[R-sig-ME] cannot increase the number of iterations in lme call over 146

Wed Jan 4 03:51:00 CET 2012

Hi Antonio,

Look at the error message: "function evaluation limit reached without
convergence" you increased the number of iterations, but the objective
function reached its limit for max evaluations prior to convergance.
The 'brute force' approach would be to use the msMaxEval argument of
lmeControl to up that, but I would suggest carefully scrutinizing your
data and model prior before blindly asking the optimizer to run
longer.

Have you graphed your data?  What sort of variables are time and
maternal_educ?  If you send us data, we can show you some examples of
how you might graph and examine your data.  Also, do you really want a
random interaction?

Finally, in model formulae, * behaves specially, so x * z expands to:
x + z + x:z, thus a simplified writing of your model (not really
important and if the other way is clearer to you, by all means use it,
but you can save a few keystrokes; also note I show the msMaxEval
argument):

model.c2 <- lme(log(child_mortality) ~  time * log(maternal_educ),
  control = lmeControl(msMaxIter = 200, msMaxEval = 500 msVerbose = TRUE),
  merged1, random = ~ log(maternal_educ) * time | country.x,
  na.action = na.omit, method = "ML")

Cheers,

Josh

On Tue, Jan 3, 2012 at 5:52 PM, Antonio P. Ramos
<ramos.grad.student at gmail.com> wrote:
> Hi all,
>
> I am trying to fit a simple mixed model for longitudinal data, but the
> algorithm is not converging. When I add additional commands in the call I
> am able to increase the number of iterations from the default of 50 to 146,
> but no more than that. Does anyway have an idea about what is going on?  I
> can provided data if needed.
>
> Best, Antonio.
>
>> model.c2 <- lme(log(child_mortality) ~  time + log(maternal_educ) +
> log(maternal_educ)*time,
> +                control=lmeControl(msMaxIter = 200, msVerbose = TRUE),
> +                merged1, random= ~time + log(maternal_educ)*time
> |country.x, na.action=na.omit,method="ML")
>  0:     11378.396: -1.65670  2.44758 -3.03894  2.00310 -34.0487 0.186837
> 0.0637447  49.2689 -10.3311  5.94936
>  1:     11375.740: -1.68701  2.45171 -3.03866  2.00265 -34.0499 0.302840
> 0.0305228  49.2682 -10.3309  5.94934
>  2:     11375.323: -1.68664  2.45188 -3.03838  2.00234 -34.0499 0.302036
> 0.0279806  49.2682 -10.3309  5.94934
>  3:     11375.161: -1.68509  2.45164 -3.03478  1.99830 -34.0500 0.301491
> 0.0299300  49.2682 -10.3309  5.94939
>  4:     11374.835: -1.68137  2.45134 -3.03272  1.99601 -34.0499 0.290639
> 0.0313596  49.2682 -10.3310  5.94943
>  5:     11361.671: -1.63878  2.45243 -2.66545  1.58982 -34.0573 0.726526
> -0.0906120  49.2606 -10.3367  5.95909
>  6:     11359.791: -1.65178  2.44927 -2.57664  1.47997 -34.0610 0.975864
> -0.170656  49.2572 -10.3386  5.96736
>  7:     11359.595: -1.65004  2.45965 -2.56790  1.46837 -34.0612  1.00787
> -0.168258  49.2564 -10.3397  5.97066
>
>
>
> 132:     11307.797: -1.39340  3.37422 0.317114 0.526105 -90.6641  44.6928
> -13.9187  667.927 -208.799  26.9546
> 133:     11307.797: -1.39346  3.38002 0.320773 0.526102 -91.1985  45.1140
> -14.0518  675.133 -211.078  27.0564
> 134:     11307.796: -1.39350  3.38197 0.321697 0.525758 -91.3801  45.2651
> -14.0996  677.663 -211.877  27.0798
> 135:     11307.795: -1.39360  3.38872 0.325211 0.525153 -92.0139  45.7838
> -14.2635  686.411 -214.643  27.1729
> 136:     11307.794: -1.39365  3.39553 0.329183 0.525088 -92.6545  46.2974
> -14.4259  695.158 -217.409  27.2829
> 137:     11307.792: -1.39368  3.40218 0.332937 0.525082 -93.2910  46.8111
> -14.5883  703.905 -220.176  27.3876
> 138:     11307.791: -1.39373  3.40895 0.337031 0.525186 -93.9332  47.3224
> -14.7500  712.652 -222.942  27.5031
> 139:     11307.790: -1.39378  3.41494 0.341038 0.525609 -94.5084  47.7708
> -14.8918  720.413 -225.398  27.6206
> 140:     11307.789: -1.39382  3.41930 0.344713 0.526541 -94.9384  48.0868
> -14.9919  726.060 -227.188  27.7364
> 141:     11307.788: -1.39387  3.42361 0.347375 0.526566 -95.3534  48.4155
> -15.0959  731.709 -228.975  27.8133
> 142:     11307.788: -1.39393  3.42785 0.349776 0.526344 -95.7643  48.7467
> -15.2006  737.357 -230.762  27.8810
> 143:     11307.787: -1.39401  3.43137 0.351265 0.525645 -96.1084  49.0365
> -15.2922  742.207 -232.294  27.9192
> 144:     11307.786: -1.39407  3.43484 0.352910 0.525314 -96.4518  49.3214
> -15.3823  747.014 -233.815  27.9635
> 145:     11307.786: -1.39410  3.43839 0.354938 0.525329 -96.8011  49.6024
> -15.4711  751.820 -235.335  28.0217
> 146:     11307.786: -1.39410  3.43839 0.354938 0.525329 -96.8011  49.6024
> -15.4711  751.820 -235.335  28.0217
> Error in lme.formula(log(child_mortality) ~ time + log(maternal_educ) +  :
>  nlminb problem, convergence error code = 1
>  message = function evaluation limit reached without convergence (9)
>>
>
>        [[alternative HTML version deleted]]
>
> _______________________________________________
> R-sig-mixed-models at r-project.org mailing list
> https://stat.ethz.ch/mailman/listinfo/r-sig-mixed-models

-- 
Joshua Wiley
Ph.D. Student, Health Psychology
Programmer Analyst II, Statistical Consulting Group
University of California, Los Angeles
https://joshuawiley.com/