Skip to main content

Questions tagged [meta-regression]

A meta-analytic tool that examines the impact of moderator variables on studies' effect size. It is another name for mixed effects model in meta-analysis (moderators are fixed effects, studies are random effects).

Filter by
Sorted by
Tagged with
0 votes
0 answers
24 views

Conditional Logit Model - Utility Structural Estimation - Meta Analysis

I am performing a structural estimation of an utility function across several databases (from distinct articles) using McFadden (2001) framework (see reference). Each article's database includes N ...
RobM's user avatar
  • 1
0 votes
0 answers
22 views

I2 (I-squared) estimates for heterogeneity of independent meta-analysis versus a single meta-regression

I am wondering how the I2 estimates of independent meta-analyses per level of a categorical moderator compare to those of a single meta-regression. The question is similar to the one about how the ...
befriendabacter's user avatar
2 votes
1 answer
102 views

Heterogeneity and ICC when using metafor's rma.mv and robust variance estimation

I am conducting a meta-analysis of standardised mean differences with many sources of dependency (multiple outcomes measuring the same construct, multiple control groups, outcomes from dyads (e.g., ...
AndreasV's user avatar
0 votes
0 answers
84 views

Combining multiple outcomes/measurements in meta-analysis

I am conducting a meta-analysis with 12 studies. 4 studies use multiple ways to measure the same outcome or measure the same outcome at different time points. In any case, the outcomes/measurements in ...
FZZ's user avatar
  • 1
1 vote
0 answers
21 views

Meta regression as mixed model: time interaction

In our meta-analysis, we have several potential moderators, both categorical (e.g. disease type, outcome type), and continuous e.g. publication year. Suppose we wish to investgate the effect of ...
user167591's user avatar
0 votes
1 answer
44 views

multivariate meta-analysis - can subgroup indicator reflect several different variables and outcome types?

I have seen that in meta - analysis, a multivariate model can be used to get the same estimates as a series of separate meta analyses e.g. https://www.metafor-project.org/doku.php/tips:...
user167591's user avatar
0 votes
1 answer
26 views

Interpreting a meta-regression table with odds ratios

I need a little help with my meta-regression interpretation. The effect sizes are based on odds ratios. I have used rma in the metafor package: reg <- rma(yi = es, sei = se, data = df, method = &...
Richard Summers's user avatar
3 votes
2 answers
84 views

Meta-analysis based on cohort studies only

I am planning a meta-analysis based on cohort studies only. There are dozens of papers reporting results of treatments A and B. But the treatments were never compared with each other. Besides, there ...
Viktor's user avatar
  • 1,035
2 votes
0 answers
75 views

Comparing Multi-level Meta-regression to Network Meta-Analysis for Dose-response Project

I am planning a meta-analysis to examine the average change in a continuous variable over time within my area of research. To be able to meta-analyze this continuous relationship, I've typically ...
zr2015's user avatar
  • 41
1 vote
0 answers
41 views

Which prediction interval to use - meta-regression selected using LOOCV

I have a research paper that conducted a meta-regression using multiple predictor variables in metafor. They did a meta-regression for all combinations of variables and then used LOOCV to select the ...
Aaron Simmons's user avatar
2 votes
0 answers
41 views

Estimating mean and prediction intervals for new predictions using meta-regression output

Let's start with linear regression. You develop a simple linear regression equation $y = ax + b$. You can predict $\hat{y}_h$ for $x_h$ and estimate the prediction intervals using $$\hat{y}_h \pm t_{\...
Aaron Simmons's user avatar
0 votes
1 answer
81 views

Including covariates in a multivariate multi-level meta-analysis

I am carrying out a multivariate multi-level meta-analysis, and I have a question regarding including moderator variables in the context of publication bias. Doucouliagos and Stanley (2009) recommend ...
Daniel's user avatar
  • 1
3 votes
1 answer
53 views

Combining meta-analysis and machine learning (accounting for heterogeneity)

What are the standard methods for training machine learning algorithms on data, issued from multiple studies? In conventional meta-analysis one usually uses weighted average to combine estimates ...
Roger V.'s user avatar
  • 4,439
2 votes
1 answer
38 views

How to conduct meta analysis for studies that have used repeated cross section surveys to report prevalence

When conducting meta-analysis on prevalence of disease, few studies have reported prevalences using different rounds of cross-sectional surveys. When analyzing such studies shall I take each reported ...
siri's user avatar
  • 51
2 votes
1 answer
71 views

How to interpret a meta-regression output?

I've conducted meta-regression analyses using the 'metafor' package in R. I am trying to interpret the outputs if you could please help? Output 1 (categorical with 3 levels): Test of moderator is ...
Helen's user avatar
  • 21
1 vote
1 answer
90 views

Meta analysis: can multiple test corrections (i.e. Bonferroni) be applied on the pooled effect p-value?

