I am trying to translate a S-PLUS command: var(x). The description of the command is: 'var', 'cov' and 'cor' compute the variance of 'x' and the covariance or correlation of 'x' and 'y' if these are vectors. If 'x' and 'y' are matrices then the covariances (or correlations) between the columns of 'x' and the columns of 'y' are computed.
Below you find the result of this command when applied to a modified auto dataset (i.e. after -drop make rep78 foreign-).
,price,mpg,headroom,trunk,length,turn,displacement,gear.ratio
price,28360.29156,4017.557201,134067.0459,-422.1304035,28360.29156,4017.557201,134067.0459,-422.1304035
mpg,-102.513884,-18.305072,-374.92521,1.626616,-102.513884,-18.305072,-374.92521,1.626616
headroom,9.725565,1.579785,36.86505,-0.1458571,9.725565,1.579785,36.86505,-0.1458571
trunk,69.202518,11.310626,239.087,-0.992773,69.202518,11.310626,239.087,-0.992773
weight,16370.92188,2931.725287,63873.45057,-269.2507495,16370.92188,2931.725287,63873.45057,-269.2507495
length,495.789893,84.660866,1707.76009,-7.0751459,495.789893,84.660866,1707.76009,-7.0751459
turn,84.660866,19.354313,313.83191,-1.3575823,84.660866,19.354313,313.83191,-1.3575823
displacement,1707.760089,313.831914,8434.07479,-34.7333827,1707.760089,313.831914,8434.07479,-34.7333827
gear.ratio,-7.075146,-1.357582,-34.73338,0.2081979,-7.075146,-1.357582,-34.73338,0.2081979
P.S. -collapse- reduces my dataset to just one column: is there any way to keep the column v1 with the panel identifier from the original dataset?
At 02.33 19/10/2007 -0400, "Austin Nichols" wrote:
>The first part is
> collapse v2-v17, by(v1)
>but I don't understand what you mean by "I would like to calculate the
>variance matrix for such new dta and saving it in one more new dta."
>
>On 10/18/07, [email protected] <[email protected]> wrote:
>> I have one dta of 17 columns and 354 rows. The first column, named id, contains the panel identifier (an integer from 1 to 63). I would like to produce a new dta file with 17 columns (keeping the original names) and 63 rows, containing the id variable, and the mean of the remaining 16 columns calculated by the id variable.
>> I know that I can have such means by -mean- and -tabstat-, but how can easily export the results in a new dataset? Next, I would like to calculate the variance matrix for such new dta and saving it in one more new dta.
>> How can I do?
*
* For searches and help try:
* http://www.stata.com/support/faqs/res/findit.html
* http://www.stata.com/support/statalist/faq
* http://www.ats.ucla.edu/stat/stata/
