Meta-analysis refers to methods focused on contrasting and combining results from different studies, in the hope of identifying patterns among study results, sources of disagreement among those results, or other interesting relationships that may come to light in the context of multiple studies.

learn more… | top users | synonyms

1
vote
0answers
12 views

Analysis of “The advantage of short paper titles”

After seeing the paper, The advantage of short paper titles showing a relationship between paper length rank and citation rank, I wondering what to make of the results. As a layman, my questions are: ...
0
votes
0answers
46 views

R and Metafor: meta-analysis with multiple cases from a single study

I am currently performing a meta-analysis on bank relationship and firm performance with 27 different studies; almost all of them report different cases. I calculated the partial effect size (I have ...
0
votes
1answer
35 views

Computing standard error of mean derived from multiple samples

I've had trouble finding a clear answer elsewhere on the internet and thought I'd put it to the XV community. Problem Description Suppose I have $N$ samples, each on a different subject. Each sample ...
0
votes
0answers
20 views

Epidemiology - Pooling relative risks or hazard ratios for different outcomes from the same trial

I have one cohort trial with separate relative risks (RRs) for disease A and disease B. I would like to merge these RRs to get a single RR for diseases A+B combined. How can I do this? I have the ...
1
vote
1answer
24 views

The confidence interval of Tau-square and I-square produced by meta package and metaphor package

I am comparing R packages including metafor and meta for meta-analysis. Both packages are excellent and most of the results are the same. However, I found that the confidence interval of tau^2 and I^2 ...
1
vote
1answer
22 views

Output too similar from FE and REML model meta-analysis on metafor for R

I'm trying to use the metafor package in R to run fixed and random effects model meta-analyses on data with a single continuous ...
2
votes
1answer
34 views

Calculating group size from hazard ratio

I am undertaking a systematic review and as part of the data extraction process I would like to know how many patients were analysed in the treatment and control arm (in a particular subgroup). In one ...
3
votes
1answer
88 views

Multilevel multivariate meta-regression

Background: I'd like to conduct a meta-regression using studies which have (1) several outcomes/constructs (= multivariate) and (2) multiple effect sizes for every of these outcomes because of ...
0
votes
0answers
19 views

combining different but linked studies in meta-analysis

I am trying to join two datasets and was wondering if there is a formal method to do a meta-analysis or even if this can be categorized as a meta-analysis in the first place. Dataset 'a' has detailed ...
4
votes
1answer
50 views

How do I convert $\eta^2$ to Pearson's r?

I am doing a meta-analysis of associations between sets of variables that are essentially all continuous. However, many studies operationalised them at 'lower' levels, and I have (converted to) most ...
4
votes
0answers
65 views

What are the reasonable properties of p-value combination methods when all p-values are the same?

Suppose we test a null hypothesis $H_0$ by combining evidence from $n$ independent tests through some $p$-value combination method $M$. The combined $p$-value is $M(p_1,...,p_n)$. Assume the extreme ...
1
vote
0answers
26 views

Meta-analysis using p-values

I have a study-level (quasi-experimental) estimator of treatment effect $\hat{\delta}_i$, where $i$ indexes the study. Due to the way the estimator is constructed, I do not have access to a measure of ...
0
votes
0answers
33 views

Meta Analysis for one proportion

I have data summarizing proportion of events from 5 different papers. The proportions are in %'s. For example, in paper number 1, there was a report of 2000 people and a proportion of 10%. I want a ...
2
votes
1answer
32 views

Q-Test of Heterogeneity for only two effect sizes?

I am using the Q-Test of Heterogeneity to investigate if several effect sizes derived from two different studies are significantly different from each other. More precisely, I have, for every effect ...
1
vote
0answers
20 views

Calculating a pooled estimate

I am writing a systematic review on certain imaging studies and I was hoping to add a meta-analysis of the sensitivities of the various modalities reported on. My goal was to put together a forest ...
4
votes
1answer
57 views

Why does Stouffer's method work?