I plan to do a meta-analysis including the effect size of each cohort as the objectives. I'd like to ask if I could apply multiple test corrections (i.e. Bonferroni) on the pooled effect p-value. I ...
Joe's user avatar
  • 21
1 vote
0 answers
14 views

Including study as a moderator in a meta-analytical model

I'm trying to figure out what it means to include 'study' as a moderator in a meta-analytical model. In the R package metafor, for example, we might build an intercept-only random effects model as ...
befriendabacter's user avatar
1 vote
1 answer
31 views

Meta-Regression with BDI mean difference as a predictor?

I am conducting a Meta-Analysis using metafor in R. I calculate the standardized mean difference between patient groups (PG) and ...
benjarmin1's user avatar
2 votes
0 answers
17 views

What is Bsum in (meta-)regression and how do you test for its significance?

I received a reviewer report on a meta-analysis that I submitted which stated that a multivariate regression that I performed should instead be "a backward stepwise multivariate logistic ...
vladbadu's user avatar
1 vote
0 answers
30 views

How can I calculate the power (number of studies) needed for a meta-regression?

I would like to know how small of a beta coefficient my meta-regression is powered to detect. Thank you for any help.
M BG's user avatar
  • 61
2 votes
0 answers
49 views

Approaches to (non-linear) meta-regression to estimate the conditional population distribution of $y$ based on aggregate data

I want to estimate the distribution of a variable in certain subgroups of the population based on pooling of aggregate data reported in various observational studies. For simplicity, assume there is a ...
user9794's user avatar
  • 216
2 votes
1 answer
69 views

Can you meta-analyze multiple outcomes of a single experiment?

Suppose there is an experimental design where the test participant is randomly assigned to 1 of 3 conditions (1 control, 1 treatment, 1 placebo). Each participant then completes 6 different measures ...
ssjjaca's user avatar
  • 221
1 vote
0 answers
296 views

Making sure I interpreted my rma.mv output correctly (metafor)

I'm looking at investigating whether a tag in a fish is retained within the body (or not) and the factors that are likely driving this effect as part of a metanalysis. This includes the size of the ...
mlaw's user avatar
  • 11
1 vote
0 answers
49 views

Multiple Meta-Regression of Proportions

I am conducting a multiple meta-regression of proportions and was hoping that I could get some help. Outcome variable is complications rates (logit transformed) and moderators are publication year and ...
seven.sabs's user avatar
2 votes
1 answer
165 views

Should a meta-analysis of group differences calculate Hedges’ G separately for each group, or calculate Hedges' G for the group difference?

I am reading a meta-analysis where the authors state the following. (I've redacted the active drug name, as my purpose is to understand not call anyone out.) The treatment response to placebo and [...
llewmills's user avatar
  • 2,043
0 votes
0 answers
21 views

Appropiate name for coefficients of meta-regression

I would like to report the slope coefficient of several meta-regressions with one predictor. I am wondering what the correct term for this coefficient is. Is it simply b1 or is it β?
g4cco's user avatar
  • 21
1 vote
0 answers
18 views

Why do the confindence intervals overlap when my p-value is significant in meta-regression? [duplicate]

I fitted a mixed effects meta-regression model with one dummy-coded predictor (USA vs. Europe). The output tells me that the predictor is significant. I then wanted to get the average estimated effect ...
g4cco's user avatar
  • 21
0 votes
1 answer
32 views

What's the difference between fisher's Z and reliability&sample size adjusted r?

I am performing a meta analysis on random-effects model and I came across studies that compute r+ (sample size-adjusted correlation) and rc (reliability-adjusted correlation), and also those that ...
helpjpls's user avatar
2 votes
1 answer
78 views

Is it possible to do meta-regression with GAMLSS?

I am about to conduct a meta-regression analysis to fit some age-related changes. Since the GAMLSS approach is highly suggested in the normal regression of such data, I want to apply GAMLSS to my ...
Jack Yang's user avatar
2 votes
0 answers
55 views

Errors-in-variables random effects meta-regression

I would like to perform an error-in-variables random effects (DerSimonian and Laird method) meta-regression, but I do not know how one goes about doing this. Does anyone have any advice on if this is ...
M BG's user avatar
  • 61
2 votes
0 answers
41 views

Weighting pharmacovigilance data in a meta-regression

I would like to run a meta-regression in which the independent variable is composed of weighted reported odds ratios (ie, the number of events for a particular medication side effect divided by total ...
M BG's user avatar
  • 61
1 vote
0 answers
14 views

When should I care about the hierarchical structure of a few included studies for a meta-analysis (multiple independent groups, same outcome)?

