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: ''option ysi not allowed'' when using metan command


From   Amal Khanolkar <[email protected]>
To   "[email protected]" <[email protected]>
Subject   RE: st: ''option ysi not allowed'' when using metan command
Date   Wed, 10 Jul 2013 14:47:31 +0000

It should be ''sbe24_3.pkg'' which i think is the latest available.

Sorry that was a typo that occurred while I was copying in the syntax from my do file. It's here again, corrected:

*Generate dataset with RR, corresponding CIs, and grouping variables; group (5 nos) and outcome (3 no):
>
> input id rr lci uci group outcome
> 1 1.12 0.78 1.62 2 1
> 2 0.96 0.83 1.30 2 2
> 3 0.96 0.85 1.09 2 3
> 4 0.84 0.65 1.07 3 1
> 5 0.98 0.90 1.07 3 2
> 6 0.95 0.88 1.02 3 3
> 7 1.11 0.69 1.80 4 1
> 8 1.08 0.90 1.30 4 2
> 9 0.85 0.73 0.97 4 3
> 10 1.76 1.24 2.50 5 1
> 11 1.15 0.98 1.34 5 2
> 12 0.86 0.75 0.99 5 3
>  end
>
> *Create labels for the group variable:
>
> gen str immigrant_group=""
> replace immigrant_group ="Western europe and North America" if group==2
> replace immigrant_group ="Finland" if group==3
> replace immigrant_group ="Eastern Europe" if group==4
> replace immigrant_group ="Poland" if group==5
>
> *Create labels for the Outcome variable:
>
> gen str Outcome_type=""
> replace Outcome_type ="Early preterm" if outcome==1
> replace Outcome_type ="Late preterm" if outcome==2
> replace Outcome_type ="Postterm" if outcome==3
>
> *Create a sorter variable to instruct stata on the right order:
>
> ***defining a sorter variable to bring the graph results into the intended order
> gen sorter =.
> replace sorter =1 if immigrant_group=="Western europe and North America" & outcome==1
> replace sorter =2 if immigrant_group=="Western europe and North America" & outcome==2
> replace sorter =3 if immigrant_group=="Western europe and North America" & outcome==3
> replace sorter =4 if immigrant_group=="Finland" & outcome==1
> replace sorter =5 if immigrant_group=="Finland" & outcome==2
> replace sorter =6 if immigrant_group=="Finland" & outcome==3
> replace sorter =7 if immigrant_group=="Eastern Europe" & outcome==1
> replace sorter =8 if immigrant_group=="Eastern Europe" & outcome==2
> replace sorter =9 if immigrant_group=="Eastern Europe" & outcome==3
> replace sorter =10 if immigrant_group=="Poland" & outcome==1
> replace sorter =11 if immigrant_group=="Poland" & outcome==2
> replace sorter =12 if immigrant_group=="Poland" & outcome==3
>
>
> *sorting data into the correct order
> sort sorter immigrant_group outcome
>
> *Generate the forestplot:
>
> #delimit ;
> metan rr lci uci,
> by(immigrant_group) nosubgroup
>         xlabel( 0.4, 0.8, 1, 1.2, 1.4, 1.8, 2.2, 2.6, 3.0)
>         xtick(0.4, 0.8, 1, 1.2, 1.4, 1.6, 1.8, 2.0, 2.2, 2.4, 2.6, 3.0)
>         effect(Risk ratio)
>         force nowt nooverall nobox
>         label(namevar=immigrant_group)
>         sortby(sorter immigrant_group group)
>         lcols(immigrant_group)
>         title("Adjusted relative risks for preterm and postterm birth by immigrant groups in Sweden", size(small) color(black))
>     pointopt( msymbol(T) mcolor(black) msize(medsmall))
>     ciopt( lcolor(gs8) lwidth(medium) )
>    favours(Pretermbirth # Postterm birth)
>     graphregion(fcolor(white) lcolor(gs15) ifcolor(white) ilcolor(white)) ;
> #delimit cr
>
>
> The output that I get:
>
>
> Study     |     ES    [95% Conf. Interval]
> ---------------------+---------------------------------------------------
>      Western europe and N
> Western europe and N |    1.120     0.780     1.620
> Western europe and N |    0.960     0.830     1.300
> Western europe and N |    0.960     0.850     1.090
> ---------------------+---------------------------------------------------
>      Finland
> Finland              |    0.840     0.650     1.070
> Finland              |    0.980     0.900     1.070
> Finland              |    0.950     0.880     1.020
> ---------------------+---------------------------------------------------
>      Eastern Europe
> Eastern Europe       |    1.110     0.690     1.800
> Eastern Europe       |    1.080     0.900     1.300
> Eastern Europe       |    0.850     0.730     0.970
> ---------------------+---------------------------------------------------
>      Poland
> Poland               |    1.760     1.240     2.500
> Poland               |    1.150     0.980     1.340
> Poland               |    0.860     0.750     0.990
>
> option ysi not allowed
> r(198);
>
> end of do-file
>
> r(198);
>

Thanks,

/Amal 

________________________________________
From: [email protected] [[email protected]] on behalf of Nick Cox [[email protected]]
Sent: 10 July 2013 16:34
To: [email protected]
Subject: Re: st: ''option ysi not allowed'' when using metan command

-metan- is from SSC. (You may be using another version, which could be
contributing to the problems here. As ever, you are asked to explain
the origin of user-written programs you are referring to.)