It seems like a fairly straightforward question, but when I really think about it, Stouffer's method doesn't make sense to me. This is why: Assume a two-tailed hypothesis. You first calculate $z_i$ ...
2
votes
0answers
52 views

Estimating the difference between adjusted and unadjusted meta-analytic effect sizes

I am working on a meta-analysis of standardized mean differences for which researchers report a variety of unadjusted data and data that are adjusted for one or two covariates. In this research ...
0
votes
0answers
24 views

Combining effect sizes in binary data

I'm working on combining effect sizes for a meta-analysis when one study reports multiple effects for the same construct. To accomplish this, I'm using the equation provided in the Borenstein ...
1
vote
0answers
31 views

Logit or arcsine transformation for proportion in meta-analysis

I am performing a meta-analysis with 137 study arms. From each arm I have extracted a proportion of a disease. Here are my proportions: ...
0
votes
0answers
26 views

What is the limitation with using a pooled standard deviation in a dependant sample?

I am not very experienced in statistics, but want to perform a meta-analysis on a number of pre-post studies. The studies have relatively small sample size ranging from around 10-38 subjects. They are ...
1
vote
1answer
22 views

Meta Analysis for Binary Outcome, Two Groups, Pre and Post

This seems like a straight-forward problem, but I can't seem to wrap my head around it. I have a binary outcome (Presence/Absence of a condition for a patient), and an intervention (educational ...
0
votes
0answers
16 views

Forest Plot shows negative estimate(slope) but mean trends are increasing.

I'm conducting a meta-analysis which shows obvious increasing trends amongst means. However when I plot my forest plot, all values are below 0. As far as I'm aware, when values are below 0, it shows a ...
0
votes
0answers
26 views

User-defined weights in meta-analysis accounting for the length of the study

I am conducting a meta-analysis in the field of ecology in which the effect size is the log ratio of the means (control and treatment). When fitting the model with ...
0
votes
0answers
26 views

Estimate ROC curve using binormal distribuiton

I am conducting a meta-analysis on diagnostic studies but for each study I have only mean and standard deviation reported. How can I estimate the ROC curve using the binormal assumption in R ? Tks,
3
votes
0answers
38 views

Methods for meta-analysis: z-transform (Stouffer's approach) vs. Fisher's method vs… infinite others? [duplicate]

Fisher's method and Stouffer's approach (z-transform) for meta-analysis roughly follow the same scheme: take the p-values from some different experiments on the same hypotheses apply to them some ...
0
votes
1answer
56 views

Heterogeneity statistics with fixed effects model in RevMan

Since a fixed-effects meta-analysis assumes that the studies are all estimating the same underlying effect, when the Cochrane RevMan software reports a Q and $I^2$ statistic with a fixed-effects ...
1
vote
0answers
57 views

Calculate combined variance from multiple dependent time-points for meta-analysis with {metafor} [closed]

I have a dataset, which is a subset containing only the studies that contain multiple measurements over time within a study, and hence not independent. Example: ...
0
votes
0answers
30 views

Comparing raw non-normal data with a mean and SD of non-normal data

I have raw data, which are non-normally distributed (negative binomial, or if converted to densities, compound Gamma-Poisson), as well as a mean and standard deviation (SD) of another data set ...
0
votes
0answers
8 views

How can we construct cumulative meta analysis plot after doing proportion meta analysis

Need to do cumulative plot for proportion meta analysis. Suggest software
0
votes
0answers
26 views

Meta regression in proportion meta analysis

I completed proportion meta analysis using stuart-ord method. Now need to do meta regression. I used stats direct for proportion meta analysis. Previously I did meta regression using comprehensive ...
0
votes
1answer
66 views

Properly calculate mean and SE for meta-analysis

I want to perform a meta-analysis, for which I have data from 30 different experiments, each of them with two different treatments. I have three different types experiments based on how the data are ...
0
votes
1answer
29 views

Interpreting stripe like shapes on funnel plot from meta-analysis

I have a set of 130 measurements from about 30 different studies. I have made a random effects meta-analysis of SMD and ROM. I used the DL method. I also made funnel plots to check for publication ...
2
votes
1answer
43 views

Fitting nonlinear meta regression models to data

I have a collection of data, obtained from different studies. To plot the ratio of means against different CO2 concentrations, I used a random effects model with a continues predictor (the CO2 ...
0
votes
0answers
41 views

Bayesian random effects meta-analysis on the risk ratio with r2jags

Following the work of Warn 2002 I am trying to set up the model for a Bayesian meta-analysis on the risk ratio and the odds ratio. I am using R together with R2jags to fit a simple RE MA model. ...
0
votes
0answers
44 views

Failed to reduce deviance while using “lme4 : glmer ”

this is my first post, so I will try to make it as clear as possible. Hopefully is not something trivial and I am just stuck. I am performing meta-analysis using the glmer function of the lme4 ...
0
votes
0answers
24 views

How to compare latent mean difference from Measurement Invariance with cohen's d from a meta-analysis?

