Abstract
In the present paper, we derive a new multivariate model to fit correlated data, representing a general model class. Our model is an extension of the Growth Curve model (also called generalized multivariate analysis of variance model) by additionally assuming randomness of regression coefficients like in linear mixed models. Each random coefficient has a linear or a bilinear form with respect to explanatory variables. In our model, the covariance matrices of the random coefficients is allowed to be singular. This yields flexible covariance structures of response data but the parameter space includes a boundary, and thus maximum likelihood estimators (MLEs) of the unknown parameters have more complicated forms than the ordinary Growth Curve model. We derive the MLEs in the proposed model by solving an optimization problem, and derive sufficient conditions for consistency of the MLEs. Through simulation studies, we confirmed performance of the MLEs when the sample size and the size of the response variable are large.
Similar content being viewed by others
References
Demidenko, E. (2004). Mixed Models: Theory and Applications. Wiley Series in Probability and Statistics. Wiley-Interscience, New York.
Filipiak, K. and Klein, D. (2017). Estimation of parameters under a generalized growth curve model. Journal of Multivariate Analysis 158, 73–86.
Fujikoshi, Y. and von Rosen, D. (2000). LR tests for random-coefficient covariance structures in an extended growth curve model. Journal of Multivariate Analysis 75, 245–268.
Imori, S. and von Rosen, D. (2015). Covariance components selection in high-dimensional growth curve model with random coefficients. Journal of Multivariate Analysis 136, 86–94.
Ip, W. C., Wu, M. X., Wang, S. G. and Wong, H. (2007). Estimation for parameters of interest in random effects growth curve models. Journal of Multivariate Analysis 98, 317–327.
Kariya, T. (1985). Testing in the Multivariate General Linear Model. Kinokuniya, Tokyo.
Kshirsagar, A. and Smith, W. (1995). Growth Curves, 145. CRC Press, Boca Raton.
Lange, N. and Laird, N. M. (1989). The effect of covariance structure on variance estimation in balanced growth-curve models with random parameters. Journal of the American Statistical Association 84, 241–247.
Lehmann, E. L. (2004). Elements of Large-Sample Theory. Springer Science & Business Media, Berlin.
Li, Z. (2015). Testing for random effects in growth curve models. Communications in Statistics-Theory and Methods 44, 564–572.
Potthoff, R. F. and Roy, S. N. (1964). A generalized multivariate analysis of variance model useful especially for growth curve problems. Biometrika 51, 313–326.
Reinsel, G. (1982). Multivariate repeated-measurement or growth curve models with multivariate random-effects covariance structure. Journal of the American Statistical Association 77, 190–195.
Rutter, C. M. and Elashoff, R. M. (1994). Analysis of longitudinal data: random coefficient regression modelling. Statistics in Medicine 13, 1211–1231.
Schott, J. R. (1985). Multivariate maximum likelihood estimators for the mixed linear model. Sankhyā: The Indian Journal of Statistics, Series B, 179–185.
Siotani, T., Fujikoshi, Y. and Hayakawa, T. (1985). Modern multivariate statistical analysis, a graduate course and handbook. American Sciences Press.
Srivastava, M. S., von Rosen, T. and von Rosen, D. (2009). Estimation and testing in general multivariate linear models with Kronecker product covariance structure. Sankhyā: The Indian Journal of Statistics, Series A, 137–163.
Volaufova, J. and Lamotte, L. R. (2013). A simulation comparison of approximate tests for fixed effects in random coefficients growth curve models. Communications in Statistics-Simulation and Computation 42, 344–359.
von Rosen, D. (1991). The growth curve model: a review. Communications in Statistics-Theory and Methods 20, 2791–2822.
von Rosen, D. (2018). Bilinear Regression Analysis: An Introduction, 220. Springer, Berlin.
Yokoyama, T. (2005). Efficiency of the mle in a multivariate parallel profile model with random effects. Hiroshima Mathematical Journal 35, 2, 197–203.
Author information
Authors and Affiliations
Corresponding author
Additional information
Publisher’s Note
Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.
The authors thank the reviewers for their constructive criticism which has improved the work. Shinpei Imori is supported in part by JSPS KAKENHI Grant Number JP17K12650 and “Funds for the Development of Human Resources in Science and Technology” under MEXT, through the “Home for Innovative Researchers and Academic Knowledge Users (HIRAKU)” consortium. Dietrich von Rosen is supported by the Swedish Research Council (2017-03003). Ryoya Oda is supported by Research Fellowship for Young Scientists from the Japan Society for the Promotion of Science.
