Recover and estimate beliefs given responses to quadratic scoring rule task
You can not select more than 25 topics Topics must start with a letter or number, can include dashes ('-') and can be up to 35 characters long.
Brian Albert Monroe 87d2d3d338
Force reports of 0 and 1 to be beliefs of 0 and 1
8 months ago
R Force reports of 0 and 1 to be beliefs of 0 and 1 8 months ago
man Update documentation, remove joint fitting functions 1 year ago
.Rbuildignore First commit 3 years ago
.gitignore First commit 3 years ago
DESCRIPTION Force reports of 0 and 1 to be beliefs of 0 and 1 8 months ago
NAMESPACE Update documentation, remove joint fitting functions 1 year ago
README.md README: Add a basic readme 2 years ago

README.md

Belief Recovery and Estimation

This package provides 3 core pieces of functionality:

  1. Recover subjective beliefs given a set of reports and risk preferences. This is an implementation of the theory of Harrison & Ulm (2016)
  2. Jointly estimate recovered beliefs and risk preferences through an interval regression approch.
  3. Jointly estimate subjective beliefs and risk preferences using a behavioral approach. This follows the approach of Andersen, Fountain, Harrison, and Rutström.

Currently supported utility functions:

  • CRRA, x^(1-r)/(1/r)
  • power, x^r

Currently supported probability weighting functions:

  • EUT
  • Power
  • Inverse-S
  • 2 parameter Prelec (1998)

This package is extended as I find additional needed functionality.