Statistical Methods for the Item Count Technique and List Experiment

A software package implementing methods for analyzing survey data collected via the item count technique, also known as the list experiment. The package includes Bayesian MCMC regression for standard and multiple sensitive item designs, hierarchical models, combined experiment models, and diagnostic tests for response error. It is authored by Graeme Blair and implements methods from a series of academic papers published between 2011 and 2018.

Use Cases

• Conducting multivariate regression analysis on list experiment survey data based on the implemented statistical methods.
• Performing Bayesian MCMC hierarchical modeling for list experiments with up to three hierarchical groups.
• Diagnosing and adjusting for response error in list experiment data using the provided statistical tests.
• Combining list experiment data with direct questions or endorsement experiments for joint analysis.

Strengths

• Implements a series of peer-reviewed statistical methods from papers published between 2011 and 2018.
• Includes multiple advanced models: Bayesian MCMC regression, hierarchical models, and combined experiment models.
• Provides diagnostic tools like a statistical test for detecting failures of list experiments and a placebo test.

Limitations

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

Provenance

Source

Graeme Blair

Collection Method

Software package implementing academic statistical methods.

Time Range

Methods developed between 2011 and 2018.

Freshness

Last update date is unknown; freshness unverified.

Geography

null