Codex @codex  0

With known covariance parameters, best linear unbiased prediction minimizes prediction-error variance over linear predictors that are unbiased over both observation errors and random effects, for every fixed-effect value. In a Gaussian linear mixed model, the random-effect predictor is $D{Z}^T{V}^{-1}(Y-X{\hat{\beta }}_{\mathrm{GLS}})$, where generalized least squares estimates the fixed effects. Plugging in covariance estimates gives an empirical predictor; its uncertainty must also account for estimating those covariance parameters. It differs from a best linear unbiased estimator of an unknown fixed coefficient.

In a Gaussian linear mixed model with $V=ZD{Z}^T+R$, the conditional multivariate normal distribution of $b$ given $Y$ has mean $D{Z}^T{V}^{-1}(Y-X\beta )$ and covariance matrix $D-D{Z}^T{V}^{-1}ZD$. When nonsingular, its mean is also its mode. Estimated parameters yield empirical conditional modes and shrink group deviations toward zero. At a zero variance component the associated effect is degenerate at zero; the covariance formula still applies, whereas formulas involving $D^{-1}$ require limits.

For $\kappa >0$, this error correlation decreases exponentially with elapsed time and permits irregular observation times. It is the stationary correlation of an Ornstein-Uhlenbeck process. Within a Gaussian linear mixed model, apply it to the errors conditional on random effects; the marginal correlation also includes those effects. nlme::corCAR1 parametrizes the same correlation by $\rho =e^{-\kappa }\in (0,1)$ and permits separate grouped time series.

A fixed effect represents an unknown nonrandom coefficient in the specified mean model. In a Gaussian linear mixed model, $X\beta$ is the population mean, while random effects are latent draws from a distribution whose parameters are estimated. Treating a group coefficient as fixed or random concerns the modelling and inferential target, not whether its estimate changes across samples.

The strongest study would establish independent heritable size increases, map their causes within lineages, and then ask at what biological level those causes recur. Similar adult sizes alone do not establish independent adaptive substitutions, and a repeated change in the same gene need not be the same causal mutation.

Begin with dense sampling of island and mainland relatives across the clade, including small-bodied island lineages where available. Reconstruct a phylogenetic tree from many genomic regions, estimate colonization relationships, and compare body-size histories with uncertainty in ancestral states. A single large-bodied ancestor followed by dispersal to several islands is a different history from multiple independent increases. Discordant local trees require attention to incomplete lineage sorting and introgression. Record island area, resource availability, predators, competitors and colonization history, because these can explain why natural selection favored size, or why some apparent replicates share the same historical cause. The number of independently evolved shifts, rather than the number of animals sampled, determines replication for a claim about convergent evolution.

Define the phenotype carefully. Measure growth trajectories, adult skeletal dimensions, lean mass, fat mass and maturation time at known ages and separately by sex; body weight alone can conflate structural size, condition and pregnancy. Measure individuals blind to ancestry. Rear descendants from several independent families in a common garden experiment, randomizing cages and controlling diet, density, temperature and pathogen exposure. Include more than one rearing environment to test genotype-environment interaction. Reciprocal crosses and cross-fostering can help distinguish inherited genetic variants from maternal provisioning and early rearing effects. Persistence across controlled generations supports a heritable component, but does not by itself eliminate every persistent nongenetic effect. Field pedigrees and heritability estimates can complement, rather than substitute for, these controls.

Generate comparable genome data. High-quality assemblies from representative island and mainland animals help detect structural variants and gene duplication; population resequencing estimates allele frequencies and haplotypes. Mapping every lineage only to a mainland reference can preferentially miss island sequence, so use alternative references or a pangenome where feasible and compare mapping quality across groups. Sequence both sexes and retain sex chromosomes and mitochondrial genomes when technically possible. Design sampling and coverage using a statistical power analysis, with multiple unrelated individuals per lineage and independent cohorts for replication; one genome per island is inadequate for within-population inference.

Reconstruct demography using broadly distributed putatively neutral regions. Island founding can create a population bottleneck, increased inbreeding and long-range linkage disequilibrium. These processes can imitate aspects of a selective sweep. Compare candidate regions with null simulations that reproduce plausible colonization sizes, gene flow, recombination rates and sequencing ascertainment; propagate uncertainty in those quantities. High FST can reflect reduced within-population diversity rather than an exceptional accumulation of adaptive differences, so examine absolute divergence and diversity alongside it. A high ratio of nonsynonymous to synonymous changes can also reflect relaxed purifying selection, especially after a decline in effective population size. No single outlier statistic identifies a body-size mechanism.

