Abstract
Summary Various topics are reviewed: the effect of modern computers on statistical calculation; analysis by vector components rather than analysis merely of variance; “stepwise regression”; testing goodness of fit by examining residuals. Possible alternatives to the method of least squares appropriate when the distribution of errors has long tails, and computation of the likelihood function resulting from a Pearson Type VII distribution of errors, are considered. Some of the methods discussed are illustrated by study of several sets of observations already well known in the literature.
Keywords
Goodness of fitLeast-squares function approximationStatisticsMathematicsApplied mathematicsComputationVariance (accounting)Computer scienceEconometricsAlgorithm
Affiliated Institutions
Related Publications
R-Squared Measures for Count Data Regression Models with Applications to Health-Care Utilization
For regression models other than the linear model, R-squared type goodness-to-fit summary statistics have been constructed for particular models using a variety of methods. The ...
Goodness-of-Fit Testing for Latent Class Models
Latent class models with sparse contingency tables can present problems for model comparison and selection, because under these conditions the distributions of goodness-of-fit i...
Maximum likelihood fitting using ordinary least squares algorithms
Abstract In this paper a general algorithm is provided for maximum likelihood fitting of deterministic models subject to Gaussian‐distributed residual variation (including any t...
A Linear Spatial Correlation Model, with Applications to Positron Emission Tomography
Abstract A simple spatial-correlation model is presented for repeated measures data. Correlation between observations on the same subject is assumed to decay as a linear functio...
Regression methods for high dimensional multicollinear data
To compare their performance on high dimensional data, several regression methods are applied to data sets in which the number of exploratory variables greatly exceeds the sampl...
Publication Info
- Year
- 1967
- Type
- article
- Volume
- 29
- Issue
- 1
- Pages
- 1-29
- Citations
- 142
- Access
- Closed
External Links
Social Impact
Altmetric
PlumX Metrics
Social media, news, blog, policy document mentions
Citation Metrics
142
OpenAlex
Cite This
F. J. Anscombe
(1967).
Topics in the Investigation of Linear Relations Fitted by the Method of Least Squares.
Journal of the Royal Statistical Society Series B (Statistical Methodology)
, 29
(1)
, 1-29.
https://doi.org/10.1111/j.2517-6161.1967.tb00672.x
Identifiers
- DOI
- 10.1111/j.2517-6161.1967.tb00672.x