A Comparison of Alternative Methods for Estimating Treatment Effects,
Abstract
A common method for testing the effectiveness of a treatment is to choose two groups of individuals at random and apply the treatment to individuals in one of the two groups, using the untreated individuals (the 'control group') as a standard for making comparisons. The effect of the treatment can then be assessed by comparing the distributions of the responses for the two groups. A statistical mathematical model is described.
Document Details
- Document Type
- Technical Report
- Publication Date
- Aug 01, 1973
- Accession Number
- ADA002172
Entities
People
- Gus W. Haggstrom
Organizations
- RAND Corporation