Bookmark and Share

Notice: On March 31, it was announced that Statalist is moving from an email list to a forum. The old list will shut down at the end of May, and its replacement, statalist.org is already up and running.


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

Re: st: calculating many distances and storing them in many new variables


From   "Vitorino, Maria Ana" <vitorino@wharton.upenn.edu>
To   "<statalist@hsphsun2.harvard.edu>" <statalist@hsphsun2.harvard.edu>
Subject   Re: st: calculating many distances and storing them in many new variables
Date   Fri, 21 Oct 2011 10:16:17 +0000

Dear Yuval,
Thanks. But the goal  is different. I know to which hospital each patient went. What I'm trying to do is to calculate the distance between each patient and each hospital alternative (ie all the hospitals that the patient could have decided to go to). 
I'm guessing this can be done with some sort of loop...

Ana


On Oct 21, 2011, at 4:42 AM, "Yuval Arbel" <yuval.arbel@gmail.com> wrote:

> Anna,
> 
> I'm not sure what your precise goal is. But if your target is only to
> map what hospital each patient went, may I suggest the following:
> 
> Suppose you have a column of coordinates under "patient" and another
> column under "hospitals"
> If you are working with STATA11 you can try running:
> 
> reg patient i.hospitals
> 
> Let me show you what is the output you get by using one of the
> examples I ran: I collected a small dataset, which measures land
> values (rent) and distance from Tel Aviv center (distance):
> 
> . reg rent i.distance
> 
>      Source |       SS       df       MS              Number of obs =      55
> -------------+------------------------------           F(  9,    45) =   12.43
>       Model |   294279904     9  32697767.1           Prob > F      =  0.0000
>    Residual |   118368183    45  2630404.07           R-squared     =  0.7131
> -------------+------------------------------           Adj R-squared =  0.6558
>       Total |   412648087    54  7641631.24           Root MSE      =  1621.9
> 
> ------------------------------------------------------------------------------
>        rent |      Coef.   Std. Err.      t    P>|t|     [95% Conf. Interval]
> -------------+----------------------------------------------------------------
>    distance |
>       1000  |  -8245.833    1238.71    -6.66   0.000    -10740.72   -5750.943
>       1500  |  -8087.026   1038.817    -7.78   0.000    -10179.31   -5994.741
>       2000  |  -6353.833   1067.634    -5.95   0.000    -8504.158   -4203.509
>       2500  |  -7560.333   1480.542    -5.11   0.000     -10542.3    -4578.37
>       3000  |  -6545.958   1097.999    -5.96   0.000    -8757.442   -4334.475
>       3500  |      -9500   1324.237    -7.17   0.000    -12167.15    -6832.85
>       4000  |  -9891.905   1119.184    -8.84   0.000    -12146.06   -7637.752
>       4500  |  -10258.33    1238.71    -8.28   0.000    -12753.22   -7763.443
>       5000  |  -11600.33   1872.753    -6.19   0.000    -15372.25   -7828.414
>             |
>       _cons |   13433.33   936.3767    14.35   0.000     11547.37    15319.29
> ------------------------------------------------------------------------------
> 
> Note that the distance variable includes values from 500 to 5000
> meters. The command made the 500 meter distance the base category.
> 
> On Fri, Oct 21, 2011 at 5:13 AM, Maria Ana Vitorino
> <vitorino@wharton.upenn.edu> wrote:
>> Dear StataList users,
>> 
>> Suppose we have the following toy data which has a list with patients, the
>> hospital to which they went (hosp_ch) and the coordinates for both.
>> 
>> patient_id hosp_ch      lat_pat lng_pat lat_hosp        lng_hosp
>> 1               a               2               4               5
>>     6
>> 2               a               1               3               5
>>     6
>> 8               c               3               5               10
>>    12
>> 9               a               5               2               5
>>     6
>> 12              b               8               6               8
>>     9
>> 
>> 
>> What I would like to do is:
>> **To create new variables with the distances from every patient to every
>> possible hospital in the data. So, I would like 3 new columns which will
>> contain the distance from each patient to each hospital in the data.
>> **Also, I would like to have those new columns labeled dist_a, dist_b and
>> dist_c.
>> 
>> Is there an efficient way to achieve this?
>> In the real data, I have many more patients and hospitals (hundreds in fact)
>> so I would like to generate these variables in an as automated way as
>> possible.
>> 
>> Any help is appreciated.
>> Thanks!
>> Ana
>> 
>> 
>> 
>> 
>> 
>> 
>> 
>> 
>> 
>> 
>> 
>> 
>> 
>> 
>> 
>> 
>> 
>> 
>> 
>> 
>> 
>> 
>> 
>> 
>> 
>> 
>> 
>> 
>> 
>> 
>> 
>> 
>> 
>> 
>> 
>> 
>> 
>> *
>> *   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/
>> 
> 
> 
> 
> -- 
> Dr. Yuval Arbel
> School of Business
> Carmel Academic Center
> 4 Shaar Palmer Street, Haifa, Israel
> e-mail: yuval.arbel@gmail.com
> 
> *
> *   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 1996–2014 StataCorp LP   |   Terms of use   |   Privacy   |   Contact us   |   Site index