8.3 Inference in Linear Mixed Models
8.3.1 Inference for Fixed Effects (β)
The goal is to test hypotheses about the fixed effects parameters β using various statistical tests:
8.3.1.1 Wald Test
The Wald test assesses whether certain linear combinations of fixed effects are equal to specified values.
Given:
ˆβ(θ)=(X′V−1(θ)X)−1X′V−1(θ)Y,
and its variance:
Var(ˆβ(θ))=(X′V−1(θ)X)−1.
In practice, we substitute ˆθ (the estimate of θ) to obtain:
Hypotheses:
H0:Aβ=d
where:
- A is a contrast matrix specifying linear combinations of β.
- d is a constant vector representing the null hypothesis values.
Wald Test Statistic:
W=(Aˆβ−d)′[A(X′ˆV−1X)−1A′]−1(Aˆβ−d).
Distribution under H0:
W∼χ2rank(A).
Caution with Wald Test:
- Underestimation of Variance:
The Wald test ignores the variability from estimating ˆθ, leading to underestimated standard errors and potentially inflated Type I error rates. - Small Sample Issues:
Less reliable in small samples or when variance components are near boundary values (e.g., variances close to zero).
8.3.1.2 F-Test
An alternative to the Wald test, the F-test adjusts for the estimation of σ2 and provides better performance in small samples.
Assume:
Var(Y)=σ2V(θ).
The F-statistic is:
F∗=(Aˆβ−d)′[A(X′ˆV−1X)−1A′]−1(Aˆβ−d)ˆσ2rank(A).
Distribution under H0:
F∗∼Frank(A),dfdenominator.
Approximating Denominator Degrees of Freedom:
- Satterthwaite approximation
- Kenward-Roger approximation (provides bias-corrected standard errors)
F-Test Advantages:
- More accurate in small samples compared to the Wald test.
- Adjusts for variance estimation, reducing bias in hypothesis testing.
Wald Test vs. F-Test:
Criterion | Wald Test | F-Test |
---|---|---|
Small Sample Performance | Poor (can inflate Type I error) | Better control of Type I error |
Variance Estimation | Ignores variability in ˆθ | Adjusts using ˆσ2 |
Reduction to t-test | Yes (for single β) | Yes (when rank(A) = 1) |
8.3.1.3 Likelihood Ratio Test
The Likelihood Ratio Test (LRT) compares the fit of nested models:
Null Hypothesis:
H0:β∈Θβ,0
where Θβ,0 is a subset of the full parameter space Θβ.
Test Statistic:
−2logλ=−2log(ˆLML,0ˆLML),
where:
- ˆLML,0 = Maximized likelihood under H0 (restricted model)
- ˆLML = Maximized likelihood under the alternative (full model)
Distribution under H0:
−2logλ∼χ2df
where df=dim(Θβ)−dim(Θβ,0) (the difference in the number of parameters).
Important Notes:
- LRT is applicable only for ML estimates (not REML) when comparing models with different fixed effects.
- REML-based LRT can be used for comparing models that differ in random effects (variance components), but not fixed effects.
8.3.2 Inference for Variance Components (θ)
For ML and REML estimators:
ˆθ∼N(θ,I(θ)−1),
where I(θ) is the Fisher Information Matrix.
This normal approximation holds well for large samples, enabling Wald-type tests and confidence intervals.
8.3.2.1 Wald Test for Variance Components
The Wald test for variance components follows the same structure as for fixed effects:
Test Statistic:
W=(ˆθ−θ0)2^Var(ˆθ).
Distribution under H0:
W∼χ21.
Limitations of Wald Test for Variance Components:
- Boundary Issues: The normal approximation fails when the true variance component is near zero (boundary of the parameter space).
- Less reliable for variance parameters than for covariance parameters.
8.3.2.2 Likelihood Ratio Test for Variance Components
LRT can also be applied to variance components:
Test Statistic:
−2logλ=−2log(ˆLREML,0ˆLREML).
Distribution under H0:
- Not always χ2-distributed when variance components are on the boundary (e.g., testing if σ2=0).
- May require mixture distributions or adjusted critical values.
Test | Best For | Strengths | Limitations |
---|---|---|---|
Wald Test | Fixed effects (β) | Simple, widely used | Underestimates variance, biased in small samples |
F-Test | Fixed effects (β) | Better in small samples, adjusts df | Requires approximation for degrees of freedom |
LRT (ML) | Fixed effects, nested models | Powerful, widely used | Not valid for REML with fixed effects |
LRT (REML) | Variance components | Robust for random effects | Boundary issues when variances are near zero |
Wald (Variance) | Variance components (θ) | Simple extension of Wald test | Fails near parameter space boundaries |