Announcement

Collapse
No announcement yet.
X
  • Filter
  • Time
  • Show
Clear All
new posts

  • Altering proportions to percentages in forest plot

    Hello all,

    I have a question and was wondering if someone could help me with it. It would be greatly appreciated!

    I am making a forest plot of prevalence rates in Stata 18. This resulted in the following code:

    Code:
    meta forestplot _id  Population _plot _esci, subgroup(Setting) prevalence nooverall noohetstats noohomtest noosigtest nogsigtests nogwhomtests noghetstats nogbhomtests nogmarkers nonotes scheme(s2color) bodyopts(justification(left))
    The forest plot is looking how I want to, but I would prefer to report the proportions times a 100 (0.44 becomes 44.1 for example). How do I code this?

    In metaprop I used the command power(2), but option power() is not allowed.
    Then I found the option of eform_option(string), but I can't find an example on how to write the string and I only end up with invalid 'eform_option. For example, if I try eform_option("prevalence" scale(100))
    Does anyone know how to make this happen/what command to give?


    Background: In my data-file I include multiple studies. I extracted number of participants and number of diagnoses. Stata calculates the proportions/prevalences and CI.

    Thank you in advance for your help!

    Karin

  • #2
    The -prevalence- option provides proportions. The -scale()- suboption is allowed when used with the -transform(invftukey)- option.

    Code:
    help meta forestplot
    Code:
    webuse metaespropset, clear
    local opts nooverall noohetstats noohomtest noosigtest nogsigtests nogwhomtests noghetstats nogbhomtests nogmarkers nonotes scheme(s2color) bodyopts(justification(left))
    
    meta forestplot, prevalence `opts'
    meta forestplot, transform(invftukey, scale(100)) `opts'
    Click image for larger version

Name:	Graph.png
Views:	1
Size:	24.9 KB
ID:	1771868


    Click image for larger version

Name:	Graph1.png
Views:	1
Size:	22.6 KB
ID:	1771869

    Comment

    Working...
    X