I can't reproduce this. I get an error message "type mismatch".

I note that

replace immigrant_group ="Eastern Europe" if group==4
replace immigrant_group ="Poland" if group==4

looks wrong.

Nick
[email protected]


On 10 July 2013 14:25, Amal Khanolkar <[email protected]> wrote:
> Hi everyone,
>
> I'm getting the following error message when I'm trying to use the metan command to generate a forest plot. The code I use is below:
>
> *Generate dataset with RR, corresponding CIs, and grouping variables; group (5 nos) and outcome (3 no):
>
> input id rr lci uci group outcome
> 1 1.12 0.78 1.62 2 1
> 2 0.96 0.83 1.30 2 2
> 3 0.96 0.85 1.09 2 3
> 4 0.84 0.65 1.07 3 1
> 5 0.98 0.90 1.07 3 2
> 6 0.95 0.88 1.02 3 3
> 7 1.11 0.69 1.80 4 1
> 8 1.08 0.90 1.30 4 2
> 9 0.85 0.73 0.97 4 3
> 10 1.76 1.24 2.50 5 1
> 11 1.15 0.98 1.34 5 2
> 12 0.86 0.75 0.99 5 3
>  end
>
> *Create labels for the group variable:
>
> gen str immigrant_group=""
> replace immigrant_group ="Western europe and North America" if group==2
> replace immigrant_group ="Finland" if group==3
> replace immigrant_group ="Eastern Europe" if group==4
> replace immigrant_group ="Poland" if group==4
>
> *Create labels for the Outcome variable:
>
> gen str Outcome_type=""
> replace Outcome_type ="Early preterm" if outcome==1
> replace Outcome_type ="Late preterm" if outcome==2
> replace Outcome_type ="Postterm" if outcome==3
>
> *Create a sorter variable to instruct stata on the right order:
>
> ***defining a sorter variable to bring the graph results into the intended order
> gen sorter =.
> replace sorter =1 if immigrant_group=="Western europe and North America" & outcome==1
> replace sorter =2 if immigrant_group=="Western europe and North America" & outcome==2
> replace sorter =3 if immigrant_group=="Western europe and North America" & outcome==3
> replace sorter =4 if immigrant_group=="Finland" & outcome==1
> replace sorter =5 if immigrant_group=="Finland" & outcome==2
> replace sorter =6 if immigrant_group=="Finland" & outcome==3
> replace sorter =7 if immigrant_group=="Eastern Europe" & outcome==1
> replace sorter =8 if immigrant_group=="Eastern Europe" & outcome==2
> replace sorter =9 if immigrant_group=="Eastern Europe" & outcome==3
> replace sorter =10 if immigrant_group=="Poland" & outcome==1
> replace sorter =11 if immigrant_group=="Poland" & outcome==2
> replace sorter =12 if immigrant_group=="Poland" & outcome==3
>
>
> *sorting data into the correct order
> sort sorter immigrant_group outcome
>
> *Generate the forestplot:
>
> #delimit ;
> metan rr lci uci,
> by(immigrant_group) nosubgroup
>         xlabel( 0.4, 0.8, 1, 1.2, 1.4, 1.8, 2.2, 2.6, 3.0)
>         xtick(0.4, 0.8, 1, 1.2, 1.4, 1.6, 1.8, 2.0, 2.2, 2.4, 2.6, 3.0)
>         effect(Risk ratio)
>         force nowt nooverall nobox
>         label(namevar=immigrant_group)
>         sortby(sorter immigrant_group group)
>         lcols(immigrant_group)
>         title("Adjusted relative risks for preterm and postterm birth by immigrant groups in Sweden", size(small) color(black))
>     pointopt( msymbol(T) mcolor(black) msize(medsmall))
>     ciopt( lcolor(gs8) lwidth(medium) )
>    favours(Pretermbirth # Postterm birth)
>     graphregion(fcolor(white) lcolor(gs15) ifcolor(white) ilcolor(white)) ;
> #delimit cr
>
>
> The output that I get:
>
>
> Study     |     ES    [95% Conf. Interval]
> ---------------------+---------------------------------------------------
>      Western europe and N
> Western europe and N |    1.120     0.780     1.620
> Western europe and N |    0.960     0.830     1.300
> Western europe and N |    0.960     0.850     1.090
> ---------------------+---------------------------------------------------
>      Finland
> Finland              |    0.840     0.650     1.070
> Finland              |    0.980     0.900     1.070
> Finland              |    0.950     0.880     1.020
> ---------------------+---------------------------------------------------
>      Eastern Europe
> Eastern Europe       |    1.110     0.690     1.800
> Eastern Europe       |    1.080     0.900     1.300
> Eastern Europe       |    0.850     0.730     0.970
> ---------------------+---------------------------------------------------
>      Poland
> Poland               |    1.760     1.240     2.500
> Poland               |    1.150     0.980     1.340
> Poland               |    0.860     0.750     0.990
>
> option ysi not allowed
> r(198);
>
> end of do-file
>
> r(198);
>
*
*   For searches and help try:
*   http://www.stata.com/help.cgi?search
*   http://www.stata.com/support/faqs/resources/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/faqs/resources/statalist-faq/
*   http://www.ats.ucla.edu/stat/stata/


© Copyright 1996–2018 StataCorp LLC   |   Terms of use   |   Privacy   |   Contact us   |   Site index