Statalist


[Date Prev][Date Next][Thread Prev][Thread Next][Date Index][Thread Index]

Re: st: AW: Randomly assigning values with a specific distribution


From   Dorothy Bridges <[email protected]>
To   [email protected]
Subject   Re: st: AW: Randomly assigning values with a specific distribution
Date   Mon, 5 Oct 2009 09:08:04 -0400

Ah, very useful, thanks!

On Mon, Oct 5, 2009 at 9:01 AM, Martin Weiss <[email protected]> wrote:
>
> <>
>
> My -irecode- approach creates a variable with values that range from 1 to 5.
> If ever you wanted irregularly spaced values (your x1 to x5), you could
> enter them into
>
>
> *************
> clear*
> set obs 100000
>
> tempvar unif
> gen `unif'=runiform()
>
> gen byte x= /*
> your x1 equals 3 here
> */ inrange(`unif',0,.4)*3+ /*
> your x2 equals 7
> */ inrange(`unif',.4,.5)*7+ /*
> your x3 equals 12
> */ inrange(`unif',.5,.8)*12+ /*
> your x4 equals 19
> */ inrange(`unif',.8,.85)*19+ /*
> your x4 equals 34
> */ inrange(`unif',.85,1)*34
>
> ta x
> *************
>
>
>
> HTH
> Martin
>
>
> -----Ursprüngliche Nachricht-----
> Von: [email protected]
> [mailto:[email protected]] Im Auftrag von Dorothy Bridges
> Gesendet: Montag, 5. Oktober 2009 14:56
> An: [email protected]
> Betreff: Re: st: AW: Randomly assigning values with a specific distribution
>
> Thank you Martin!
>
> On Mon, Oct 5, 2009 at 8:51 AM, Martin Weiss <[email protected]> wrote:
>>
>> <>
>>
>>
>>
>> *************
>> clear*
>> set obs 10000
>>
>> gen x=irecode(runiform(), 0, 0.4, /*
>> */  0.5, 0.8, .85)
>>
>> ta x
>> *************
>>
>>
>>
>> HTH
>> Martin
>>
>> -----Ursprüngliche Nachricht-----
>> Von: [email protected]
>> [mailto:[email protected]] Im Auftrag von Dorothy
> Bridges
>> Gesendet: Montag, 5. Oktober 2009 14:50
>> An: [email protected]
>> Betreff: st: Randomly assigning values with a specific distribution
>>
>> Dear Statalist:
>>
>> I would like to create a random variable taking five different values
>> whose distribution mirrors that of another variable.  In other words,
>> I have one variable whose distribution is, say:
>>
>> value      %
>> x1         40
>> x2         10
>> x3         30
>> x4         5
>> x5         15
>>
>> ... and I want to create another variable with the same values and
>> distribution, but randomly assigned.  Something like gen randomvar =
>> mydist() instead of uniform().
>>
>> Thanks,
>> Dorothy
>> *
>> *   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/
>>
>>
>> *
>> *   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/
>>
>
> *
> *   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/
>
>
> *
> *   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/
>

*
*   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/



© Copyright 1996–2024 StataCorp LLC   |   Terms of use   |   Privacy   |   Contact us   |   What's new   |   Site index