Semiparametric lag dependent functions
(2013) In Applied Mathematical Sciences 7(12). p.551-566- Abstract
- This paper introduces a suite of tests for linear and general non-
linear serial dependence. The problem is complex as the number of
variations of realistic non-linear alternatives is very large.
The alternative model is dened in terms of penalized truncated
polynomial splines, making the approximation capable of accurately
approximating a large class of linear and non-linear processes.
The asymptotic distribution for the test statistic is derived, and we
show using Monte Carlo simulations that one test is equivalent to the
Ljung-Box test, other linear tests corresponds to ordinary or partial
sample autocorrelation while the non-linear versions are capable of... (More) - This paper introduces a suite of tests for linear and general non-
linear serial dependence. The problem is complex as the number of
variations of realistic non-linear alternatives is very large.
The alternative model is dened in terms of penalized truncated
polynomial splines, making the approximation capable of accurately
approximating a large class of linear and non-linear processes.
The asymptotic distribution for the test statistic is derived, and we
show using Monte Carlo simulations that one test is equivalent to the
Ljung-Box test, other linear tests corresponds to ordinary or partial
sample autocorrelation while the non-linear versions are capable of de-
tecting non-linear eects, even when other tests fail to do so. (Less)
Please use this url to cite or link to this publication:
https://lup.lub.lu.se/record/3232990
- author
- Lindström, Erik LU
- organization
- publishing date
- 2013
- type
- Contribution to journal
- publication status
- published
- subject
- keywords
- time series, hypothesis testing, Stationary processes
- in
- Applied Mathematical Sciences
- volume
- 7
- issue
- 12
- pages
- 551 - 566
- publisher
- Hikari Ltd
- external identifiers
-
- scopus:84871703698
- ISSN
- 1314-7552
- language
- English
- LU publication?
- yes
- id
- fb8191f0-fd07-4fe0-b467-196d687004e3 (old id 3232990)
- alternative location
- http://www.m-hikari.com/ams/ams-2013/ams-9-12-2013/lindstromAMS9-12-2013.pdf
- date added to LUP
- 2016-04-01 10:31:09
- date last changed
- 2022-01-25 23:59:56
@article{fb8191f0-fd07-4fe0-b467-196d687004e3, abstract = {{This paper introduces a suite of tests for linear and general non-<br/><br> linear serial dependence. The problem is complex as the number of<br/><br> variations of realistic non-linear alternatives is very large.<br/><br> The alternative model is dened in terms of penalized truncated<br/><br> polynomial splines, making the approximation capable of accurately<br/><br> approximating a large class of linear and non-linear processes.<br/><br> The asymptotic distribution for the test statistic is derived, and we<br/><br> show using Monte Carlo simulations that one test is equivalent to the<br/><br> Ljung-Box test, other linear tests corresponds to ordinary or partial<br/><br> sample autocorrelation while the non-linear versions are capable of de-<br/><br> tecting non-linear eects, even when other tests fail to do so.}}, author = {{Lindström, Erik}}, issn = {{1314-7552}}, keywords = {{time series; hypothesis testing; Stationary processes}}, language = {{eng}}, number = {{12}}, pages = {{551--566}}, publisher = {{Hikari Ltd}}, series = {{Applied Mathematical Sciences}}, title = {{Semiparametric lag dependent functions}}, url = {{http://www.m-hikari.com/ams/ams-2013/ams-9-12-2013/lindstromAMS9-12-2013.pdf}}, volume = {{7}}, year = {{2013}}, }