Scribd
Upload
11 views5 pages

DW & GLS

The Durbin-Watson statistic is a test used to detect autocorrelation in regression residuals, with a value of 2 indicating no autocorrelation. It tests the null hypothesis that residuals are not autocorrelated, and is applicable under certain assumptions, including the absence of lagged dependent variables. When autocorrelation is present, Generalized Least Squares (GLS) can be used to provide more accurate estimates compared to Ordinary Least Squares (OLS).

Uploaded by

sscaspirant1002
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PDF, TXT or read online on Scribd
11 views5 pages

DW & GLS

The Durbin-Watson statistic is a test used to detect autocorrelation in regression residuals, with a value of 2 indicating no autocorrelation. It tests the null hypothesis that residuals are not autocorrelated, and is applicable under certain assumptions, including the absence of lagged dependent variables. When autocorrelation is present, Generalized Least Squares (GLS) can be used to provide more accurate estimates compared to Ordinary Least Squares (OLS).

Uploaded by

sscaspirant1002
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PDF, TXT or read online on Scribd
You are on page 1/ 5

DURBIN WATSON

https://youtu.be/3mjIRmDyIZE
https://www.cbpbu.ac.in/userfiles/file/2020/STUDY_MAT/ECO/1.pdf
https://www.geeksforgeeks.org/durbin-watson-test/
https://epgp.inflibnet.ac.in/epgpdata/uploads/epgp_content/business_economics/08._fun
damentals_of_econometrics/18._test_for_autocorrelation/et/6776_et_18_et.pdf
The Durbin Watson statistic is a test statistic used in statistics to detect autocorrelation in the
residuals from a regression analysis. The Durbin-Watson test statistic tests the null hypothesis
that the residuals from an ordinary least-squares regression are not autocorrelated against the
alternative that the residuals follow an AR1 process. For example, the errors from a regression
model on daily stock price data might depend on the preceding observation because one day's
stock price affects the next day's price. The Durbin Watson statistic will always assume a value
between 0 and 4. A value of DW = 2 indicates that there is no autocorrelation. One important
way of using the test is to predict the price movement of a particular stock based on historical
data.The test statistic is calculated using the residuals of the regression model, and it compares
the differences between consecutive residuals to their average. An approximation for a large
sample is as such:

Calculation of Durbin Watson Statistic


The hypotheses followed for the Durbin Watson statistic:
The hypothesis is formulated to check for autocorrelation which can either be positive or
negative.
H(0) = First-order autocorrelation does not exist.
H(1) = First-order autocorrelation exists.

Assumptions
1. The Regression model includes the intercept term.
2. The explanatory variables the Xs are non-stochastic , or fixed in repeated sampling.
3. The disturbances Ut are generated by the first order autoregressive scheme
Ut = ρut-1 + εt
4. Error term ut is assumed to be normally distributed
5. The regression models does not include the lagged values of the dependent variables of the
explanatory variables.
The test is inapplicable in models of the following type
Yt = β1 + β2 X2t + β3 X3t +……+ βk Xkt + γYt-1 + ut
The Durbin–Watson statistic, while displayed by many regression analysis programs, is not
applicable in certain situations. For instance, when lagged dependent variables are included in
the explanatory variables, then it is inappropriate to use this test. Durbin's h-test or likelihood
ratio tests, that are valid in large samples, should be used.
Generalized Least Squares for Autocorrelation
Even when autocorrelation is present the OLS coefficients are unbiased, but they are not
necessarily the estimates of the population coefficients that have the smallest variance. the
generalized least squares (GLS) method is used for estimating the regression coefficients with
the smallest variance.
Method to estimate parameters of a linear regression model with autocorrelated errors
 Transforms model to account for autocorrelation structure in errors
 Transformed model satisfies assumptions of classical linear regression model
(homoscedasticity, no autocorrelation)
Applying GLS involves multiple steps
 Estimate autocorrelation structure of errors using residuals from OLS regression
(Durbin-Watson test)
 Transform original data using estimated autocorrelation structure (Cochrane-Orcutt
procedure)
 Estimate regression model using transformed data

Estimation of GLS models


 Obtain transformed data based on estimated autocorrelation structure
 Apply OLS to transformed data to estimate model parameters
 Interpret GLS model parameters
 Coefficients represent change in dependent variable for one-unit change in independent
variable, holding other variables constant
 Interpretation similar to OLS, but coefficients adjusted for autocorrelation in errors
(weather patterns, stock returns)
 Hypothesis tests and confidence intervals for GLS model parameters
 Use standard errors of coefficients from GLS estimation
 Interpret results the same as OLS, but estimates adjusted for autocorrelation (t-tests, p-
values)
Comparing OLS and GLS
o GLS outperforms OLS with autocorrelated errors, providing more accurate and
efficient estimates (economic models, climate data)
o OLS used when errors not autocorrelated, simpler to implement and interpret
(cross-sectional data)
https://www.cbpbu.ac.in/userfiles/file/2020/STUDY_MAT/ECO/1.pdf
https://www.geeksforgeeks.org/durbin-watson-test/
https://epgp.inflibnet.ac.in/epgpdata/uploads/epgp_content/business_economics/08._fundame
ntals_of_econometrics/18._test_for_autocorrelation/et/6776_et_18_et.pdf

You might also like

pFad - Phonifier reborn

Pfad - The Proxy pFad of © 2024 Garber Painting. All rights reserved.

Note: This service is not intended for secure transactions such as banking, social media, email, or purchasing. Use at your own risk. We assume no liability whatsoever for broken pages.


Alternative Proxies:

Alternative Proxy

pFad Proxy

pFad v3 Proxy

pFad v4 Proxy