages (from-to)212-221
Number of pages10
JournalJournal of Econometrics
Issue number2
Early online date20 Jun 2015
Publication statusPublished - Feb 2016


  • Weak instruments
  • Multiple endogenous variables
  • F-test


Dive into the research topics of 'A Weak Instrument F-Test in Linear IV Models with Multiple Endogenous Variables'. Together they form a unique fingerprint.

Cite this