Solution singular problem in lme4? And, why is optimizer (nloptwrap) convergence code: 0 (OK

[Alex2024]

I used a linear mixed-effects model but couldn't get the Fixed effects.

Linear mixed model fit by maximum likelihood ['lmerMod']
Formula:
Weight ~ 1 + (Age.Av.pwr2 + Sex + HHSize + Wealth) + (1 + Age.Av.pwr2) | Country
Data: datafm1

  AIC       BIC    logLik  deviance  df.resid 

225026.1 225170.4 -112496.1 224992.1 35683

Scaled residuals:
Min 1Q Median 3Q Max
-4.6510 -0.5225 -0.0724 0.3993 9.3087

Random effects:
Groups Name Variance Std.Dev. Corr
Country (Intercept) 20.11602 4.4851
Age.Av.pwr2 0.02339 0.1529 -0.98
SexMale 0.73445 0.8570 -0.49 0.49
HHSize 0.03168 0.1780 0.82 -0.84 -0.88
Wealth 67.87233 8.2385 -0.97 1.00 0.54 -0.87
Residual 31.88536 5.6467
Number of obs: 35700, groups: Country, 4
Fixed effects:
Estimate Std. Error t value
(Intercept) 12.0234 0.3458 34.77

optimizer (nloptwrap) convergence code: 0 (OK)
boundary (singular) fit: see help('isSingular')
So, how do I solve the singular problem in lme4? And, why is optimizer (nloptwrap) convergence code: 0 (OK)? And, also how can I add each p-value after t-vales?

Thank you a lot!

[technocrat]

Can't help much without a reprex (see the FAQ. But `help("is.Singular") has a good discussion of the issue and possible approaches to dealing with what is being returned. Just eyeballing

@Alex2024

Weight ~ 1 + (Age.Av.pwr2 + Sex + HHSize + Wealth) + (1 + Age.Av.pwr2)

looks like there won't be much variance if Age.Av.pwr2 dominates and the AIC/BIC and other measures are so out of the ballpark, it looks like sampling a random process.