2005
DOI: 10.1016/j.econlet.2005.05.013
|View full text |Cite
|
Sign up to set email alerts
|

On the effect of deterministic terms on the bias in stable AR models

Abstract: This paper compares the first-order bias approximation for the autoregressive (AR) coefficients in stable AR models in the presence of deterministic terms. It is shown that the bias due to inclusion of an intercept and trend is twice as large as the bias due to an intercept. For the AR(1) model, the accuracy of this approximation is investigated by simulation.

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...
3
1
1

Citation Types

0
6
0

Year Published

2010
2010
2020
2020

Publication Types

Select...
8
1

Relationship

0
9

Authors

Journals

citations
Cited by 18 publications
(6 citation statements)
references
References 8 publications
0
6
0
Order By: Relevance
“…where Z is the matrix of size (n − 1)·3 whose second column contains (n − 1) values equal to 1, and the third column contains the numbers 2 to n and y is a vector of size (n − 1)·1 containing the observations x 2 to x n . The bias-corrected serial correlation coefficient ρ * [45,86] is calculated using the formula mentioned in Equation (27). This value is used in bias-corrected pre-whitening and trend detection studies.…”
Section: Trend-free Pre-whiteningmentioning
confidence: 99%
“…where Z is the matrix of size (n − 1)·3 whose second column contains (n − 1) values equal to 1, and the third column contains the numbers 2 to n and y is a vector of size (n − 1)·1 containing the observations x 2 to x n . The bias-corrected serial correlation coefficient ρ * [45,86] is calculated using the formula mentioned in Equation (27). This value is used in bias-corrected pre-whitening and trend detection studies.…”
Section: Trend-free Pre-whiteningmentioning
confidence: 99%
“…where Z is the matrix of size ( − 1) x 3 whose second column contains ( − 1) values equal to 1, and the third column contains the numbers 2 to and is a vector of size ( − 1) x 1 containing the observations 2 to . Bias corrected serial correlation coefficient ρ * [42,78] is calculated using the formula mentioned in Equation (27). This value is used in bias-corrected pre-whitening and trend detection studies.…”
Section: Trend Free Pre-whiteningmentioning
confidence: 99%
“…However, it is vital to note that the ordinary least squares estimates of 1 are negatively biased [55], and bias corrected 1 ( * ) can be computed by [56] (2) Graphical CRD Approach to Identify Changes. The CRD plot (i.e., the cumulative sum from (A.20) versus the time of the data points) can be used to identify changes in the series over unknown periods as illustrated in Figure 7.…”
Section: (B) Correction Of Variance Inflation Due To Long-term Persismentioning
confidence: 99%