# Test fixed effects for joint significance in R

Just as in this post I'm looking to test for the joint significance of the fixed effects in a model. Unlike the post I referred to, I'm looking to test each fixed effect individually. I have used a sample dataset which is publicly available and I already ran an F test on the fixed effects. I would like to know if you think this is the right way to test for joint significance.:

library(foreign)
Panel\$RandomFactor <- sample(LETTERS[1:6],nrow(Panel),replace=T)
fit <- lm(y~factor(RandomFactor)+factor(country)+factor(year)+x1 + x2 -1,data=Panel)
summary(fit)
library(aod)
wald.test(b=coef(fit),Sigma=vcov(fit),Terms= 1:6,) # F test on Random Factor

#Wald test:
#----------
#
#Chi-squared test:
#X2 = 5.9, df = 6, P(> X2) = 0.43

wald.test(b=coef(fit),Sigma=vcov(fit),Terms= 7:12,) # F test on Country

#Wald test:
#----------
#
#Chi-squared test:
#X2 = 20.5, df = 6, P(> X2) = 0.0022
wald.test(b=coef(fit),Sigma=vcov(fit),Terms= 13:21,) #F test on year
#Wald test:
#----------
#
#Chi-squared test:
#X2 = 12.1, df = 9, P(> X2) = 0.21


Is this the right way to test for joint significance in a fixed effects model? The results look plausible to me, country is significant but year and RandomFactor(as expected) not.

Since I use many fixed effects in my real dataset, I would really like to test each individual fixed effect for significance (as I did here) and mix different combinations.

Any help is much appreciated. Many thanks,

Tim