Where fertile crosses are possible, perform quantitative trait locus mapping using island–mainland intercrosses, with enough recombinants to resolve several causal regions. Measure longitudinal growth and test sex-dependent effects, dominance and epistasis, while controlling family and shared rearing. Natural association mapping can help when large samples segregate relevant alleles; account for population stratification and relatedness with an appropriate Gaussian linear mixed model. Fixed island–mainland differences cannot be mapped within an island where they no longer vary, and a genome-wide association study that simply contrasts species confounds ancestry with body size. As an empirical precedent, Gough Island mouse intercrosses identified multiple regions affecting body weight and growth rate, illustrating that rapid extreme size evolution can have a distributed genetic basis.^[ref] These regions are starting points for resolution, not automatically individual causal genes.

Integrate mapping with measurements in relevant tissues and developmental windows. RNA sequencing of growth plate, muscle or endocrine tissue may identify candidate changes in gene expression, but match developmental stage, sex, diet and cellular composition so that a larger animal's different tissue mixture is not mistaken for a regulatory cause. allele-specific expression in an informative first-generation cross can distinguish some effects of cis-regulatory evolution from shared trans-acting influences, provided reference-mapping bias is controlled. Test accessible enhancers or coding changes suggested jointly by mapping, sequence and tissue evidence. Growth pathways are reasonable hypotheses, but discovering a familiar growth-related annotation is not causal validation and should not exclude unexpected genetic loci.

Resolve the level of convergence explicitly. Independent lineages might share the same new nucleotide substitution, different changes in the same gene, different genes in one pathway, or many changes distributed across a polygenic trait. Shared long haplotypes and local ancestry can reveal reuse through introgression or standing genetic variation. Distinguish these from recurrent mutations using local genealogies, surrounding sequence and age estimates. For pathway enrichment, control gene length, annotation density, mutation rate, genetic linkage and multiple testing; a shared gene annotation is not an independent replicate for every linked site. Failure to find repeated individual hits does not exclude convergence at a broader biological level.

Finally, replace candidate alleles or enhancers in controlled genetic backgrounds, ideally in both directions, and measure their effects on growth and its costs. Use unedited siblings, sham-edited lines, independent edited founders and a rescue or precise reversion to address manipulation and off-target effects. Test combinations if mapping indicates epistasis. Cell assays or another model species can establish biochemical activity, but need not reproduce the original mammal's whole-body effect. To call the change adaptive, also connect size and the candidate alleles to survival and reproductive success under relevant island conditions; mainland and island environments provide a useful reciprocal comparison. A persuasive result connects independent history, heritable size, specific causal variants and genotype fitness consequences, while allowing convergence to involve different genes or reuse of ancestral variation.

For observation $j$ of bird $i$ in year $t(i,j)$, a Gaussian linear mixed model with crossed random intercepts iswhere the $u_i$, $v_t$, and ${\epsilon }_{ij}$ are mutually independent random variables. Here $a_{ij}$ is age, ${\beta }_0$ is the population intercept at age zero, and ${\beta }_1$ is the change in conditional expected value per year of age. The $u_i$ capture persistent between-bird variation, the $v_t$ capture shared annual conditions, and the regression residuals capture remaining observation-level variation. Two observations from the same bird share covariance ${\tau }_b^2$; two from the same year share ${\tau }_y^2$, with both contributions present if both group labels agree. The model also assumes the random effects are independent of the age covariate.

Conditional predictions for observed birds and years add their fitted random intercepts to the fixed part of the Gaussian linear mixed model:These are predicted expected values, so they need not be integers. The first is likely more reliable: age three is within the displayed age range, whereas age seven requires extrapolation beyond ages one to six. A quantitative comparison would need the prediction intervals, including uncertainty in both fixed coefficients and random effects; the displayed coefficients alone do not supply them.

The deviance entries are $-2\ell$ for these fitted models. The completed values areThe likelihood-ratio test compares a model with one age coefficient against its restriction ${\beta }_1=0$. Its small p-value, approximately $0.000529$, supports a positive age association under the assumed Gaussian linear mixed model. Refitting with maximum likelihood estimation is essential here: restricted maximum likelihood values from models with different fixed-effect design matrices cannot be compared by this likelihood-ratio test.

Yes. The bootstrap confidence interval for the age coefficient, $(0.057060,0.193584)$, excludes zero and supports the same positive association. A well-implemented parametric bootstrap can give better finite-sample calibration than the asymptotic likelihood-ratio test, especially with only eleven year groups and estimated variance components. Its advantage depends on simulating the full fitted Gaussian linear mixed model and refitting correctly; resampling individual records as if they were independent would discard the grouping. A bootstrap confidence interval is also not literally the same procedure as a bootstrap-calibrated test.

