R software implementation of combining mixed treatment comparisons and meta regression. Metaanalysis regression, or metaregression, is an extension to standard meta. There are loads of packages in r associated with metaanalysis. Linear regression analysis using stata introduction. The command meta summarize, subgroup can be used to do a subgroup analysis. Although there is not heterogeneity in these data to be explained by a metaregression, an example of the command and its output is given below. Assess the impact of publication bias on results with trimandfill analysis. An example of this is not given, as there is no appropriate variable in the dataset to use for a subgroup analysis. A network metaanalysis toolkit cochrane comparing multiple. Note, results are not backtransformed in printouts of metaanalyses using summary measures with transformations, e. In this paper we provide guidance on how to undertake meta analysis using stata, one of the most commonly used software packages for meta analysis.
Let me know in the comment section below what metaanalysis software you are using. A meta regression can be done in stata 16 with the meta regress command. Meta regression may be performed using the metareg macro available for the stata statistical package. A proposal for a refined method for multivariate meta analysis and meta regression. The power of the analysis is thus greater and the probability of falsepositive findings is reduced. Tackle heterogeneity using subgroup analyses and meta regression. Multivariate randomeffects meta analysis is implemented in stata as mvmeta white, 2009, which has recently been extended to implement multivariate randomeffects meta regression white, 2011. In order to keep graphical depictions of meta analytic results squarely in accord with the underlying inferential statistics, therefore, analysts are well advised to avoid using standard software for graphing meta regression results, or at least to doublecheck that the confidence bands match the meta. Metaregression is often used to explore heterogeneity induced by the relationship between moderators and study effect sizes.
Get a thorough understanding of the statistical concepts of metaanalysis. Linear regression, also known as simple linear regression or bivariate linear regression, is used when we want to predict the value of a dependent variable based on the value of an independent variable. We present the general case for random effects multivariate meta regression and so include meta analysis as a special case where there are no study level covariates and. Adrian mander has written software for a wide variety of statistical procedures in stata. The program is illustrated using a multipletreatments meta analysis. If substantial heterogeneity is found to be present from the analyses detailed above, then reasons for such heterogeneity can be explored by relating study level covariates e. Do these relate to subgroups if yes, i do not see any problem because that seems to be reason why you want to perform the meta regression. I am running a meta regression where my dependent variable is fdi and independent. In this chapter we show in detail how to use the statistical package stata both to perform a metaanalysis and. If you are using the official meta analysis commands in stata 16, the collection of stata journal articles is still valuable because the collection contains information about meta analysis, and not just information on the communitycontributed meta analysis commands. The regression coefficients will estimate how the intervention effect in each subgroup differs from a nominated reference subgroup.
I am conducting a meta analysis in psychotherapy research and want to use meta regression to identify moderators. Metaanalysis of prevalence data using metaprop command. Software for publication bias michael borenstein biostat, inc. Stata module to perform robust variance estimation in metaregression with dependent effect size estimates, statistical software components s457219, boston college department of economics, revised 23 apr 2014. The p value of each regression coefficient will indicate whether this difference is statistically significant. Metaanalysis is a statistical technique for combining the results from several similar studies.
How to conduct meta regression with continuous and categorial variables. Stata module to perform meta analysis regression, statistical software components s446201, boston college department of economics, revised 05 jan 2009. This book is composed of four chapters covering a variety of topics about using stata for regression. In this paper we provide guidance on how to undertake metaanalysis using stata, one of the most commonly used software packages for metaanalysis. Also im not sure if a multilevel multivariate metaregression is possible. These can be installed from within stata, and are released officially listed at here. It was first released in 1998 and has been updated to take account of improvements in stata estimation facilities and recent methodological developments.
