I'm sorry, but I don't understand this, and I don't see how it is
connected to the discussion so far.
Eva
2009/3/15 <[email protected]>:
> My data combine 4 regions together with dummy variables as following
>
> sm se t d1 d2
> .6592281 .027027 1 1 0
> .7192982 .0263158 2 1 0
> .7461538 .0230769 3 1 0
> .7723577 .0243902 4 1 0
> .7862595 .0229008 5 1 0
> .8114285 .0171429 6 1 0
> .8058823 .0176471 7 1 0
> .8171428 .0171429 8 1 0
> .7743902 .0182927 9 1 0
> .7607362 .0245399 10 1 0
> .755102 .0272109 11 1 0
> .7569444 .0208333 12 1 0
> .7588652 .0212766 13 1 0
> .7536232 .0217391 14 1 0
> .736 .024 15 1 0
> .725 .0333333 16 1 0
> .7629629 .0222222 17 1 0
> .760274 .0273973 18 1 0
> .5359314 .0367697 1 0 1
> .5833333 .0357143 2 0 1
> .62 .04 3 0 1
> .6037736 .0377358 4 0 1
> .6962963 .0222222 5 0 1
> .6805556 .0208333 6 0 1
> .7375 .01875 7 0 1
> .7484277 .0188679 8 0 1
> .7465754 .0205479 9 0 1
> .7191781 .0273973 10 0 1
> .7142857 .0225564 11 0 1
> .7152778 .0208333 12 0 1
> .7092199 .0212766 13 0 1
> .6953125 .03125 14 0 1
> .7177419 .0322581 15 0 1
> .7213115 .0327869 16 0 1
> .7122302 .0215827 17 0 1
> .7103449 .0275862 18 0 1
> .6496138 .041598 1 0 0
> .7070707 .040404 2 0 0
> .6952381 .047619 3 0 0
> .7102804 .0373832 4 0 0
> .7272727 .0363636 5 0 0
> .7438017 .0330578 6 0 0
> .7537314 .0298507 7 0 0
> .7569444 .0347222 8 0 0
> .7357143 .0357143 9 0 0
> .76 .0266667 10 0 0
> .78125 .025 11 0 0
> .7449664 .0268456 12 0 0
> .7375886 .035461 13 0 0
> .7142857 .037594 14 0 0
> .7251908 .0305344 15 0 0
> .7209302 .0310078 16 0 0
> .7307692 .0384615 17 0 0
> .7132353 .0367647 18 0 0
> .6315789 .0345543 1 0 0
> .6315789 .037594 2 0 0
> .6258993 .0431655 3 0 0
> .6090226 .0451128 4 0 0
> .620438 .0437956 5 0 0
> .610687 .0458015 6 0 0
> .6736111 .0416667 7 0 0
> .6394558 .0408163 8 0 0
> .6470588 .0392157 9 0 0
> .6547619 .0357143 10 0 0
> .6566265 .0361446 11 0 0
> .6526946 .0299401 12 0 0
> .6521739 .0310559 13 0 0
> .6325301 .0361446 14 0 0
> .6369048 .0416667 15 0 0
> .6453488 .0406977 16 0 0
> .6436782 .045977 17 0 0
> .6436782 .045977 18 0 0
> .6698113 .0260135 1 0 0
> .6698113 .0283019 2 0 0
> .6697248 .0275229 3 0 0
> .6666667 .0285714 4 0 0
> .6315789 .0263158 5 0 0
> .6694915 .0254237 6 0 0
> .716129 .0258065 7 0 0
> .7356322 .0344828 8 0 0
> .7368421 .0233918 9 0 0
> .7431694 .0218579 10 0 0
> .7235294 .0235294 11 0 0
> .70625 .025 12 0 0
> .7142857 .0310559 13 0 0
> .7586207 .0413793 14 0 0
> .6923077 .027972 15 0 0
> .6766917 .037594 16 0 0
> .6842105 .037594 17 0 0
> .7007299 .0437956 18 0 0
> .6422764 .0373636 1 0 0
> .6422764 .0406504 2 0 0
> .6446281 .0495868 3 0 0
> .6341463 .0487805 4 0 0
> .632 .04 5 0 0
> .6532258 .0322581 6 0 0
> .6814815 .0296296 7 0 0
> .6595744 .0283688 8 0 0
> .6758621 .0206897 9 0 0
> .7012987 .025974 10 0 0
> .7019867 .0198676 11 0 0
> .6973684 .0263158 12 0 0
> .69375 .025 13 0 0
> .7065868 .0239521 14 0 0
> .7025316 .0316456 15 0 0
> .7168674 .0301205 16 0 0
> .7142857 .0357143 17 0 0
> .718232 .0220994 18 0 0
> .6666667 .0167117 1 0 0
> .6666667 .0181818 2 0 0
> .6666667 .0175439 3 0 0
> .671875 .015625 4 0 0
> .6836734 .0204082 5 0 0
> .7040817 .0204082 6 0 0
> .733945 .0183486 7 0 0
> .75 .015873 8 0 0
> .7572464 .0144928 9 0 0
> .7695035 .0177305 10 0 0
> .7676057 .0176056 11 0 0
> .7822878 .0184502 12 0 0
> .7814815 .0185185 13 0 0
> .755814 .0232558 14 0 0
> .756 .02 15 0 0
> .7448559 .0246914 16 0 0
> .6525822 .028169 17 0 0
> .6359649 .0263158 18 0 0
>
>
>
> Does the time variable cause the problem?
