pilot - individual participant data metaanalysis (just for CSI and GABA this time)

Mai multe ca aceasta

THINK Climate

după Sally N

Mind Map SDLC

după Diana Castañeda

Mean, Median, Mode, and Range

după Mandi Turner

psoriasis

după pereira camille

vendor

control for

group

gender

age

pilot - individual participant data metaanalysis (just for CSI and GABA this time)

data

BDNF

Caumo et al.

Pollli et al. (2020)

GABA

Terumitsu et al. (2022)

Aguila et al. (2016)

Peek et al. (2021)

planned procedure

harmonization/residualization

is excluding the effects of factors that may be relevant and may effect the results, but are not the scope of analysis (e.g., vendor, age, gender...)

can be done via

residualization using linear models

ComBAT harmonization

according to

what do we have to do in IPD?

how will we do it?

using multilevel correlations as implemented in the psych package

pool correlations from all studies using harmonized (residualized) data

pool within-study correlations (part of correlation that does not belong to the actual CSI-GABA relation)

pool between - study correlations (effect that we need)

merge the data from all studies (with a study identificator)

harmonize first where harmonization is needed

Chen, D. G., & Peace, K. E. (2021). Applied Meta-analysis with R and Stata. Boca Raton, FL: CRC Press.

meta-analysis with IPD

IPD with mixed-effect models (a type of multilevel modeling)

pooling all studies together

technical

ICC (for any model)

model comparison (rsri/ri)

random-intercept only model

fitting random-slope random-intercept model

goal: estimate both between- and within- study effects

IPD with covariates (analogous to harmonization/residualization)

interactions of covariates and study (cov1*study, cov2*study, cov1*effect, cov2*effect, effect*study; summarily, all main effects and two-way interactions, no three-way interactions)

IPD analysis with pooled data

Subtopic

textbook: tested the treatment-study interaction

IPD analysis for each study

descriptives (by study)

removing missing data (overall)

data summary (overall)