Bayesian Approach for Identifying Efficient Stated-Choice Survey Designs with Reduced Prior Information
Bibliographic record
Abstract
This paper presents the results of a stated-choice survey design in which reduced information is available about the values of the parameters. The main objective of the survey is to develop discrete choice models to analyze the carrier selection process by shippers. The only information available is the expected sign of the parameter in the utility function. Therefore, the use of a Bayesian approach is necessary in analyzing the efficiency of potential survey designs. The measure of efficiency adopted is the 95th percentile value of the D-error, the determinant of the asymptotic variance–covariance matrix, obtained via Monte Carlo simulation. This measure would maximize the expected gain of information with the experiment. In the survey, the respondents (shippers) will be asked to provide the main carrier's attributes used in the selection process. On the basis of the answers, the survey will be customized to each respondent (situation). In this paper, only the results of the design for situations in which shippers select continuous attributes are presented. An algorithm is developed in a statistical package to search and evaluate the efficiency of 1,000 randomly selected potential survey designs. The algorithm maintains the 10 most efficient designs to be evaluated and uses box plots to identify the most suitable design. The results show that the approach adopted improves the efficiency of the design substantially, which would result in more accurate models from the survey data.
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 | 0.122 | 0.269 |
| Meta-epidemiology (narrow) | 0.003 | 0.004 |
| Meta-epidemiology (broad) | 0.007 | 0.005 |
| Bibliometrics | 0.007 | 0.005 |
| Science and technology studies | 0.002 | 0.004 |
| Scholarly communication | 0.003 | 0.006 |
| Open science | 0.005 | 0.005 |
| Research integrity | 0.004 | 0.005 |
| Insufficient payload (model declined to judge) | 0.010 | 0.002 |
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".