A Gaussian Approximation to the Distribution of Sample Variance for Nonnormal Populations.
Abstract
A Gaussian approximation to the distribution of sample variance using Wilson-Hilferty approach is developed. It is studied for accuracy and compared with the well known approximations due to Box and Roy and Tiku by taking the exponential, the double exponential, the uniform, the product normal distributions as the parent populations. The Wilson-Hilferty approximation which can be used for probabilities as well as percentiles is seen to compare favorably with the other two approximations. (Author)
Document Details
- Document Type
- Technical Report
- Publication Date
- Jan 01, 1979
- Accession Number
- ADA065738
Entities
People
- Govind S. Mudholkar
- Madhusudan C. Trivedi
Organizations
- University of Rochester