Dear Stata user,
I could create a coupled forest plot of sensitivity and specificity by a subgroup variable with the midas command using the following code: midas tp fp fn tn , by(subgroup) texts(0.50) bfor(dss) id(studyid) ford fors
The problem is that I do not manage to create a "nice" output. I have to modify the graph by hand to add the labels for each subgroup and customize the forestplot obtain.
Would you know how how I could add subheadings for the subgroup variable in bold if possible?
Another solution I have been looking at was to use admetan instead. I did one forestplot for sensitivity and one for specificity but do not manage to combine both without repeating the columns for study name and to keep the same formatting options. The code I used is:
admetan se lci_se uci_se, ///
by(subgroup variable) study(studyvar) nohet nooverall nosubgroup notable nowt ///
lcols(tp fn tn fp) effect(Sensitivity) forestplot(boxsca(0) ciopts(lwidth(vvthin)) ///
xsize(4) ysize(6) savedims(matname) ///
pointopts(msymbol(S) msize(tiny)) nonull astext(70)) saving($datadir/datafilename_se, replace) nograph
use $datadir/datafilename_se, clear
replace _LABELS = `"{bf:"' + _LABELS + `"}"' if _USE==0
forestplot, useopts saving(datafilegph_se, replace)
admetan sp lci_sp uci_sp, ///
by(subgroup variable) study(studyvar) nohet nooverall nosubgroup notable nowt ///
lcols(tp fn tn fp) effect(Sensitivity) forestplot(boxsca(0) ciopts(lwidth(vvthin)) ///
xsize(4) ysize(6) usedims(matname) ///
pointopts(msymbol(S) msize(tiny)) nonull astext(70)) saving($datadir/datafilename_sp, replace) nograph
use $datadir/datafilename_se, clear
replace _LABELS = `"{bf:"' + _LABELS + `"}"' if _USE==0
forestplot, useopts saving(datafilegph_sp, replace)
graph combine datafilegph_se.gph datafilegph_sp.gph, imargin(zero)
However this does not work. I am not familiar with this command and I would much appreciate your help.
I could create a coupled forest plot of sensitivity and specificity by a subgroup variable with the midas command using the following code: midas tp fp fn tn , by(subgroup) texts(0.50) bfor(dss) id(studyid) ford fors
The problem is that I do not manage to create a "nice" output. I have to modify the graph by hand to add the labels for each subgroup and customize the forestplot obtain.
Would you know how how I could add subheadings for the subgroup variable in bold if possible?
Another solution I have been looking at was to use admetan instead. I did one forestplot for sensitivity and one for specificity but do not manage to combine both without repeating the columns for study name and to keep the same formatting options. The code I used is:
admetan se lci_se uci_se, ///
by(subgroup variable) study(studyvar) nohet nooverall nosubgroup notable nowt ///
lcols(tp fn tn fp) effect(Sensitivity) forestplot(boxsca(0) ciopts(lwidth(vvthin)) ///
xsize(4) ysize(6) savedims(matname) ///
pointopts(msymbol(S) msize(tiny)) nonull astext(70)) saving($datadir/datafilename_se, replace) nograph
use $datadir/datafilename_se, clear
replace _LABELS = `"{bf:"' + _LABELS + `"}"' if _USE==0
forestplot, useopts saving(datafilegph_se, replace)
admetan sp lci_sp uci_sp, ///
by(subgroup variable) study(studyvar) nohet nooverall nosubgroup notable nowt ///
lcols(tp fn tn fp) effect(Sensitivity) forestplot(boxsca(0) ciopts(lwidth(vvthin)) ///
xsize(4) ysize(6) usedims(matname) ///
pointopts(msymbol(S) msize(tiny)) nonull astext(70)) saving($datadir/datafilename_sp, replace) nograph
use $datadir/datafilename_se, clear
replace _LABELS = `"{bf:"' + _LABELS + `"}"' if _USE==0
forestplot, useopts saving(datafilegph_sp, replace)
graph combine datafilegph_se.gph datafilegph_sp.gph, imargin(zero)
However this does not work. I am not familiar with this command and I would much appreciate your help.
