Proceedings of the Survey Methods Section THE OUTLIER DETECTION AND TREATMENT STRATEGY FOR THE MONTHLY WHOLESALE AND RETAIL TRADE SURVEY OF STATISTICS CANADA
Bibliographic record
Abstract
The Monthly Wholesale and Retail Trade Survey (MWRTS), conducted by Statistics Canada, produces estimates at various geographic and industry levels based on monthly data collected for sales and inventories. The sales trend is used as an important economic indicator, and the monthly sales estimates form a substantial portion of the estimates for the Gross Domestic Product (GDP). The MWRTS is currently being redesigned, in part to produce estimates according to the new North American Industry Classification System (NAICS) and to take full advantage of the availability of administrative data from the Goods and Services Tax (GST) program. Although many improvements will be implemented, such as a reduction of frame mis-classifications by the use of administrative data and an innovative sample update procedure, influential units will continue to occur as a result of mis-classifications and specific procedures must be put in place to treat them. This paper presents the overall strategy developed to reduce the effect of these influential units. The results from an empirical study that compares the efficiency of four proposed methods to identify and treat outliers are presented and the implementation of these methods in the context of a monthly survey production is discussed.
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 | 0.067 | 0.155 |
| Meta-epidemiology (narrow) | 0.002 | 0.002 |
| Meta-epidemiology (broad) | 0.002 | 0.002 |
| Bibliometrics | 0.006 | 0.010 |
| Science and technology studies | 0.004 | 0.003 |
| Scholarly communication | 0.006 | 0.002 |
| Open science | 0.003 | 0.003 |
| Research integrity | 0.002 | 0.004 |
| Insufficient payload (model declined to judge) | 0.096 | 0.052 |
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".