1992
DOI: 10.2307/2109675
|View full text |Cite
|
Sign up to set email alerts
|

The Durbin-Watson Test for Autocorrelation in Nonlinear Models

Abstract: This paper shows a simple method of approximating the exact distribution of the Durbin-Watson Test Statistic for first-order autocorrelation in a nonlinear model. The proposed Approximate Nonlinear Durbin-Watson (A.N.D.) test has good size and power when compared to alternatives.

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...
2
1
1

Citation Types

0
55
0
3

Year Published

1998
1998
2024
2024

Publication Types

Select...
7
2

Relationship

0
9

Authors

Journals

citations
Cited by 95 publications
(58 citation statements)
references
References 2 publications
0
55
0
3
Order By: Relevance
“…1 5 According to White (1992) the Wald statistic is given by: W = n 1 /2´r where n corresponds to the number of observations and r represents the autocorrelation coe cient. and Wales (1987) and Kohli (1991Kohli ( , 1994, the failure of curvature conditions is common in empirical estimations of¯exible functional forms.…”
Section: I Data Estimati On and Curvature Condi Tionsmentioning
confidence: 99%
“…1 5 According to White (1992) the Wald statistic is given by: W = n 1 /2´r where n corresponds to the number of observations and r represents the autocorrelation coe cient. and Wales (1987) and Kohli (1991Kohli ( , 1994, the failure of curvature conditions is common in empirical estimations of¯exible functional forms.…”
Section: I Data Estimati On and Curvature Condi Tionsmentioning
confidence: 99%
“…In order to test the AR(1) specification against the alternative of an AR(2) specification, we employed the Godfrey Lagrange multiplier test for non-linear regression models (Godfrey 1988, p. 117;White 1992). This test statistic has a critical value of 6.635, which implies acceptance of the AR(1) process at a 1 percent level for all our specifications (see Table 3).…”
mentioning
confidence: 99%
“…where r m is the lag1 residual autocorrelation (White 1992), where lag1 defines the NDVI measurements in the time-series separated by 1 day. Therefore, the criterion for lambda selection was the Durbin-Watson test, which was used to verify that the smoothed line described sufficiently the information from the original time-series, and thus would not influence the subsequent analyses.…”
Section: Preparation Of Ndvi Time-seriesmentioning
confidence: 99%