R Package

An R package, SHELF, is available on CRAN, and a development version is on GitHub. The package includes both Shiny apps and command line implementation for all the methods described in the SHELF documentation.

Shiny apps

The apps linked below are available online, but are also all included in the SHELF R package. Online access to these apps is time-limited (they are hosted on RStudio’s service). If you want to use the apps in an actual elicitation workshop, we strongly encourage you to use the offline versions in the SHELF package.

SHELF: Single expert

Eliciting a distribution from a single expert.

Access single expert online

SHELF: Multiple experts

Eliciting individual distributions from multiple experts. Includes methods for mathematical aggregation using linear pooling.

Access multiple experts online

SHELF: Bivariate elicitation

Eliciting a bivariate distribution using a Gaussian copula.

Access bivariate elicitation online

SHELF: Dirichlet elicitation

Eliciting a Dirichlet distribution for a set of proportions constrained to sum to 1.

Access dirichlet elicitation online

SHELF: Extension method – continuous

Eliciting a distribution for a continuous target variable X via a distribution for a continuous extension variable Y and a conditional distribution for X|Y.

Access extension method – continuous online

SHELF: Extension method – discrete

Eliciting a distribution for a continuous target variable X via a distribution for a discrete extension variable Y and a conditional distribution for X|Y. Can be used to elicit multimodal distributions.

Access extension method – discrete online

Other elicitation methods

We have been involved in developing other elicitation methods, outside of the SHELF project. There is a paper and supporting app/code for each method, but templates for conducting the elicitation are not available within SHELF.

Elicitation for survival and time-to-event outcomes

Ren, S. and Oakley, J. E. (2014) Assurance calculations for planning clinical trials with time-to-event outcomes. Statistics in Medicine, 33(1), 31-45.

Download supporting R code (ZIP, 922KB)

Elicitation for survival analysis with delayed treatment effects

Salsbury, J. A., Oakley J. E, Julious, S. A, Hampson, L. V. (2024). Statistics in Medicine. Assurance methods for designing a clinical trial with a delayed treatment effect

Eliciting proper priors for heterogeneity in random-effects meta analysis

Ren, S., Oakley, J. E. and Stevens, J. W. (2018) Incorporating genuine prior information about between-study heterogeneity in random effects pairwise and network meta-analyses. Medical Decision Making, 38(4), 531-542.

See the appendix for details of supporting software.

Eliciting distributions for population variances

Alhussain, Z. A. and Oakley, J. E. (2020) Assurance for clinical trial design with normally distributed outcomes: Eliciting uncertainty about variances. Pharmaceutical Statistics, 19, 827-839.

MATCH elicitation tool

As part of the MATCH project, David Morris, Jeremy Oakley and John Crowe produced a web-based elictation tool which is based on an earlier version of the SHELF R code. A user guide was produced as part of the PCOD+ project, sponsored by the Office for Naval Research.