Improving causal inference from unreplicated on‐farm strip trials with propensity score matching: Application to plant growth regulator effects in wheat
Bibliographic record
Abstract
Abstract Farmers often conduct unreplicated on‐farm experiments (OFE) to evaluate management practices such as the application of plant growth regulators (PGR) in winter wheat ( Triticum aestivum L.). Traditional methods of comparing strip average yields, such as using weigh wagons or yield monitors, lack error estimates and are causally confounded by field variability. Prescription (Rx) maps with randomization and replication may reduce causal confounding but are not always feasible. We propose a methodology to improve causal inference from unreplicated strip trials using propensity score matching (PSM). PGR strip trials were implemented using growers’ fields and equipment at two sites. Yield data, topographic covariates, and soil properties were collected. Propensity scores were calculated and used to create weights for covariate balancing. Next, treatment effect estimates and 95% confidence intervals were calculated for each site using G‐computation. Various benchmark models were included to compare the results of commonly implemented spatial models to the results from PSM. Spatial benchmark models showed evidence of spatial confounding, a purely statistical artifact rather than a causal effect. This artifact may alter treatment estimates and test statistics in strip trials where experimental units are not randomized throughout the field. PSM has potential to address the lack of replication and randomization in simple two‐treatment strip trials. PSM can potentially increase accessibility to rigorous OFE and improve decision‐making in agricultural practices, particularly in contexts where traditional experimental designs present barriers to participation.
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 | 0.184 | 0.366 |
| Meta-epidemiology (narrow) | 0.001 | 0.001 |
| Meta-epidemiology (broad) | 0.003 | 0.004 |
| Bibliometrics | 0.002 | 0.003 |
| Science and technology studies | 0.001 | 0.002 |
| Scholarly communication | 0.002 | 0.002 |
| Open science | 0.003 | 0.004 |
| Research integrity | 0.002 | 0.003 |
| Insufficient payload (model declined to judge) | 0.005 | 0.000 |
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".