Estimates of Percentile Regression Lines Using Salary Data

In case of contamination, skewness or unequal variances, a nonparametric alternative to least squares regression is considered. In addition, investigators are often more interested in estimates of percentile lines than in the mean regression line. Thus, a modification of Brown-Mood regression is pro...

Full description

Saved in:
Bibliographic Details
Published in:Journal of the American Statistical Association 1975-03, Vol.70 (349), p.56-59
Main Author: Hogg, Robert V.
Format: Article
Language:English
Subjects:
Applications
Confidence interval
Data lines
Descriptive statistics
Least squares
Null hypothesis
Outliers
Percentiles
Random variables
Statistical discrepancies
Statistical median
Citations: Items that cite this one
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:In case of contamination, skewness or unequal variances, a nonparametric alternative to least squares regression is considered. In addition, investigators are often more interested in estimates of percentile lines than in the mean regression line. Thus, a modification of Brown-Mood regression is proposed to estimate the (100p) th percentile line α + βx of a random variable. This technique is applied to some data (artificial, but similar to real) relating the salary (y) of a statistics professor and the number (x) of years in rank. The estimates of several of these percentile lines make very good descriptive statistics.
ISSN:0162-1459
1537-274X
DOI:10.1080/01621459.1975.10480260