Bayesian Model Averaging in Consumer Demand Systems with Inequality Constraints
Bibliographic record
Abstract
Share equations for the translog and almost ideal demand systems are estimated using Markov Chain Monte Carlo. A common prior on the elasticities and budget shares evaluated at average prices and income is used for both models. It includes equality restrictions (homogeneity, adding up and symmetry) and inequality restrictions (monotonicity and concavity). Posterior densities on the elasticities and shares are obtained; the problem of choosing between the results from the two alternative functional forms is resolved by using Bayesian model averaging. The application is to USDA data for beef, pork and poultry. Estimation of elasticities and shares, evaluated at mean prices and expenditure, is insensitive to model choice. At points away from the means, the estimates are sensitive, and model averaging has an impact. On estime les équations de partage des systèmes translog et de demande quasi idéale par la méthode de Monte Carlo en chaînes de Markov. Ces deux modèles reposent sur une prémisse commune, celle de l'évaluation des élasticités et des pans du budget à des prix et à des revenus moyens. Les analyses supposent certaines restrictions au niveau de l'égalité (homogénéité, addition et symétrie) et de l'inégalité (monotonie et concavité). On établit la densité des élasticités et des pans a posteriori. Le calcul de la moyenne par le modèle bayesien rend le choix entre les résultats de l'une ou l'autre fonction plus facile. L'auteur a appliqué cette méthode aux données de l'USDA sur le bœuf, le porc et la volaille. L'estimation des parts et des élasticités selon des dépenses et des prix moyens est insensible au modéle utilisé. Néanmoins, elle devient sensible quand on s'éloigne des valeurs moyennes, auquel cas, le modèle employé pour calculer la moyenne a une incidence sur les résultats.
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 distilled prediction
Teacher imitationNot calibrated prevalence, not ground truth. Human validation pending. Learned from the 10,348 direct Codex labels and 10,348 direct Gemma labels. Candidate is the union of thresholded teacher heads; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels or direct frontier model labels.
Codex and Gemma teacher scores by category
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.001 | 0.000 |
| Meta-epidemiology (narrow) | 0.001 | 0.001 |
| Meta-epidemiology (broad) | 0.001 | 0.000 |
| Bibliometrics | 0.001 | 0.000 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.000 | 0.001 |
| Open science | 0.001 | 0.000 |
| Research integrity | 0.000 | 0.001 |
| Insufficient payload (model declined to judge) | 0.000 | 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 teacher head, 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".