Explore chapters and articles related to this topic
Multivariate Meta-Analysis
Published in Ding-Geng (Din) Chen, Karl E. Peace, Applied Meta-Analysis with R and Stata, 2021
Ding-Geng (Din) Chen, Karl E. Peace
The fixed-effects meta-analysis is implemented using method="fixed" as follows: > # Call mvmeta with fixed-effects> berkey.mvmeta.fixed = mvmeta(cbind(PD,AL),S=berkey98[,c("var_PD","cov_PD_AL","var_AL")],method="fixed",data=berkey98)> # Print the summary> summary(berkey.mvmeta.fixed)Call: mvmeta(formula = cbind(PD, AL) ~ 1, S = berkey98[, c("var_PD", "cov_PD_AL", "var_AL")], data = berkey98, method = "fixed") Multivariate fixed-effects meta-analysis Dimension: 2 Fixed-effects coefficients Estimate Std. Error z Pr(>|z|) 95%ci.lb 95%ci.ub PD 0.3072 0.0286 10.7513 0.0000 0.2512 0.3632*** AL -0.3944 0.0186 -21.1471 0.0000 -0.4309 -0.3578*** Multivariate Cochran Q-test for heterogeneity: Q = 128.2267 (df = 8), p-value = 0.0000 I-square statistic = 93.8% 5 studies,10 observations,2 fixed and 0 random-effects parameters logLik AIC BIC -45.4416 94.8833 95.4884
Individual Participant Data Meta-Analysis
Published in Christopher H. Schmid, Theo Stijnen, Ian R. White, Handbook of Meta-Analysis, 2020
Once treatment effect estimates are found for each study, they may be combined in a meta-analysis using any of the methods described earlier in this book. In the original analysis of the PARIS data, a common-effect meta-analysis was used to pool relative risks. The Mantel–Haenszel or Peto methods might also be used. In later re-analyses, DerSimonian–Laird random-effects meta-analyses of the log odds ratios and their variances were performed, as described in Chapter 4 (DerSimonian and Laird, 1986; Mantel and Haenszel, 1959). Heterogeneity was assessed using both Cochran’s Q test and I2 (Higgins and Thompson, 2002). Figure 8.1 shows the forest plot for this analysis.
A comprehensive update to Dendritic Cell therapy for glioma: a systematic review and meta-analysis
Published in Expert Review of Vaccines, 2022
Parisa Shamshiripour, Mehdi Nikoobakht, Zahra Mansourinejad, Davoud Ahmadvand, Mahzad Akbarpour
Meta-analysis was conducted by medcalculator software. The heterogeneity within studies was assessed by I2 statistics; however, we believe that the heterogeneity analysis using the I2 statistic defined as the fraction of variance that is due to heterogeneity can be biased when the number of included studies in the meta-analysis is small [21]. Heterogeneity was classified as negligible (I2 = 0–25%), low (I2 = 25–50%), moderate (I2 = 50–75%), or high (I2> 75%). Cochran’s Q test was also used to assess the heterogeneity [22]. In the presence of high heterogeneity, Random Effect Model was applied by the Dersimonian and Laird method, and when the heterogeneity analysis showed homogenous distribution, fixed effect model was used for proportion meta-analysis [23]. Egger’s and Begg’s tests were used to examine the presence of publication bias [24,25].
Effect of dance therapies on motor-cognitive dual-task performance in middle-aged and older adults: a systematic review and meta-analysis
Published in Disability and Rehabilitation, 2021
Alvaro Murillo-Garcia, Santos Villafaina, Daniel Collado-Mateo, Juan Luis Leon-Llamas, Narcis Gusi
A total of five articles and 205 participants [29,44,46,50,51] were included in the meta-analysis (see Figure 2) focused on the effects of dance-based intervention on cognitive TUG. The experimental groups performed Tango classes [44,46,51], Flamenco and Sevillanas [50] and Exergames based on Dance [29] while the control groups conducted an education seminar [44], fall prevention exercises [51], self-directed exercises [46], followed a booklet with physical activity recommendations [50] and continued with their daily routine [29]. The overall effect size for the cognitive TUG performance was −0.48 with a 95% CI from −0.88 to −0.08 which is small following the defined classification (0–0.5) [39,40]. The p-value was 0.01 which means a significant improvement in TUG cognitive. The p-value of the Cochran Q-test was 0.1. In addition, this was supported by the other computed coefficients: I2 = 46% which is medium following the defined classification [39,40] and H = 0.68.
Functional and Morphological Results of Epiretinal Membrane Surgery in Idiopathic versus Diabetic Epiretinal Membranes
Published in Seminars in Ophthalmology, 2021
Mine Ozturk, Dilek Guven, Hakan Kacar, Murat Karapapak, Mehmet Demir
Statistical analysis was performed using SPSS software (version 15,0 SPSS (IBM), Chicago, IL, USA). Continuous variables are reported as the mean ± standard deviation (SD) and range (minimum to maximum). For comparison of continuous variables in two independent groups, the Student’s T-Test was conducted with a normal distribution and the Mann–Whitney U-test was used with a non-normal distribution. In the dependent group, differences of continuous variables were analyzed with the Friedman test to see if the distribution was non-normal. Subgroup analyses were done with Wilcoxon test and Bonferroni correction. The proportions of the groups were analyzed with the chi-square test, and Monte Carlo Simulation was used when needed. Proportions of related groups were analyzed with Cochran’s Q test. Subgroup analyses were done with Friedman test and Bonferroni correction. A p < .05 was considered statistically significant.