Datasets for Bayesian Latent Class Models in Diagnostic Test Validation

Dataverse contains the datasets used in exercises from the textbook "Inference Without a Gold Standard: Bayesian Latent Class Models for Diagnostic Test Validation and Prevalence Estimation". Author Dufour, Simon deposited the data via the Borealis Harvested Dataverse platform. The record was last updated on 2026-07-18.

Use Cases

• Validate diagnostic tests without a perfect reference standard based on the textbook's methodological framework.
• Estimate disease prevalence using imperfect test data based on the described Bayesian models.
• Compare the performance of different diagnostic tests based on the latent class modeling approach.
• Implement and practice Bayesian computational methods for medical statistics as outlined in the textbook exercises.

Strengths

• Data is directly linked to a specific, named textbook on Bayesian latent class models.
• The record has a specific last updated timestamp of 2026-07-18 04:10:45.

Limitations

• Row count, column names, and file formats are unknown, which limits suitability assessment.
• Description metadata is limited; actual data quality requires manual inspection after download.
• Column-level documentation is absent; field semantics must be inferred after download.

Provenance

Source

Borealis Harvested Dataverse

Collection Method

Created as companion data for textbook exercises.

Freshness

Last updated 2026-07-18 04:10:45; freshness should be verified.