[Paul Somwe]

Thanks for the example. What is biting is the observation number. It's better to automate the search rather than relying on a manual approach.

webuse diet, clear
qui stset dox, origin(time dob) enter(time doe) id(id) scale(365.25) fail(fail==1 3 13)
preserve
qui log using firstfile, name(log1) text replace
stmh hienergy
log close log1
insheet using "firstfile.log", clear
gen obs=_n
qui sum obs if regexm(v1, "P>chi2")
keep in `=r(min)+2'
local chi2= word(v1, 2)
local p= word(v1, 3)
local ci= "[`=word(v1, 4)' `=word(v1, 5)']"
restore
di "`chi2'"
di "`p'"
di "`ci'"

Hi Andrew Musau

Your code has worked but when I try to replacing some of your code with mine in the hope of achieving the same results I get an error. See code below:

. qui stset date_of_nextapp, fail(ltfup_status) id(artnumber) origin(art_start_date) enter(art_start_date)  scale(365.25) 

. preserve

. qui log using firstfile, name(log1) text replace

. stmh age_at_artstart2, c(2,1)

         failure _d:  ltfup_status
   analysis time _t:  (date_of_nextapp-origin)/365.25
             origin:  time art_start_date
  enter on or after:  time art_start_date
                 id:  artnumber

Maximum likelihood estimate of the rate ratio
  comparing age_at_artstart2==2 vs. age_at_artstart2==1

RR estimate, and lower and upper 95% confidence limits

        ----------------------------------------------------------
             RR       chi2        P>chi2      [95% Conf. Interval]
        ----------------------------------------------------------
          2.041     143.33        0.0000         1.812      2.300
        ----------------------------------------------------------

. log close log1
      name:  log1
       log:  C:\Users\Paul.Somwe\Documents\Tx abstract\firstfile.log
  log type:  text
 closed on:   7 Jul 2020, 14:20:38
--------------------------------------------------------------------------------------------------------------------------------------------------------------------------

. insheet using  "firstfile.log", clear
(3 vars, 19 obs)

. gen obs=_n

. qui sum obs if regexm(v1, "P>chi2")
v1 not found
r(111);

Thank you once again,

Paul

[Andrew Musau]

Show the output of the following:

insheet using "firstfile.log", clear
list

[Paul Somwe]

Hi Andrew Musau ,

I ran the exact code you shared i.e.

. webuse diet, clear
(Diet data with dates)

. qui stset dox, origin(time dob) enter(time doe) id(id) scale(365.25) fail(fail==1 3 13)

. preserve

. qui log using firstfile, name(log1) text replace

. stmh hienergy

failure _d: fail == 1 3 13
analysis time _t: (dox-origin)/365.25
origin: time dob
enter on or after: time doe
id: id

Maximum likelihood estimate of the rate ratio
comparing hienergy==1 vs. hienergy==0

RR estimate, and lower and upper 95% confidence limits

----------------------------------------------------------
RR chi2 P>chi2 [95% Conf. Interval]
----------------------------------------------------------
0.520 4.84 0.0277 0.288 0.941
----------------------------------------------------------

. log close log1
name: log1
log: C:\Users\Paul.Somwe\Documents\Tx abstract\firstfile.log
log type: text
closed on: 7 Jul 2020, 13:04:21
--------------------------------------------------------------------------------------------------------------------------

. insheet using "firstfile.log", clear
(1 var, 20 obs)

. keep in 14
(19 observations deleted)

. local chi2= word(v1, 2)

. local p= word(v1, 3)

. local ci= "[`=word(v1, 4)' `=word(v1, 5)']"

. restore

.
. stmh hienergy

failure _d: fail == 1 3 13
analysis time _t: (dox-origin)/365.25
origin: time dob
enter on or after: time doe
id: id

Maximum likelihood estimate of the rate ratio
comparing hienergy==1 vs. hienergy==0

RR estimate, and lower and upper 95% confidence limits

----------------------------------------------------------
RR chi2 P>chi2 [95% Conf. Interval]
----------------------------------------------------------
0.520 4.84 0.0277 0.288 0.941
----------------------------------------------------------

. di "`chi2'"


. di "`p'"


. di "`ci'"
[ ]

Notice that the chi2, p and ci values are not being displayed?