I was wondering if it is possible to compare latent mean differences estimated in a scalar invariance model to an overall Cohen's d found in a meta-analysis. Is there a way to convert one value to the ...
0
votes
0answers
26 views

How should I combine this binary scale with this 4-point scale?

I'm doing a meta-analysis and I want to combine the results of two questionnaires. One questionnaire has 30 questions about whether you've experienced certain traumatic life events. They're all ...
2
votes
1answer
26 views

Fitting curves to means and variances from multiple samples

I have data on a variable measured in multiple longitudinal samples. I do not have the individual-level data for each sample, just the sample means and variances at each time point. The samples do not ...
0
votes
0answers
12 views

If doing a meta-analysis with R, using log hazard ratios, do I supply the variance/SE or the log variance/SE? [duplicate]

As above, really! I have a load of trials for which I have the HR, the standard error of the HR, and n. I can either supply the variance with vi=(SE*sqrt(n))^2 or ...
2
votes
1answer
75 views

Meta-analysis of trials given hazard ratios

I'm trying to do a meta-analysis in R (using metafor) of trials where the outcomes are hazard ratios and I'm given the 95% CI for them and/or the standard error and n. So if I have columns like: ...
2
votes
1answer
46 views

Can I get an Odds Ratio (or other effect size) from two proportions and a p-value?

I am conducting a meta analysis that is comparing dichotomous outcomes for two groups. So for each study, I have the proportion of the outcome for both groups and the sample size of each group, and I ...
4
votes
1answer
71 views

Metafor rma.mv function: missing estimates for two levels of a categorical moderator

I am conducting a meta-analysis with several categorical moderators and one continuous moderator; I am also interested in an interaction between two of the moderators (outcome and scale). I have ...
3
votes
1answer
76 views

How to convert the standard error of the log odds ratio to the odds ratio standard error

I am using the log odds ratio (and its standard error) for meta-analysis. I want to convert back to odds ratio to write up the results... maybe i'm putting in the wrong search terms but can't find ...
0
votes
0answers
16 views

User weight specification in Meta-analysis using STATA

I want to perform Meta-analysis in STATA using User define weight option "wgt()", i.e., metan coef, fixed wgt(weight-variable). However, the model is not running, stata says, " too few variables ...
0
votes
0answers
11 views

How to manually do Bayesian fixed effects meta-analysis?

Assume $Y_i \sim Normal(\mu, \sigma_i)$ for $i = 1, 2, 3, \ldots, k$ independent studies. Here I assume $\sigma_i$ is known. The prior distribution is $\mu \sim Normal(\mu_0, \sigma_0)$. What will be ...
2
votes
1answer
77 views

Method of meta-analysis of studies to determine mean blood level

Generally meta-analysis is done to determine the efficacy of some treatment as compared to controls. Is it possible to do a meta-analysis of different studies for mean blood level of a chemical, its ...
0
votes
0answers
26 views

Explanation of heterogeneity

Following is the output of meta-analysis of five fictitious studies: ...
2
votes
1answer
68 views

How to choose between fixed effects and random effect meta-analysis

In meta-analysis packages, both fixed effects and random effects models are available. How do one choose between these 2 models? Since one is assessing different studies, should one not choose random ...
0
votes
0answers
26 views

How to compare the continuous outcome of two group of studies in a meta synthesis?

While doing a meta synthesis, I would like to state if there is a difference in the compost quality (e.g. the carbon content) between studies carried out in tropical and temperate region. Within each ...
3
votes
1answer
63 views

How to combine data several studies with events?

I have a compilation of following data on 10 studies, all of which had 2 groups: a control group which received usual treatment and an active group which received an intervention. The subjects were ...