------------------------------------------------------------------------------- help formetaeff-------------------------------------------------------------------------------

Title

metaeff-- Meta-analysis module for effect sizes calculations

Syntax

metaeffvarname1varname2[if] [in] [,options]where

varvame1the variable corresponding to the estimated effect sizes.

varvame2the variable corresponding to the estimated standard errors of the effect sizes.

optionsDescription ------------------------------------------------------------------------- Optionsni(varname)specifies the number of units in the intervention groupnc(varname)specifies the number of units in the control groupi(varname)specifies the number of events in the intervention groupc(varname)specifies the number of events in the control} grouporval(varname)specifies the odds ratioci95lo(varname)specifies the lower end of 95% confidence interval of the mean difference or odds ratioci95up(varname)specifies the upper end of 95% confidence interval of the mean difference or odds ratiomd(varname)specifies the mean difference (not standardised)meani(varname)specifies the mean of the intervention groupmeanc(varname)specifies the mean of the control groupsdi(varname)specifies the standard deviation in the intervention groupsdc(varname)specifies the standard deviation in the control groupci95loi(varname)specifies the lower end of the 95% confidence interval of the mean for the intervention groupci95upi(varname)specifies the upper end of the 95% confidence interval of the mean for the intervention groupci95loc(varname)specifies the lower end of the 95% confidence interval of the mean for the control groupci95upc(varname)specifies the upper end of the 95% confidence interval of the mean for the control groupp(varname)specifies the p value for a two-sample t-testt(varname)specifies the t value for a two-sample t-test (assumes df=ni+nc-2)orselects odds ratio (1b) over the default risk difference method (1a), when ni, nc, i & c are availableowritespecifies thatvarvame1andvarvame2will be overwritten, if they already exist in the datasetinfovarprovides information on the method selected (for each case) in a new string variable _method

DescriptionThe

metaeffcommand provides a way to calculate the effect sizes (and the respective standard errors) of research studies, for use with meta-analysis methods (see meta, metan & metaan). The methods used for the calculations have been derived from the Cochrane Collaboration handbook. The calculated effect sizes are standardised mean differences and binary data are transformed towards that end.metaeffis meant to be used for meta-analysing studies with various types of outcomes; if all studies provide binary outcomes thenmetaeffshould not be used since better approaches exist and a transformation is not required.

Dichotomous data

Method 1a, based on Risk Difference. Requiresni,nc,i&a.

Method 1b, based on Odds Ratio. Requiresni,nc,i&a.

Method 2, based on Odds Ratio. Requiresni,nc,orval,ci95lo&ci95up.

Continuous data

Method 3, based on Mean Difference. Requiresni,nc,mdor (meaniandmeanc) ,ci95lo&ci95up.

Method 4, based on Mean Difference. Requiresni,nc,mdor (meaniandmeanc),sdi&sdc.

Method 5, based on Mean Difference. Requiresni,nc,mdor (meaniandmeanc),ci95loi,ci95upi,ci95loc,ci95upc.

Method 6, based on Mean Difference. Requiresni,nc,mdor (meaniandmeanc) &port.

Dichotomous or Continuous data

Method 7, based on z-value. Requiresni,nc&port.

RemarksSome methods are more accurate than others and have been prioritised accorgingly (in case user has provided input that allows 2 or more methods to be selected). For dichotomous data the method order is

2,1a,1b,7and for continuous data4,5,3,6& finally7. Methods6and (especially)7should only be used if no other method can be selected (due to distibutional assumptions and the use of the reported p-value is usually inaccurate). The methods are described in Kontopantelis and Reeves, 2009 and have been prioritised according to expected precision: that is, the expectation that the effect size and associated variance computed from the input data will be accurate. As a general rule, the fewer the number of mathematical transformations involved in getting from the 'raw data' to the statistical parameters used as input for the method, the higher the expected precision.

Examples

. metaeff eff SEeff, ni(ivsize) nc(clsize) i(ivevents) c(ivevents)

. metaeff eff SEeff, ni(ivsize) nc(clsize) i(ivevents) c(ivevents) orowrite

. metaeff eff2 SEeff2, ni(ivsize) nc(clsize) md(meandiff) sdi(ivsd)sdc(clsd)

. metaeff eff SE, ni(ivsize) nc(clsize) meani(ivmean) meanc(clmean)ci95loi(ivlo) ci95upi(ivup) ci95loc(cllo) ci95upc(clup)

. metaeff eff SEeff, ni(ivsize) nc(clsize) t(tvalue)

AuthorsEvangelos Kontopantelis, National Primary Care Research and Development Centre,

University of Manchester, e.kontopantelis@manchester.ac.uk

David Reeves, Health Sciences Primary Care Research Group, University of Manchester

ReferencesCochrane Collaboration handbook: http://www.cochrane.org/resources/handbook/ Kontopantelis, E. and Reeves D. 2009. A Meta-Analysis add-in for Microsoft Excel. Journal of Statistical Software.

Also seeSTB: STB-44 sbe24

help for metaan, metan7 (if installed)

metannt (if installed), meta (if installed)

metacum (if installed), metareg (if installed)

metabias (if installed), metatrim (if installed)

metainf (if installed), galbr (if installed)

metafunnel (if installed)