R help - Apr 2013 - hierarchical confirmatory factor analysis with sem package

Hi,
I am doing a hierarchical CFA using the sem package. I have 20 items, and I
have 2 factors (F3 and F4), and also F1 and F2 are nested within F3.
Here is the code that I have, but it is giving me an error message "Warning
message:
In eval(expr, envir, enclos) : Negative parameter variances.
Model may be underidentified." and a further error "Error in
summary.objectiveML(cfa, fit.indices = c("NNFI", "CFI",
"RMSEA")) :
coefficient covariances cannot be computed". I have run CFA before with no
issues. This is the first time I am running a nested model. Any help will be
greatly appreciated.
Regards,
Mat
cov.matrix<-cov(na.omit(df))
cfa.model<-specifyModel()
F1->i2,a1
F1->i3,a2
F1->i4,a3
F1->i11,a4
F1->i12,a5
F1->i15,a6
F1->i18,a7
F2->i6,b1
F2->i7,b2
F2->i8,b3
F2->i13,b4
F2->i20,b5
F3->F1,c1
F3->F2,c2
F4->i1,d1
F4->i5,d2
F4->i9,d3
F4->i10,d4
F4->i14,d5
F4->i16,d6
F4->i17,d7
F4->i19,d8
F1<->F1,NA,1
F2<->F2,NA,1
F3<->F3,NA,1
F4<->F4,NA,1
i2<->i2,error1
i4<->i4,error2
i6<->i6,error3
i7<->i7,error4
i8<->i8,error5
i11<->i11,error6
i13<->i13,error7
i15<->i15,error8
i18<->i18,error9
i20<->i20,error10
i1<->i1,error11
i3<->i3,error12
i5<->i5,error13
i9<->i9,error14
i10<->i10,error15
i12<->i12,error16
i14<->i14,error17
i16<->i16,error18
i17<->i17,error19
i19<->i19,error20
cfa<-sem(cfa.model,cov.matrix,nrow(df))
summary(cfa,fit.indices=c("NNFI","CFI","RMSEA"))

	[[alternative HTML version deleted]]