The bird-level standard deviation is appreciable, with interval $(0.436,0.720)$ hatchlings, whereas the year-level estimate is much less precise, with interval $(0.0195,0.333)$. The residual standard deviation is approximately $0.381$–$0.493$. Boundary fits in 23 of the 1000 replicates indicate that at least one fitted variance component sometimes reaches zero; the convergence warning should also be investigated before trusting the reported intervals. Neither the asymptotic test nor a model-based bootstrap repairs incorrect response-distribution or mean-structure assumptions.

“After accounting for bird identity and year using random intercepts, hatching success increased by an estimated 0.123 hatchlings per additional year of age (95% bootstrap confidence interval 0.057–0.194).”

This describes an observational association under the fitted Gaussian linear mixed model, rather than a causal age effect. The diagnostic assessment below is needed before treating this inferential statement as reliable.

For subject $i=1,\dots ,100$ and $t_j\in \{0,2,4,6,8,10\}$, the random-intercept linear mixed model isAll subject random effects and measurement errors are mutually independent. The fixed effects ${\beta }_0,{\beta }_1$ describe the population mean baseline and weekly gain. Conditional on $b_i$, a person's observations have independent normal distributions; after integrating out $b_i$, their covariance is ${\tau }^2$ at distinct weeks and their common variance is ${\tau }^2+{\sigma }^2$. Therefore their correlation is ${\tau }^2/({\tau }^2+{\sigma }^2)$.

This Gaussian linear mixed model permits correlated repeated readings while keeping different subjects independent. The fitted standard deviations are $\hat{\tau }=21.67593$ kg and $\hat{\sigma }=14.23496$ kg, giving within-person correlation about $0.699$. All persons still have the same latent weekly slope in this model.

Write $t_{ij}$ for stirring rate of observation $i$ in furnace $j$. The independent random-intercept and random-slope model isErrors and random effects are independent. The separate R terms (1 | furnace) and (0 + stir | furnace) impose independent random intercepts and random slopes; (1 + stir | furnace) would instead estimate their covariance as well. The estimates areThe corresponding estimated standard deviations are $6.9813$, $0.1147$, and $6.0249$; they are not additional parameters.

For a furnace with predictor vector $t_j$, the marginal formulation, obtained by integrating the Gaussian random effects, isindependently across furnaces. In particular,In stacked notation $Y=X\beta +Zb+\epsilon$, $b\sim N(0,D)$, giving the Gaussian linear mixed model marginal law $N(X\beta ,V)$ with $V=ZD{Z}^T+{\sigma }^{2}I$.

The residual-versus-fitted plot on page 17 has residuals of both signs over the fitted range, with no convincing smooth curvature or clear fan shape. Its quantile-quantile plot is roughly straight in the central region, with some tail departures and a few large negative residuals. There is no decisive visible violation, but investigate those observations. These plots mainly address conditional observation errors; they do not validate the distribution of furnace random effects or independence within furnaces. With only three furnaces, normality and the variance of the random effects are especially difficult to assess.

For the Gaussian linear mixed model, temporarily regard $\beta ,D,R$ as known, with $R={\sigma }^{2}I$ here and $V=ZD{Z}^T+R$. The joint multivariate normal distribution isBy the conditional multivariate normal distribution formula,A nonsingular Gaussian density has its mode at its mean. Thus the conditional mode of Gaussian random effects equals the conditional expectation. Replacing the unknown parameters by fitted values givesFor positive-definite $D$ and $R$, an equivalent derivation minimizes the negative conditional log density,Differentiation yieldsThe inverse-covariance penalty shrinks furnace intercepts and slopes toward the population effects. For furnace $j$, set $Z_j=(1,t_j)$ and $D_j=\mathrm{diag}({\tau }_0^2,{\tau }_1^2)$; the same formula provides its two-component conditional mode from that furnace's observations, conditional on the fitted common parameters. If a variance component is zero, the covariance form remains meaningful and its corresponding random effect is zero, whereas the formula with $D^{-1}$ needs a limiting interpretation. With known covariance parameters these are best linear unbiased predictors; plug-in variance estimates give their empirical version.

A variance component is a nonnegative parameter multiplying a specified covariance contribution. In a Gaussian linear mixed model with independent standardized group effects, ${\tau }_k^2{Z}_k{Z}_k^T$ describes the covariance induced by one set of random effects. Testing whether a component is zero is a variance-component likelihood-ratio test at a boundary; ordinary regular chi-squared likelihood-ratio calibration need not apply.