2017
DOI: 10.1371/journal.pone.0175111
|View full text |Cite
|
Sign up to set email alerts
|

A flexible method for aggregation of prior statistical findings

Abstract: Rapid growth in scientific output requires methods for quantitative synthesis of prior research, yet current meta-analysis methods limit aggregation to studies with similar designs. Here we describe and validate Generalized Model Aggregation (GMA), which allows researchers to combine prior estimated models of a phenomenon into a quantitative meta-model, while imposing few restrictions on the structure of prior models or on the meta-model. In an empirical validation, building on 27 published equations from 16 s… Show more

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...
2
1
1
1

Citation Types

0
5
0

Year Published

2018
2018
2022
2022

Publication Types

Select...
4

Relationship

0
4

Authors

Journals

citations
Cited by 4 publications
(5 citation statements)
references
References 45 publications
0
5
0
Order By: Relevance
“…While in small sample, empirical likelihood estimators may perform better, implementation can be substantially more complex. Recently, a simulation based method has been also described for combining information on model parameters across disparate studies (Rahmandad et al , 2017). Computationally, the proposed method may also enjoy substantial advantages in dealing with complex models, such as those in high-dimensional settings, where repeated model fitting on simulated data is extensive.…”
Section: Discussionmentioning
confidence: 99%
“…While in small sample, empirical likelihood estimators may perform better, implementation can be substantially more complex. Recently, a simulation based method has been also described for combining information on model parameters across disparate studies (Rahmandad et al , 2017). Computationally, the proposed method may also enjoy substantial advantages in dealing with complex models, such as those in high-dimensional settings, where repeated model fitting on simulated data is extensive.…”
Section: Discussionmentioning
confidence: 99%
“…Faster and more capable computing spurred the development of methods to estimate parameters in nonlinear systems, avoid getting stuck on local optima in parameter space, deal with autocorrelation and heteroscedasticity, and especially model misspecification and causal identification (see below). These methods include indirect inference (Gourieroux et al, ; Hosseinichimeh et al, ), the simulated method of moments (McFadden, ; Jalali et al, ), Generalized Model Aggregation (Rahmandad et al, ) and extended Kalman and particle filters (Fernández‐Villaverde and Rubio‐Ramírez, ). Bootstrapping and subsampling (see, e.g., Politis and Romano, ; Dogan, ; Struben et al, ) and Markov chain Monte Carlo and related Bayesian methods (Ter Braak, ; Vrugt et al, ; Osgood and Liu, ) became feasible for models of realistic size and complexity, enabling modelers to estimate parameters and the confidence intervals around them without making unrealistic assumptions about the properties of the models and error terms.…”
Section: Parameter Estimation and Model Analysismentioning
confidence: 99%
“…11 However, current meta-analysis techniques can only combine data from studies using similar variables and measures. 11 They cannot be used when studies use different statistical models, different subsets of potential explanatory variables, or different transformations on included variables. 11 Conventional meta-analysis can combine multiple measurements of the same thing (e.g.…”
Section: Risk Factors For Cervical Cancer In Women In China: a Meta-mmentioning
confidence: 99%
“…11 They cannot be used when studies use different statistical models, different subsets of potential explanatory variables, or different transformations on included variables. 11 Conventional meta-analysis can combine multiple measurements of the same thing (e.g. pooling ORs for the same risk factor), but cannot synthesize evidence related to multiple risk factors simultaneously.…”
Section: Risk Factors For Cervical Cancer In Women In China: a Meta-mmentioning
confidence: 99%
See 1 more Smart Citation