21 REML

Learning Objectives

By the end of this chapter, you will be able to:

State the difference between ML and REML and why REML is preferred
Describe the EM, Newton–Raphson, and average information algorithms
Run AI-REML and interpret its output
Obtain standard errors of variance components and of heritability
Diagnose convergence failure in multi-trait analyses

Assumes Ch 20.

Chapter in progress

This chapter has not been written yet. The objectives above are the contract it will be written against — they are taken from CHAPTERS.md, which is the outline for the whole book.

Purpose. The workhorse.

---
title: "REML"
---

::: {.callout-note icon=false}
## Learning Objectives

By the end of this chapter, you will be able to:

1. **State** the difference between ML and REML and why REML is preferred
2. **Describe** the EM, Newton–Raphson, and average information algorithms
3. **Run** AI-REML and interpret its output
4. **Obtain** standard errors of variance components and of heritability
5. **Diagnose** convergence failure in multi-trait analyses
:::

*Assumes Ch 20.*

::: {.callout-warning}
## Chapter in progress

This chapter has not been written yet. The objectives above are the contract it will be written
against — they are taken from `CHAPTERS.md`, which is the outline for the whole book.

**Purpose.** The workhorse.
:::