I plan to meta-analyze proportion data (i.e. compliance rates in %) from >150 studies. Most of the studies will be single-group designs, but there will also be a few eligible multiple group studies ...
pieuvre's user avatar
  • 11
1 vote
1 answer
42 views

Meta-regression with Peto's odds ratio? / best approach for rare events in control arm

I am conducting a meta-analysis with a binary outcome in which there are only 2 events in the control arm (most studies have 0) and an event rate of ~7% in the treatment arm. I have 2 questions: Can ...
Lindsay's user avatar
  • 11
3 votes
0 answers
66 views

Why are $R^2$ values not available in mixed effects meta regressions

I'm currently conducting a meta-regression for my predictors from a meta-analysis of proportion. In calculating the mixed effects meta-regressions, I wanted to identify how much heterogeneity is ...
Yakubu's user avatar
  • 31
1 vote
0 answers
247 views

interpretation of moderation in meta analysis

I'm conducting a meta-analysis using package metafor in r and I want to test the possible moderation effect of 3 variables. Of the 3 variables, only one gives me a significant effect on the '...
Enrico 's user avatar
2 votes
0 answers
36 views

Arm-based meta-analysis of variation and mean with interval scale data

I’ve been extracting data for an arm-based meta-analysis on the distribution of a self-report survey in various research contexts. I am interested in the approach taken in Nagakawa et al. (2015), ...
thisisaname's user avatar
1 vote
0 answers
46 views

How to find the optimal coefficients of the two predict_proba output matrices of two different classifiers using regression and maximizing accuracy? [closed]

I am performing classification, where there are six labels and two predict_proba (predicted probabilities) matrices as outputs. These two predict_proba matrices correspond to the outputs of two ...
cemrifki's user avatar
1 vote
0 answers
37 views

Meta-regression for continuous data - effect size or otherwise?

I'm trying to parse the output of multiple studies to quantify how age impacts the prevalence of HPV in Europe. Thanks to an excellent suggestion in a previous question, it has been suggested that ...
DRG's user avatar
  • 323
1 vote
0 answers
133 views

How to compare ANOVA results from multiple data sets

I am trying to find out if there is an age-education category difference between people in the number of votes which they use while voting with a multiple vote voting method. Basically, I am trying to ...
Stefan A. Schulte's user avatar
3 votes
0 answers
130 views

Why are GLMMs distinct from GLMs for Meta-analysis of study level data?

Would anyone be able to explain conceptually why GLMMs with a random intercept at the study level are occasionally used for meta-analysis of proportions / counts, when the observations are already at ...
Richard Walker's user avatar
1 vote
0 answers
34 views

Meta regresssion with Standardized Mean Difference

I am doing a meta-analysis of studies comparing A and B. As some studies used different scales (measurement techniques), we have decided to pool all studies and used standardized mean difference (SMD)....
Kristanto Paulus's user avatar
1 vote
0 answers
73 views

Should I expect lower R2 with meta-regression in meta-analyses with low heterogeneity?

The question in short: Should I expect lower R2 values in meta-regression performed in a meta-analysis with low levels of heterogeneity? In meta-analysis, I2 represents a ratio of between-study ...
Clueless's user avatar
1 vote
0 answers
27 views

How can I validate my curve fitting meta-regression?

I'm doing a meta-regression analysis on Normal Pressure Hydrocephalus Gait Analysis. Studying the variation of gait velocity after a procedure (Tap-test). Keeping into account single study (#14) ...
Massimiliano 's user avatar
3 votes
0 answers
92 views

Considering sample size as controlling factor in meta-regression

In a meta-regression, authors have 3 explanatory variables of interest for 2 countries. But all these three variables were not present in all those studies which were finally selected for meta-...
time's user avatar
  • 1,607
2 votes
0 answers
80 views

Predicted treatment effect for causally related conditions

Let's say there are two medical conditions $A$ and $B$ that are causally-related, i.e. that they share a common etiological process $C$. For example, $A$ and $B$ could be related autoimmune conditions ...
Brandon Brown's user avatar
2 votes
1 answer
481 views

How to back-transform regression coefficients in a multi-level meta-regression in metafor

My question is an extension of this one, where I asked about back-transforming the results of a reliability generalization meta-analysis. I have run a three-level meta-regression, using the Bonett-...
PyjamaNinja's user avatar
1 vote
0 answers
30 views

A reasonable choice of effect size for a meta-analysis

I'm doing a meta-analysis where the studies ask the study participants to read, find, and correct the wrong words in a text. Some studies score each study participant's performance on the text using: ...
Luke Martinez's user avatar
3 votes
1 answer
179 views

comparing effect sizes (partial correlations) for multiple outcomes in a meta-analysis

I'm conducting a meta-analysis using the metafor package. I'm using partial correlations and I'm interested in two effects - correlations between X and Y1 and X and Y2 (both controlling for Z). I have ...
llbia's user avatar
  • 361
1 vote
0 answers
119 views

Specifying a complex random-effects structure in metafor

I am working on a project in which I am using metafor to carry out a single-paper meta-analysis. My project contains data from 5 different studies; each study ...
Andrew V's user avatar
1 vote
0 answers
146 views

Combining moderator variables in meta-regression

I have a meta-analysis type dataset of compiled information from primary studies; including hazard ratio's and confidence intervals together with predictors (i.e. "moderators" in the context ...
user167591's user avatar

1
2 3 4 5