Dear Stata users,

I am estimating the impact of income (lrgdp) on per capita carbon emissions(lpccarb). For this, I ran a gmm model using xtabond2 command. Please see the command below.

Code:
 qui xtabond2 lpccarb L.lpccarb lrgdp c.lrgdp#c.lrgdp frleg c.frleg#c.frleg c.frleg#c.lrgdp lenguse lpopden indus period3-period31, gmm(L2.(lpccarb) L.(lrgdp lrgdp2 frleg c.frleg#c.frleg  lpopden lenguse indus), collapse lag(1 4) ortho) iv(i.year frleg frleg2 c.frleg#c.lrgdp lenguse , equation(level)) robust twostep small ortho
I want to see the marginal effect of income on per capita carbon emissions at different income percentiles. For this, I ran margins postestimation command. Since, both dependent (per capita carbon emissions) and independent variable (income) are log-transformed, I estimate elasticities.

Code:
margins , eyex(lrgdp) at((p10) lrgdp) at((p25) lrgdp) at((p50) lrgdp) at((p75) lrgdp) at((p90) lrgdp)

Warning: cannot perform check for estimable functions.
(note: default prediction is a function of possibly stochastic quantities other than e(b))
could not calculate numerical derivatives -- discontinuous region with missing values
encountered
r(459);
However, I get an error message due to missing values. How can I fix this error?

I checked an old thread https://www.statalist.org/forums/for...es-encountered, but could not find my answer in this thread.

Can someone please help me fix this issue?

Thank you,

Ritika