Claim · model-written summary
Residual dependence across years was lower for the mixture model.
CoffeaNot reportedMaterialGeneCompoundOrgan / stageInteractorInteractor roleSecond interactorSecond interactor roleTreatmentSettingValueQualifier
Organisms pictured · Representative pictures of the matched species, not figures from the paper.
Verbatim
e0“Residual dependence across years was lower for the mixture model”
t0“Coffee Bean Progenies”
Title
Mixture Mixed Models: Biennial Growth as a Latent Variable in Coffee Bean Progenies
Indalécio Cunha Vieira Júnior; Carlos Pereira da Silva; Joel Jorge Nuvunga; et al. Crop Science 2019. doi:10.2135/cropsci2018.02.0141
Other claims from this paper (8)
- Method / resource Mixture models drastically reduced prediction error variance, CV and residual variance on real coffee data.
- Method / resource Mixture models produced higher estimated heritability.
- Method / resource Mixture models produced higher expected gain from selection.
- Method / resource Genetic correlations did not differ between models.
- Method / resource The posterior probability matrix captured progeny biennial patterns.
- Association Spearman correlation of 0.87 suggested grouped-mean selection may be inefficient.
- Method / resource The proposed model was more efficient when subpopulation means differed more.
- Recommendation The authors conclude mixture mixed models are superior for progenies with distinct biennial patterns.