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 on April 23, and its replacement, is already up and running.

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

RE: st: Combining Frequency Tables

From   "Nick Cox" <>
To   <>
Subject   RE: st: Combining Frequency Tables
Date   Tue, 1 Jun 2010 18:50:40 +0100

This makes a lot of sense to me, because the need for it used to bite me a lot. 

As Austin implies, you need to -reshape- (or -stack-) to get official Stata commands to work here. That's the bad news. But -tabm- (in the package on SSC -tab_chi-) does it for you. That's the good news. Use -ssc inst tab_chi- to download. 

Stata 7 is required. 


Austin Nichols

Oren Jalon <>:
Doesn't make a lot of sense to me, but try e.g.:

ren varX fake1
ren varY fake2
g long i=_n
keep i fake1 fake2
reshape long fake, i(i) j(j)
tab fake j
tab fake

On Tue, Jun 1, 2010 at 10:09 AM, Oren Jalon <> wrote:

> Not quite.  For example, if Var X has 100 records and Var Y has 200 records
> where Var X has #6 twenty times and and  Var Y has #6 ten times, the
> frequency of the variable would be:
> (20+10) /(100+200) = 30/300 or 0.1
> I guess 'table' is the wrong term.  I need the combined frequency of two
> variables.  Does this make sense?

 On 6/1/2010 3:00 PM, Maarten buis wrote:

>> --- Oren Jalon wrote:
>>> I have two variables (Var X and Var Y) which both have values ranging
>>> from 1 to 9.  I can tabulate the frequency of values from each variable
>>> individually but is there a way to combine all the values and get a
>>> combined frequency table?
>> -tab x y- will give you a cross tabulation, which is I suppose what
>> you mean with a "combined frequency table". For more see: -help tab2-.

*   For searches and help try:

© Copyright 1996–2015 StataCorp LP   |   Terms of use   |   Privacy   |   Contact us   |   Site index