0

I'm investigating the effect of FDI on Freedom and want to apply panel IV regression.

I use the plm package. While I run the regression, it gives me the following error: 

Error in plm.fit(formula, data, model, effect, random.method, random.models,  : 
  insufficient number of instruments

I alterned the number of control variables but it didn´t work. 

plm(FH~Lag_logUN_FDI_Stock_gdp+Lag_GDPpC+Lag_polity2+Lag_conflict+Lag_logtax+Lag_logresources+Lag_logtrade |.- Lag_logUN_FDI_Stock_gdp -Lag_logpopulation + Land ,data = pd_main)
Helix123
  • 3,502
  • 2
  • 16
  • 36
Luca
  • 3
  • 4

1 Answers1

0

Your formula suggests that you are using one IV (Land) for two instrumented variables. You are supposed to provide two instruments for one instrumented variable. Possibly you just wrote the syntax the wrong way around? According to this book (Chapter 15) you are supposed to write the syntax as: 

plm( y ~ x + b | z1 + z1 + b, data=pd_main )

Where x is your endogenous variable, and z1, z2 are your instruments.

Tom
  • 2,173
  • 1
  • 17
  • 44
  • Great, thanks for cour comment! This makes absolute sense! – Luca Jun 13 '20 at 07:08
  • Am not sure if ``plm`` takes one IV. Always a good practice to use enough external ``IV`` . Rule of thumb: Intrumented variables should be correlated with with your explanatory variables and also they should be exogenous - https://www.econometrics-with-r.org/12-3-civ.html – linkonabe Jul 16 '20 at 02:23