The metaanalysis function of jasp is based on the aforementioned metafor r package. We used the procedure glimmix in sas and the commands melogit in stata. The question is why are there multiple observations per study. Convert effect sizes reported in original studies to the ones you need for your meta analysis. You can use any word processor and save the file in ascii format, or you can use stata s dofile editor with the. When you wish to use the file in the future, you would just use the cd command to change to the c. Multilevel multivariate metaregression cross validated. The estimated overall effect sizes, test for heterogeneity, moderator effects, and publication bias were reported using r software. A fixed effects metaregression model that investigates the.
While stata has no intrinsic support for meta analysis, various experts have written macros for meta analysis, which can be downloaded from the stata web site and incorporated into stata. Consistency and inconsistency in network metaanalysis. Tessa is using metareg and stata, but its not an issue related to that, its an issue related to meta regression. Notes on subgroup analyses and metaregression introduction computational model multiple comparisons software analyses of subgroups and regression analyses are observational statistical power for subgroup analyses and metaregression introduction in this chapter we address a number of issues that are relevant to both subgroup. Moderators may include a mixture of continuous and categorical variables. Using these regression techniques, you can easily analyze the variables having an impact on a topic or area of interest. Stata is very powerfull, and i find it easy enough to use. Jasp is a free, opensource program used to perform statistical analysis tests by using r packages. Convert effect sizes reported in original studies to the ones you need for your metaanalysis.
Im quite comfortable with stata, but have never done a meta. Throughout, bold type will refer to stata commands, while le names, variables names, etc. Metaregression may be performed using the metareg macro available for the stata statistical package. We use the software packages sas, stata, and r to demonstrate fitting the mixedeffects logistic regression model for meta analysis of the sclerotherapy data, using the numbers of events and numbers of subjects in each trial. Perform various types of fixed and random effects meta analyses, assess subgroups, make basic indirect comparisons, integrate covariates via meta regression, and do this all while you have access to the largest selection of plots in any meta analysis software which are all excel objects so easily adjustable. Basics of stata this handout is intended as an introduction to stata. Meta stata meta analysis reference manual me stata multilevel mixedeffects reference manual mi stata multipleimputation reference manual mv stata multivariate statistics reference manual pss stata power, precision, and samplesize reference manual p stata programming reference manual rpt stata reporting reference manual. These macros include procedures for basic analysis, for cumulative analysis, for meta regression. The major revisions involve improvements to the estimation methods and the addition of an option to use a permutation test to estimate pvalues, including an adjustment for multiple testing we have also made additions to the output, added an. A refined method for multivariate metaanalysis and meta. Stata is available on the pcs in the computer lab as well as on the unix system.
Check if selective outcome reporting publication bias or \p\hacking is present in your data. Which are the free software to perform metaregression. Metaregression comprehensive metaanalysis software. Meta regression using comprehensive metaanalysis youtube. Metaregression models can be used to analyse associations between treatment effect and study characteristics. It has usually been performed in a bayesian setting, but recently it has become possible in a frequentist setting using multivariate metaanalysis and metaregression, implemented in stata with mvmeta. The program is illustrated using a multipletreatments metaanalysis. In stata, you perform metaregression by using meta regress. This is a revised version of the program originally written by stephen sharp stb42, sbe23.
Stata 16 contains a suite of commands for performing metaanalysis. We should emphasize that this book is about data analysis and that it demonstrates how stata can be used for regression analysis, as opposed to a book that covers the statistical basis of multiple regression. In order to keep graphical depictions of metaanalytic results squarely in accord with the underlying inferential statistics, therefore, analysts are well advised to avoid using standard software for graphing metaregression results, or at least to doublecheck that the confidence bands match the metaanalytic model. This r function is a wrapper function for r function rma. Hi there, i am seeking some help regarding the meta analysis of the prevalence data using the metaprop command. I am conducting single arm meta analysis of a rare event data are in proportion with many predictor variables categorical and continuous. We present a revised version of the metareg command, which performs metaanalysis regression metaregression on studylevel summary data. Then, rank correlation and regression procedures ask whether or not there is evidence of bias, while the failsafe n and its.