Thanks,

Paul

Hi Andrew,

Thanks once again for your help! I successfully ran the edited version of your example and it works just fine. However, when I tried to rerun the same code with minor edits made to stset command, I get an error (v1 not found). Kindly see code below:

. qui stset date_of_nextapp, fail(ltfup_status) id(artnumber) origin(art_start_date) enter(art_start_date)  scale(365.25) 

. preserve

. qui log using firstfile, name(log1) text replace

. stmh age_at_artstart2, c(2,1)

         failure _d:  ltfup_status
   analysis time _t:  (date_of_nextapp-origin)/365.25
             origin:  time art_start_date
  enter on or after:  time art_start_date
                 id:  artnumber

Maximum likelihood estimate of the rate ratio
  comparing age_at_artstart2==2 vs. age_at_artstart2==1

RR estimate, and lower and upper 95% confidence limits

        ----------------------------------------------------------
             RR       chi2        P>chi2      [95% Conf. Interval]
        ----------------------------------------------------------
          2.041     143.33        0.0000         1.812      2.300
        ----------------------------------------------------------

. log close log1
      name:  log1
       log:  C:\Users\Paul.Somwe\Documents\Tx abstract\firstfile.log
  log type:  text
 closed on:   7 Jul 2020, 14:20:38
--------------------------------------------------------------------------------------------------------------------------------------------------------------------------

. insheet using  "firstfile.log", clear
(3 vars, 19 obs)

. gen obs=_n

. qui sum obs if regexm(v1, "P>chi2")
v1 not found
r(111);

Thanks,

Paul

[Andrew Musau]

You have not responded to #13. Show me the output of the list command

qui stset date_of_nextapp, fail(ltfup_status) id(artnumber) origin(art_start_date) enter(art_start_date) scale(365.25)
preserve
qui log using firstfile, name(log1) text replace
stmh age_at_artstart2, c(2,1)
log close log1
insheet using "firstfile.log", clear
list

[Paul Somwe]

You have not responded to #13. Show me the output of the list command

qui stset date_of_nextapp, fail(ltfup_status) id(artnumber) origin(art_start_date) enter(art_start_date) scale(365.25)
preserve
qui log using firstfile, name(log1) text replace
stmh age_at_artstart2, c(2,1)
log close log1
insheet using "firstfile.log", clear
list

Hi Andrew,

See output below:

            
1.    stmhage_at_artstart2            
    failure _d:  ltfup_status            
                
    c2    v3        
        .        
                

                
2.    stmhage_at_artstart2            
    analysis time _t:  (date_of_nextapp-origin)/365.25            
                
    c2    v3        
        .        
                

                
3.    stmhage_at_artstart2            
    origin:  time art_start_date            
                
    c2    v3        
        .        
                

                
4.    stmhage_at_artstart2            
    enter on or after:  time art_start_date            
                
    c2    v3        
        .        
                

                
5.    stmhage_at_artstart2            
    id:  artnumber            
                
    c2    v3        
        .        
                

                
6.    stmhage_at_artstart2            
    Maximum likelihood estimate of the rate ratio            
                
    c2    v3        
        .        
                

                
7.    stmhage_at_artstart2            
    comparing age_at_artstart2==2 vs. age_at_artstart2==1            
                
    c2    v3        
        .        
                

                
8.    stmhage_at_artstart2            
    RR estimate            
                
    c2    v3        
    and lower and upper 95% confidence limits    .        
                

                
9.    stmhage_at_artstart2            
                
                
    c2    v3        
        .        
                

                
10.    stmhage_at_artstart2            
    RR       chi2        P>chi2      [95% Conf. Interval]            
                
    c2    v3        
        .        
                

                
11.    stmhage_at_artstart2            
                
                
    c2    v3        
        .        
                

                
12.    stmhage_at_artstart2            
    2.041     143.33        0.0000         1.812      2.300            
                
    c2    v3        
        .        
                

                
13.    stmhage_at_artstart2            
                
                
    c2    v3        
        .        
                

                
14.    stmhage_at_artstart2            
    . log close log1            
                
    c2    v3        
        .        
                

                
15.    stmhage_at_artstart2            
    name:  log1            
                
    c2    v3        
        .        
                

                
16.    stmhage_at_artstart2            
    log:  C:\Users\Paul.Somwe\Documents\Tx abstract\firstfile.log            
                
    c2    v3        
        .        
                

                
17.    stmhage_at_artstart2            
    log type:  text            
                
    c2    v3        
        .        
                

                
18.    stmhage_at_artstart2            
    closed on:   7 Jul 2020            
                
    c2    v3        
    15:32:51    .        
                

                
19.    stmhage_at_artstart2            
            -..    
                
    c2    v3        
        .

[Andrew Musau]

Thanks. Try

insheet using "firstfile.log", clear
gen obs=_n
qui sum obs if regexm(stmhage_at_artstart2, "P>chi2")
keep in `=r(min)+2'
local chi2= word(stmhage_at_artstart2, 2)
local p= word(stmhage_at_artstart2, 3)
local ci= "[`=word(stmhage_at_artstart2, 4)' `=word(stmhage_at_artstart2, 5)']"
restore
di "`chi2'"
di "`p'"
di "`ci'"

[Paul Somwe]

Hi Andrew,

The above edited code has worked. Just for my own knowledge, does this mean that there is no other straightforward way to obtain these values? Why doesn't the

. return list

scalars:
                 r(RR) =  2.041365521809395

command output the p and confidence interval values together with RR value. Otherwise, your help is very much appreciated!

