Problems with mvtobit command and use the draws

[Sofia Cruz]

Hello,

I am trying to rum M-tobit with 3 equations, one of the dependent variables has a lot of zeros but not the same amount. So I am using Stata 14 and tried to use maxvar and max memory, but I think the problem is related to the use of draws, how many draws I should use?. I have 9705, and the variable paid_work has 5,262 zeros. This is my Stata code


[clear
set virtual on
set segmentsize 64m
set maxvar 32000
]

[mvtobit (hw1= i.relation_head age_group i.edu_level eth)(hw2= i.relation_head age_group i.edu_level eth) ///
(paid_work= i.relation_head age_group i.edu_level eth) if gender==1 [aw=FACTOR], dr(1440)an
]

So, Stata says:

[(sum of wgt is 1.3540e+06)
(sum of wgt is 1.3540e+06)
(sum of wgt is 1.3540e+06)
Maximum # of censored equations is 3

Draws (Halton/pseudo random) are being made:

Created 1440 Halton draws per equation for 3 dimensions. Number of initial
draws dropped per dimension = 0 . Primes used:

2 3 5
Also created 1440 antithetic draws per dimension for 3 dimensions. Note:
there are now 2880 draws per equation

plugin not loaded or not available: use the adoonly option
r(199);]

If I use less draws says that I need more, I did't get it. May you help me?


Thanks,