The analysis can be done by using mvprobit program in stata. Stata 16 contains a suite of commands for performing meta analysis. The command can perform fixed and random effects network meta analysis assuming either a common or different betweenstudy variances across comparisons. Apr 08, 2019 in estimating a network metaanalysis model using a bayesian framework, the rjags package is a common tool. A metaregression can be done in stata 16 with the meta regress command. Use funnel plots and formal tests to explore publication bias and smallstudy effects. Tackle heterogeneity using subgroup analyses and metaregression. Metaregression analysis metareg command problem statalist. The major revisions involve improvements to the estimation methods and the addition of an option to use a permutation test to estimate pvalues, including an adjustment. The standard meta regression model thompson and sharp, 1999 is the special case of with p 1, so that y i, s i and. This is not an introduction to the use of stata software. Let y denote a covariate, for instance, y0 for low risk of bias studies and y1 for high risk of bias studies.
We present a revised version of the metareg command, which performs meta analysis regression meta regression on studylevel summary data. Metaregression columbia university mailman school of. The first day 3 september 2019 is entirely dedicated to using stata, which is a very convenient and powerful software for carrying out metaanalyses. Metaregression is a tool used in metaanalysis to examine the impact of moderator variables on study effect size using regressionbased techniques. Presents statistical model relating it to multilevel models and presents a conditional notation for the different types of integrative methods fixed effects and random effects metaanalysis, metaregression. Results from meta regression analyses also indicated that race is potentially related to the strength of the association between. It has usually been performed in a bayesian setting, but recently it has become possible in a frequentist setting using multivariate metaanalysis and metaregression, implemented in stata. The goal is to provide a single estimate of the effect. Although there is not heterogeneity in these data to be explained by a meta regression, an example of the command and its output is given below. Difference between metaregression and linear regression in stata. Depicting estimates using the intercept in metaregression. Metaregression is more effective at this task than are standard metaanalytic techniques. A handson practical tutorial on performing metaanalysis.
Metaregression refers to a fixed effects model or random effects model that includes one or more study features as covariates. Network metaanalysis is a popular way to combine results from several studies usually randomized trials comparing several treatments or interventions. The computer programs discussed are comprehensive meta analysis, stata,metawin,andrevman. Metaanalysis is key to the synthesis of quantitative data within. However there are some constraints using this approach compared to a multivariate approach based on correlations. Advanced methods using the stata software lausanne, 36 september 2019 registration deadline. Metaregression to compare subgroups assumes the betweenstudy variance 2 is the same in all subgroups sensible when some or all subgroups have few studies estimates the difference in treatment effect between subgroups example. The metasem package only describes a multilevel multivariate metaanalysis or a multilevel univariate metaregression. Which are the free software to perform meta regression. Evaluate study heterogeneity with subgroup analysis or metaregression. I have done a meta analysis and heterogeneity is too high. It is a userfriendly way of conducting stats without having to deal with the r code itself. We address the three topics covered in the previous issues of the journal, focusing on their implementation in stata using a working example from mental health research. The mvmeta command in stata employs a recent approach to network meta analysis that handles the different treatment comparisons appeared in studies as different outcomes.
Meta regression reduces the number of tests and estimations as compared with subgroup analysis and uses all included studies. Alternatively, if it is all binary data you might be able to tackle the problem with the usual multilevel mixed effects regression commands. If you are using the official metaanalysis commands in stata 16, the collection of stata journal articles is still valuable because the collection contains information about metaanalysis, and not just information on the communitycontributed metaanalysis commands. I am working with eventotal for experimental and control groups to calculate the odds ratio.
29 143 717 1142 1154 6 1241 523 1480 83 384 1477 185 1593 489 436 823 1029 1591 1157 630 1193 442 956 630 1331 701 1501 1283 300 176 1324 102 475 355 1124 140