# ATINER ' s Conference Paper Series MAT 2018-2661

@inproceedings{ODriscoll2019ATINERS, title={ATINER ' s Conference Paper Series MAT 2018-2661}, author={D O'Driscoll}, year={2019} }

The standard linear regression model can be written as Y=Xβ+ε with uncorrelated zero mean and homoscedastic errors. Here X is a full rank n x p matrix containing the explanatory variables and the response vector y is n x 1 consisting of the observed data. The Ordinary Least Squared (OLS) estimators are given by and the Gauss-Markov Theorem states that is the best linear unbiased estimator. However, the OLS solutions require that be accurately computed. In most real life situations, for example… CONTINUE READING

#### References

##### Publications referenced by this paper.

SHOWING 1-7 OF 7 REFERENCES

## Optimum solution of Many Variable Equations

VIEW 5 EXCERPTS

HIGHLY INFLUENTIAL

## Author ' s personal copy Surrogate models in ill-conditioned systems

VIEW 3 EXCERPTS

HIGHLY INFLUENTIAL

## Limitations of the Least Squares Estimators; A Teaching Perspective

## TRACKING MSE EFFICIENCIES IN RIDGE REGRESSION

VIEW 3 EXCERPTS

## Anomalies in the Foundations of Ridge Regression

VIEW 2 EXCERPTS