We formulate the problem as an optimization of (i) a collection of linearization nodes around which individual linear models are formed and (ii) aggregation of the individual linearizations, where the linearization fields are subject to optimization.
In addition, we found no significant (α = 0.05) correlation between total number of larvae per plant with mass per larva using individual linear models for each plant line separately (supplementary fig. S3, Supplementary Material online).
Overall mean values of individual linear regression model coefficients were significantly > 0 for U-Alb and U-A1M when both were included in the same model as predictors of U-Cd, regardless of whether the dependent variable was U-Cd excretion rate or U-Cd concentration adjusted for U-Crea or SG (data not shown).
The optimal number of the latent variables in PLSR for the individual HRTF linear model is also chosen by cross-validation.
Individual linear regression models were run in which child BMI z score and child diet quality indicators were dependent variables and HFE variables and child/parent characteristics were independent variables of interest.
To account for the paired structure of the data (more than one sample available for each individual), linear mixed models (LMMs) for repeated measurements were used to determine which metabolites were significantly changed in the urine of volunteers after treatment.
However, for valine, serine, and histidine belonging to the GC-medium group, the individual linear regression models can be used to improve the prediction performance up to R = 0.51, 0.37, and 0.22, respectively (Additional file 1: Tables S3, S4).
We then fit individual generalized linear models with a logit transform to estimate ORs for SCC in association with a unit increase in urinary ΣAs, iAs, MMA, DMA, %iAs, %MMA, %DMA, iAs/MMA, and DMA/MMA.
Individual generalised linear models were used to determine the association between gene expression and DNA methylation of specific loci with surgical debulking status adjusting for microarray batch, age at diagnosis and stage.
Using individual generalised linear models adjusting for microarray batch, age and stage and adjusting for multiple comparisons using FDR, two probes; MTDH (probe ID '212250_at') and IGF1R (probe ID '208441_at') were found to be significantly differentially expressed (P<0.05, FDR <5%) associated with optimal (⩽1 cm residual disease) or suboptimal (>1 cm residual disease) surgery.