Thanks,

Paul

[Leonardo Guizzetti]

Paul, more recent versions of the -stmh- command do return those values as scalars. This is the case in my copy of Stata 16.1.

[Andrew Musau]

Did you follow the earlier advice to update your Stata installation? It appears that this was fixed in a recent update.

update all

[Paul Somwe]

Paul, more recent versions of the -stmh- command do return those values as scalars. This is the case in my copy of Stata 16.1.

Hi Leonardo Guizzetti

Guess I need to get myself a copy of STATA 16 then, thanks for your feedback!

Regards,

Paul

[Paul Somwe]

Did you follow the earlier advice to update your Stata installation? It appears that this was fixed in a recent update.

update all

Hi Andrew Masau,

Yes I did, though I got an error when downloading the update files. I suspect my internet network connection signal is weak. I resorted to going to the STATA website to download the update. I will give you feedback on whether the update will work or not.

Thank you,

Paul

[Paul Somwe]

Hi Andrew Musau,

I have run into another frustrating situation again. I am not sure why it is so difficult to obtain stored results in STATA15/IC. I executed the following command:

strate facility_code, per(1000)

         failure _d:  ltfup_status
   analysis time _t:  (date_of_nextapp-origin)/365.25
             origin:  time art_start_date
  enter on or after:  time art_start_date
                 id:  artnumber

Estimated rates (per 1000) and lower/upper bounds of 95% confidence intervals
(15288 records included in the analysis)

  +-----------------------------------------------------+
  | facili~e      D        Y     Rate    Lower    Upper |
  |-----------------------------------------------------|
  |        1   2617   5.0111   522.24   502.61   542.64 |
  |        2   1030   2.8195   365.31   343.67   388.31 |
  |        3   2798   4.2639   656.21   632.34   680.98 |
  |        4   2668   4.4831   595.12   572.96   618.13 |
  +-----------------------------------------------------+

The

 return list

command does not provide any output of the stored rate values. Imagine I have a over 200 facilities and I need the rate and ci for each, does this mean I will have to manually copy the values into excel?

Thanks,

Paul

[Andrew Musau]

It is unfortunate that Stata does not store these scalars. I can replicate the problem with the most updated version of Stata 16. You can use the procedure that I suggested earlier, try to understand what the code does. Below I highlight the lines that you need to change in your code, the rest should stay the same.

webuse diet, clear
stset dox, origin(time doe) id(id) scale(365.25) fail(fail==1 3 13)
stsplit ageband, at(40(10)70) after(time=dob) trim
preserve
qui log using firstfile, name(log1) text replace
strate ageband, per(1000)
log close log1
insheet using "firstfile.log", clear
gen obs=_n
levelsof obs if regexm(v1, "Lower     Upper"), local(first)
levelsof obs if regexm(v1, "Notes"), local(last)
keep if inrange(obs, `first', `=`last'-2')
drop in 2
replace v1= trim(itrim(v1))
split v1, p(" ")
keep v12-v17
export excel using myfile, replace
restore

Res.:

 strate ageband, per(1000)

         failure _d:  fail == 1 3 13
   analysis time _t:  (dox-origin)/365.25
             origin:  time doe
                 id:  id
               note:  ageband<=40 trimmed

Estimated failure rates
Number of records  =       729

  +----------------------------------------------------+
  | ageband    D        Y      Rate    Lower     Upper |
  |----------------------------------------------------|
  |      40    6   0.9070    6.6152   2.9719   14.7246 |
  |      50   18   2.1070    8.5428   5.3823   13.5591 |
  |      60   22   1.4933   14.7325   9.7007   22.3746 |
  +----------------------------------------------------+
   Notes: Rate = D/Y = failures/person-time (per 1000).
          Lower and Upper are bounds of 95% confidence intervals.



. import excel myfile, first clear
(6 vars, 3 obs)

. l

     +----------------------------------------------------+
     | ageband    D        Y      Rate    Lower     Upper |
     |----------------------------------------------------|
  1. |      40    6   0.9070    6.6152   2.9719   14.7246 |
  2. |      50   18   2.1070    8.5428   5.3823   13.5591 |
  3. |      60   22   1.4933   14.7325   9.7007   22.3746 |
     +----------------------------------------------------+

[Paul Somwe]

Thank you Andrew Musau, your help is greatly appreciated!