>
> Jingjing
>
>
> Quoting Eva Poen <[email protected]>:
>
>> Jingjing,
>>
>> I'm not sure I understand you here. Are you referring to the line
>>
>>> replace `lnc' = 5+`aq'*`lnq' ...
>>
>> where there is a hard coded 5 (not a starting value! This is a set
>> value.), and did you replace this value of 5 by another parameter,
>> e.g. `a0'? In terms of the program, that is not a problem as long as
>> you adjust your code. It would be easiest if you put this parameter
>> last, since this saves you the pain of changing all your `at'[1,x]
>> statements to `at'[1,x+1]. Therefore, my suggestion would be to code
>>
>> scalar `dmm'=`at'[1,61]
>> tempname a0
>> scalar `a0' =`at'[1,62]
>>
>>
>> quietly {
>> replace `lnc' = `a0'+ ....
>> }
>>
>> Now, for the debugging, just follow my suggestions earlier, and invoke
>> your program directly. You need to create a matrix of initial values,
>> e.g. zeros for all coefficients. If you have 62 parameters, you do
>>
>> matrix a = J(1,62,0)
>>
>> which gives you a row vector of 62 zeros. Next create copies of all
>> your dependent variables, and invoke your program:
>>
>> set trace on
>> nlsurwellbehav "copies of dep. variables" "right hand side variables" ,
>> at(a)
>>
>> and see where the problem lies.
>>
>> Eva
>>
>>
>> 2009/3/15 <[email protected]>:
>>>
>>> Hi,
>>>
>>> First, I corrected all the typo.
>>>
>>> Then I changed constant item 5 to a0 in the first equation. I setted
>>> constant item a0 as a strating value 5 in my previous codes, because they
>>> did so in the example. Now I decide to scalar a new coef. a0. Is that ok?
>>> Or
>>> I need to set the constant item at other starting value?
>>>
>>> Second, I typed -set trace on- before running the stuff. Here's the error
>>> record:
>>>
>>>
>>> }
>>> -------------------------------------------------------------- end
>>> nlsurwellbehav ---
>>> - }
>>> - if _rc {
>>> - di as error "nlsur`eqn' returned " _rc
>>> = di as error "nlsurwellbehav returned " _rc
>>> nlsurwellbehav returned 111
>>> - di as error "verify that nlsur`eqn' is a function evaluator program"
>>> = di as error "verify that nlsurwellbehav is a function evaluator
>>> program"
>>> verify that nlsurwellbehav is a function evaluator program
>>> - exit _rc
>>> }
>>> }
>>> ---------------------------------------------------------------- end
>>> nlsur.Estimate ---
>>> end nlsur ---
>>> r(111);
>>>
>>> I am thinking there maybe another kind of errors in my codes. Say there's
>>> two items in my equation: a*lne and b*lne*lne. I think I should
>>> define
>>> them as:
>>>
>>> replace `lnc'=`a'*`lne'+`b'*``lnpe'*`lne''
>>>
>>> In my previous codes I defined them as:
>>>
>>> `lnc'=`a'*`lne'+`b'*`lnpe'*`lne'
>>>
>>> Does it cause the r(111)?
>>>
>>> Jingjing
>>>
*
* For searches and help try:
* http://www.stata.com/help.cgi?search
* http://www.stata.com/support/statalist/faq
* http://www.ats.ucla.edu/stat/stata/
