The Misuse of BLUP in Ecology and Evolution
Bibliographic record
Abstract
Best linear unbiased prediction (BLUP) is a method for obtaining point estimates of a random effect in a mixed effect model. Over the past decade it has been used extensively in ecology and evolutionary biology to predict individual breeding values and reaction norms. These predictions have been used to infer natural selection, evolutionary change, spatial-genetic patterns, individual reaction norms, and frailties. In this article we show analytically and through simulation and example why BLUP often gives anticonservative and biased estimates of evolutionary and ecological parameters. Although some concerns with BLUP methodology have been voiced before, the scale and breadth of the problems have probably not been widely appreciated. Bias arises because BLUPs are often used to estimate effects that are not explicitly accounted for in the model used to make the predictions. In these cases, predicted breeding values will often say more about phenotypic patterns than the genetic patterns of interest. An additional problem is that BLUPs are point estimates of quantities that are usually known with little certainty. Failure to account for this uncertainty in subsequent tests can lead to both bias and extreme anticonservatism. We demonstrate that restricted maximum likelihood and Bayesian solutions exist for these problems and show how unbiased and powerful tests can be derived that adequately quantify uncertainty. Of particular utility is a new test for detecting evolutionary change that not only accounts for prediction error in breeding values but also accounts for drift. To illustrate the problem, we apply these tests to long-term data on the Soay sheep (Ovis aries) and the great tit (Parus major) and show that previously reported temporal trends in breeding values are not supported.
Fetched live from OpenAlex and de-inverted. Abstracts are not stored in this database: the inverted indexes are 8.6 GB of the frame’s 9.3 GB of text, and the host has 13 GB free.
How this classification was reachedexpand
Full frame machine prediction
Teacher imitationNot calibrated prevalence, not ground truth. Human validation pending. The Gemma side is a direct model label for every work in the frame, read from the title-only record. The Codex side is a classifier learned from the 10,348 direct Codex labels and calibrated to design-weighted sample rates; fields without enough sample support carry no Codex call. Candidate is the union of the two sides; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels.
Distilled classifier scores by category (both heads)
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.055 | 0.146 |
| Meta-epidemiology (narrow) | 0.002 | 0.002 |
| Meta-epidemiology (broad) | 0.003 | 0.003 |
| Bibliometrics | 0.003 | 0.007 |
| Science and technology studies | 0.002 | 0.015 |
| Scholarly communication | 0.005 | 0.009 |
| Open science | 0.005 | 0.005 |
| Research integrity | 0.006 | 0.015 |
| Insufficient payload (model declined to judge) | 0.005 | 0.003 |
Machine scores (provisional)
The two teacher heads of the student model, read on this work. A score orders the frame for review; it never asserts a category, and the validation status ships verbatim with every row.
Baseline scores from an immature model (maturity gate not passed, 7 training rounds). Scores rank; they never assert a category.
score_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from itClassification
machine, unvalidatedMachine predicted; a candidate call from one source (direct Gemma or distilled Codex), not a consensus.
How this classification was reached, model by model and score by score, is at the end of the page under "How this classification was reached".