Nonlinear Time Series: Computations and Applications 2012View this Special Issue
Research Article | Open Access
Lei Song, Hongchang Hu, Xiaosheng Cheng, "Hypothesis Testing in Generalized Linear Models with Functional Coefficient Autoregressive Processes", Mathematical Problems in Engineering, vol. 2012, Article ID 862398, 19 pages, 2012. https://doi.org/10.1155/2012/862398
Hypothesis Testing in Generalized Linear Models with Functional Coefficient Autoregressive Processes
The paper studies the hypothesis testing in generalized linear models with functional coefficient autoregressive (FCA) processes. The quasi-maximum likelihood (QML) estimators are given, which extend those estimators of Hu (2010) and Maller (2003). Asymptotic chi-squares distributions of pseudo likelihood ratio (LR) statistics are investigated.
Consider the following generalized linear model: where is -dimensional unknown parameter, are functional coefficient autoregressive processes given by where are independent and identically distributed random variable errors with zero mean and finite variance , is a one-dimensional unknown parameter, and is a real valued function defined on a compact set which contains the true value as an inner point and is a subset of . The values of and are unknown. is a known continuous differentiable function.
Model (1.1) includes many special cases, such as an ordinary regression model (when; see [1–7]), an ordinary generalized regression model (when ; see [8–13]), a linear regression model with constant coefficient autoregressive processes (when , ; see [14–16]), time-dependent and function coefficient autoregressive processes (when ; see ), constant coefficient autoregressive processes (when , ; see [18–20]), time-dependent or time-varying autoregressive processes (when ; see [21–23]), and a linear regression model with functional coefficient autoregressive processes (when; see ). Many authors have discussed some special cases of models (1.1) and (1.2) (see [1–24]). However, few people investigate the model (1.1) with (1.2). This paper studies the model (1.1) with (1.2). The organization of this paper is as follows. In Section 2, some estimators are given by the quasi-maximum likelihood method. In Section 3, the main results are investigated. The proofs of the main results are presented in Section 4, with the conclusions and some open problems in Section 5.
2. The Quasi-Maximum Likelihood Estimate
Write the “true” model as where . Define, and by (2.2), we have Thus is measurable with respect to the field generated by, and
Assume at first that the are i.i.d. , we get the log-likelihood of conditional on given by At this stage we drop the normality assumption, but still maximize (2.5) to obtain QML estimators, denoted by. The estimating equations for unknown parameters in (2.5) may be written as Thus, satisfy the following estimation equations where
Remark 2.1. If , then the above equations become the same as Hu’s (see ). If ,, then the above equations become the same as Maller’s (see ). Thus we extend those QML estimators of Hu  and Maller .
For ease of exposition, we will introduce the following notations, which will be used later in the paper. Let vector . Define By (2.7), we have where the * indicates that the elements are filled in by symmetry, Because and are mutually independent, we have where By (2.8) (2.7) and, we have
3. Statement of Main Results
In the section pseudo likelihood ratio (LR) statistics for various hypothesis tests of interest are derived. We consider the following hypothesis: When the parameter space is restricted by a hypothesis , letbe the corresponding QML estimators of , and let be minus twice the log-likelihood, evaluated at the fitted parameters. Also let be the “deviance” statistic for testing against. From (2.5) and (2.8), and similarly
In order to obtain our results, we give some sufficient conditions as follows.(A1) is positive definite for sufficiently large and where and denotes the maximum in absolute value of the eigenvalues of a symmetric matrix.(A2) There is a constant such that(A3)andexist and are bounded, andis twice continuously differentiable, , .
4. Proof of Theorem
To prove Theorem 3.1, we first introduce the following lemmas.
Lemma 4.1. Suppose that (A1)–(A3) hold. Then, for all , where
Lemma 4.2. Suppose that (A1)–(A3) hold. Then , and where are on the line ofand.
Proof of Theorem 3.1. Note that and are nonsingular. By Taylor’s expansion, we have
where for some . Since , also . By (4.1), we have
Thus is a symmetric matrix with. By (4.5) and (4.6), we have
Letdenoteand, respectively. By (4.7), we have
By (2.15), (4.2) and (4.8), we get
By (2.1), (2.11) and (4.12), we have
By (4.13) and (2.10), we have
By (4.13), we have
By (4.15), we have
By (4.14) and (4.16), we have
By (4.15), we have
Thus, by (4.17) and (4.18), we have
Since , we have
Thus, by (4.17), (4.20) and mean value theorem, we have
where for some .
It is easy to know that By Lemma 4.2 and (4.22), we have Hence, by (4.11), we have By (4.24), we have By Lemma 4.2, we have Now, we prove (3.8). By (4.12), we have Note that From (4.28), we have By (2.8) and (2.10), we have From (4.30), we obtain that By (4.29), (4.31) and Lemma 4.2, we have By (3.3)–(3.5), we have Under the , and by (4.26), (4.32) and (4.33), we have It is easily proven that Thus, by (4.33)–(4.35), we finish the proof of (3.8).
Next we prove (3.9). Under, , and , we have Hence By (2.8), (2.10), we have From (4.38), we obtain, Thus, by (4.37), (4.39) and Lemma 4.2, we have By (3.3)–(3.5), we have Under the, by (4.26), (4.40), and (4.41), we obtain Thus, by (4.35), (4.42), (3.9) holds.
Finally, we prove (3.10). Under, we have Thus By (2.8) and (2.10), we have From (4.45), we obtain By (4.44), (4.46) and Lemma 4.2, we have