Bookmark and Share

Notice: On April 23, 2014, Statalist moved from an email list to a forum, based at statalist.org.


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

Re: st: Table to count how many times an event occurs with another


From   Eric Booth <[email protected]>
To   "<[email protected]>" <[email protected]>
Subject   Re: st: Table to count how many times an event occurs with another
Date   Thu, 4 Aug 2011 15:34:59 +0000

<>

Try:

***********
clear
input str12(Date              Time )     D1 D2 D3 D4
"01/01/2008"     "8:00"       1   0    0   1
"01/01/2008"     "9:00"       0   1    0   0
"01/01/2008"    "10:00"      0   1    1   0
"01/01/2008"     "9:00"       0   0    0   0
"01/01/2008"    "10:00"      1   1    1   1
"01/01/2008"     "9:00"       0   1    0   1
"01/01/2008"    "10:00"      1   0    0   1
end


**number of times each pair co-occurs:
tuples D1-D4, display max(2)
*tuples 5-10 are what you want:
forval i = 5/`ntuples' {
		loc one: piece 1 2 of "`tuple`i''"
		loc two: piece 2 2 of "`tuple`i''"
    g myvar`i' = 1 if `one'==1 & `two'==1
    lab var myvar`i' "`tuple`i''"
    }

**count number of times in each Time interval:
preserve
collapse (count) myvar5-myvar10, by(Date Time)
l Time my*, noobs 
restore

*or you can use -egen count-
**********

- Eric
__
Eric A Booth
Public Policy Research Institute
Texas A&M University
[email protected]

On Aug 4, 2011, at 10:07 AM, Katia Bobulova wrote:

> This is an example of my databse:
> 
> Date              Time      D1 D2 D3 D4
> 01/01/2008     8:00       1   0    0   1
> 01/01/2008     9:00       0   0    0   0
> 01/01/2008    10:00      0   1    1   0
> .....               .......       .    .     .   .
> 
> For every day I have something similar to the above example with dummy
> variables.
> In the fist row (8:30) I have that two dummies happen at the same time
> and also in the last row (10:00).
> I want to construct a table, in which I have the number of times ( for
> each interval throughout my whole sample) I have that events D1 and D4
> happen together and D2 and D3 happen together and so on for all
> possible combinations.
> 
> Thanks,
> Katia
> 
> 
> 
> 
> 
> 2011/8/4 Anders Alexandersson <[email protected]>:
>> Please provide the original example data of the 4 events and 10
>> observations from which you want to create the table.
>> The reason I ask is that I do not understand your provided 4*4 table.
>> 
>> Anders Alexandersson
>> [email protected]
>> 
>> On Thu, Aug 4, 2011 at 10:08 AM, Katia Bobulova
>> <[email protected]> wrote:
>>> Because it doesn't do what I want and anyway it is not possible to use
>>> tabulate with more than two variables.
>>> 
>>> Katia
>>> 
>>> 2011/8/4 Nick Cox <[email protected]>:
>>>> Why not -tabulate-?
>>>> 
>>>> Nick
>>>> 
>>>> On 4 Aug 2011, at 10:52, Katia Bobulova <[email protected]>
>>>> wrote:
>>>> 
>>>>> Dear All,
>>>>> 
>>>>> I have many events in my dataset and I want to count how many times
>>>>> one event happens with another one.
>>>>> 
>>>>> Assuming fro example 4 events and ten observations, I would like to
>>>>> have a table like this:
>>>>> 
>>>>>    x1 x2 x3 x4
>>>>> x1  10  2   1  3
>>>>> x2  1  10  0   0
>>>>> x3  0  3   10  1
>>>>> x4 2   5   0   10
>>>>> 
>>>>> Could you please help me?
>> 
>> *
>> *   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 1996–2018 StataCorp LLC   |   Terms of use   |   Privacy   |   Contact us   |   Site index