st: RE: do file: t-score, dfuller, to sw regress

[Nick Cox <n.j.cox@durham.ac.uk>]

I haven't tried to understand the detail here, not least "excel" and whatever "vlooking up" is (perhaps a technical term, perhaps a typo: Stata experts aren't usually MS Excel experts too), but it sounds as if you should be looking at -help density functions- and particularly for Student's t functions, direct and inverse. Perhaps you should be putting results in a variable, and then sorting. 

Statistically, your procedure sounds a bit difficult to defend, but that is different territory. 

Nick 
n.j.cox@durham.ac.uk 

steven quattry

I am on a quest to create a do-file that would perform (1) bi-variate
regressions, sort by t-score, delete observations below a certain
threshold, and then (2) run Dickey-Fuller on the remaining set of
variables, list only those that pass a Dickey-Fuller test at the 1%
critical level, then (3) filter out any missing data in my dataset via
a filter and then, of the data that passes through these three, I am
looking to:


- sort the remaining variables by t-score, highest to lowest

- delete the variables that are not amongst the 72 highest t-score variables

- then run a sw regress with these 72 variables, sorted by t-score still



With the help of many on this listserv, I have been able to achieve
(1), (2) and (3) (code listed below in 2.1-2.2).  However currently I
am copying the output from (1)- (3) into excel, vlooking up the
t-scores, sorting by t-scores, and then pasting this back into my
do-file to do the sw regress (2.3 in code below).  I suppose I was
hoping to achieve some insight as to coding or possible help topics in
stata that would allow me to build this in as it would save me hours
of tedious work each day.  If anyone can suggest some code or at least
point me in the right direction of how I might learn to do this, I
would be very appreciative.



Thank you for your consideration,



-Steven





I am using Stata/SE 11.1 for Windows



* 2.1 T-test and Dickey-Fuller Filter



    drop if n<61



    tsset n

tempname memhold

    tempname memhold2

    postfile `memhold' str20 var  double t using t_score, replace

    postfile `memhold2' str20 var2 double df_pvalue using df_pvalue, replace



    foreach var of varlist swap1m-allocglobal uslib1m-infdify
dswap1m-dallocglobal6 {

        qui reg dhealth `var'

        matrix e =e(b)

        matrix v = e(V)

        local t = abs(e[1,1]/sqrt(v[1,1]))

if `t' < 1.7 {

drop `var'

}

else {

local mylist "`mylist' `var'"

post `memhold' ("`var'") (`t')

}

    }

    postclose `memhold'



    foreach l of local mylist {

   qui dfuller `l', lag(1)

   if r(p) > .01 {

       drop `l'

   }

   else {

       local mylist2 "`mylist2' `l'"

       post `memhold2' ("`l'") (r(p))

   }

    }

    postclose `memhold2'

    keep `mylist2'

log on

    use t_score,clear

    gsort -t

    l

    use df_pvalue, clear

    l

log off

restore



* 2.2 Missing data Filter

preserve

    drop if n<61



    foreach x of varlist `mylist2' {

        qui sum `x'

            if r(N)<72 {

                di in red "`x'"

                drop `x'

            }

            else {

                local myvar "`myvar' `x'"

            }

    }



    sum date

    keep if date==r(max)



    foreach x of varlist `myvar' {

        if `x'==. {

            drop `x'

        }

        else {

            local myvar2 "`myvar2' `x'"

        }

    }

log on

d `myvar2'

log off

restore




* 2.3 Stepwise Regressions



preserve

    drop if n<61



    local x "Here is where I paste in variables after sorting by
t-score and keeping only 72 highest"





log on

    sw reg dhealth `x', pe(0.05)





vif


*
*   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/