Sensitivity analysis method in the presence of a missing not at random ordinal independent variable
Bibliographic record
Abstract
Data analysis often encounters missing data, which can result in inaccurate conclusions, especially when it comes to ordinal variables. In trauma data, the Glasgow Coma Scale is useful for assessing the level of consciousness. This score is often missing in patients who are intubated or under sedation upon arrival at the hospital, and those with normal reactivity without head injury, suggesting a Missing Not At Random (MNAR) mechanism. The problem with MNAR is the absence of a definitive analysis. While sensitivity analysis is often recommended, practical limitations sometimes restrict the analysis to a basic comparison between results under Missing Completely At Random (MCAR) and Missing At Random (MAR) assumptions, disregarding MNAR plausibility. Our objective is to propose a flexible and accessible sensitivity analysis method in the presence of a MNAR ordinal independent variable. The method is inspired by the sensitivity analysis approach proposed by Leurent et al. (2018) for a continuous response variable. We propose an extension for an independent ordinal variable. The method is evaluated on simulated data before being applied to Pan-Canadian trauma data from April 2013 to March 2018. The simulation shows that MNAR estimates are less biased than MAR estimates and more precise than complete case analysis (CC) estimates. The confidence intervals coverage rates are relatively better for MNAR estimates than CC and MAR estimates. In the application, it is observed that the Glasgow Coma Scale is significant under MNAR, unlike MCAR and MAR assumptions.
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 | 0.093 | 0.200 |
| Meta-epidemiology (narrow) | 0.003 | 0.001 |
| Meta-epidemiology (broad) | 0.003 | 0.006 |
| Bibliometrics | 0.004 | 0.003 |
| Science and technology studies | 0.001 | 0.002 |
| Scholarly communication | 0.003 | 0.003 |
| Open science | 0.003 | 0.005 |
| Research integrity | 0.003 | 0.006 |
| Insufficient payload (model declined to judge) | 0.010 | 0.001 |
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".