2018
DOI: 10.3150/17-bej928
|View full text |Cite
|
Sign up to set email alerts
|

Schwarz type model comparison for LAQ models

Abstract: For model-specification purpose, we study asymptotic behavior of the marginal quasi-log likelihood associated with a family of locally asymptotically quadratic (LAQ) statistical experiments. Our result entails a far-reaching extension of applicable scope of the classical approximate Bayesian model comparison due to Schwarz, with frequentist-view theoretical foundation. In particular, the proposed statistics can deal with both ergodic and non-ergodic stochastic-process models, where the corresponding M -estimat… Show more

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...
3
2

Citation Types

0
27
0

Year Published

2018
2018
2024
2024

Publication Types

Select...
7

Relationship

1
6

Authors

Journals

citations
Cited by 25 publications
(27 citation statements)
references
References 46 publications
0
27
0
Order By: Relevance
“…The proof given in Section 5.5 goes through as in [4] under essentially weaker conditions due to Theorem A.1.…”
Section: Consistent Model Selectionmentioning
confidence: 99%
See 2 more Smart Citations
“…The proof given in Section 5.5 goes through as in [4] under essentially weaker conditions due to Theorem A.1.…”
Section: Consistent Model Selectionmentioning
confidence: 99%
“…We here consider consistent model selection by the (quasi-)Bayesian information criterion ((Q)BIC for short) studied in [4]; previously, the correct form of the classical Schwarz's BIC for ergodic diffusion observed at high frequency was given in [4, Theorems 3.7, 4.5, and 4.6] when h is given a priori.…”
Section: Consistent Model Selectionmentioning
confidence: 99%
See 1 more Smart Citation
“…[14] proposes likelihood-ratio-type test statistic for discretely observed ergodic diffusions to examine parametric hypotheses such as [6] and shows the convergence in law of test statistics and the consistency of the test. As another approach, [18] researches contrast-based information criterion for ergodic diffusion processes with discretised observation scheme (see also [8] and [3]). These instruments to examine goodness-of-fit are important to see whether we are motivated to use the flexible modelling with stochastic differential equations.…”
Section: Introductionmentioning
confidence: 99%
“…Hence, Kaino et al (2017) and Kaino and Uchida (2018a,b) propose hybrid multi-step estimation procedure for diffusion processes where initial values in optimisation are derived from Bayes type estimation with reduced sample sizes and the sequential optimisation with these initial values is implemented, which inherits the idea of hybrid multi-step estimation for diffusion processes with full sample sizes in Kamatani and Uchida (2015) (see also Kutoyants, 2017). In this research, we also consider hybrid multi-step estimation and apply the idea into inference problem, in particular, PLDI for the quasi likelihood functions and the convergence of moments of estimators for discretely and noisily observed ergodic diffusion processes since PLDI and convergence of moment of estimators are key tools to show the mathematical validity of information criteria for model selection problems (see Uchida, 2010;Fujii and Uchida, 2014;Eguchi and Masuda, 2018).…”
Section: Introductionmentioning
confidence: 99%