Appendices
Appendix: Transformation From General Form to Canonical Form
We present one way of transforming the Growth Curve model to a canonical form. Let PA and PC be defined by
where \(Q_{A}^{\top } A=O_{p-q, q}\), \(Q_{A}^{\top } Q_{A}=I_{p-q}\), CQC = Ok,n−k and \(Q_{C}^{\top } Q_{C}=I_{n-k}\) are fulfilled. Thus,
Moreover, it follows that \(P_{A}^{\top } P_{A}=I_{p}\), \(P_{C}^{\top } P_{C}=I_{n}\) and
Using PA and PC indicates that
where \(\tilde {A}=(I_{q}, O_{q, p-q})^{\top }\), \(\tilde {B}=(A^{\top } A)^{1/2}B(CC^{\top })^{1/2}\), \(\tilde {C}=(I_{k}, O_{k, n-k})\), \(\tilde {D}^{2}=\tilde {A}\tilde {{\varSigma }}\tilde {A}^{\top } + \delta ^{2}I_{p}\), \(\tilde {F}^{2}=\tilde {C}^{\top }\tilde {{\varPsi }}\tilde {C} + I_{n}\), \(\tilde {{\varSigma }}=(A^{\top } A)^{1/2}{\varSigma }(A^{\top } A)^{1/2}\) and \(\tilde {{\varPsi }}=(CC^{\top })^{1/2}{\varPsi }(CC^{\top })^{1/2}\). Hence, by replacing X, A, B, C, Σ and Ψ by \(\tilde {X}\), \(\tilde {A}\), \(\tilde {B}\), \(\tilde {C}\), \(\tilde {{\varSigma }}\) and \(\tilde {{\varPsi }}\), respectively, we obtain the canonical form in Eq. 7.
Appendix B. Proof of Theorem 1
Proof.
Since the fourth term on the right hand side in Eq. 10, \(\delta ^{2}\text {tr}\{{\varPsi }_{*}^{-1}\\(X_{11}-B){\varSigma }_{*}^{-1}(X_{11}-B)^{\top }\}\) is non-negative, the optimum value of B is given by \(\hat {B}=X_{11}\). On the other hand, it follows from Schott (1985) that the maximum point of \(\ell (\hat {B}, {\varSigma }_{*}, {\varPsi }_{*}, \delta ^{2}|X)\) attains when Σ∗ and Ψ∗ satisfy that \(Q_{12}{\varSigma }_{*}Q_{12}^{\top }\) and \(Q_{21}{\varPsi }_{*}Q_{21}^{\top }\) are diagonal matrices, respectively. Hence, we re-parametrize \(Q_{12}{\varSigma }_{*}Q_{12}^{\top }=\text {diag}({\sigma _{1}^{2}}, \ldots , {\sigma _{q}^{2}})\) and \(Q_{21}{\varPsi }_{*}Q_{21}^{\top }=\text {diag}({\psi _{1}^{2}}, \ldots , {\psi _{k}^{2}})\). Moreover, the assumptions Σ∗− δ2Iq ≥ 0 and Ψ∗− δ2Ik ≥ 0 imply \({\sigma _{s}^{2}} \geq \delta ^{2}\) and \({\psi _{t}^{2}} \geq \delta ^{2}\), respectively. Therefore, instead of minimizing (10),
where \(\tilde {\delta }^{2}=\delta ^{-2}\), \(\tilde {\sigma }_{s}^{2} = \sigma _{s}^{-2}\) and \(\tilde {\psi }_{t}^{2} = \psi _{t}^{-2}\). We note that this optimization problem consisting of Eqs. B.1 and B.2 is a convex problem because np − nq − kp is assumed to be positive. Hence, the Karush-Kuhn-Tucker (KKT) conditions are necessary and sufficient conditions for the optimization of Eqs. B.1 given B.2. By using KKT multipliers λσ,s ≥ 0 and λψ,t ≥ 0, along with Eq. 16, we obtain the following KKT conditions:
Let two index sets Iσ and Iψ be defined by
The 2nd − 5th KKT conditions show that
Moreover, it follows from Eq. B.3 and the 1st KKT condition that
where #Iσ and #Iψ are the number of elements in the sets Iσ and Iψ, respectively. Hence, given Iσ and Iψ, estimators of \({\sigma _{s}^{2}}\), \({\psi _{t}^{2}}\) and δ2 equal
Because of Eq. B.2, they have to satisfy that \(\hat {\delta }^{2}(I_{\sigma }, I_{\psi }) \leq \hat {\sigma }_{s}^{2}(I_{\sigma }, I_{\psi })\) and \(\hat {\delta }^{2}(I_{\sigma }, I_{\psi }) \leq \hat {\psi }_{t}^{2}(I_{\sigma }, I_{\psi })\) for all s ∈ Iσ and t ∈ Iψ. Note that if Iσ and Iψ are full sets, then the MLEs of δ2, Σ∗ and Ψ∗ are given by \(\hat {\delta }^{2}(I_{\sigma }, I_{\psi })=\text {tr}(X_{22}X_{22}^{\top })/(np-nq-kp)\), \(\hat {{\varSigma }}_{*}(I_{\sigma }, I_{\psi }) = X_{12}X_{12}^{\top }/n\) and \(\hat {{\varPsi }}_{*}(I_{\sigma }, I_{\psi }) = X_{21}^{\top } X_{21}/p\), respectively.
Next, we want to optimize the index sets Iσ and Iψ. Let ℓ(Iσ,Iψ) be the maximum likelihood function given Iσ and Iψ, where
At first, we fix Iψ, and compare the index sets \(I_{\sigma }^{(1)}=I_{\sigma }^{(0)} \cup \{s_{1}\}\) and \(I_{\sigma }^{(2)} =I_{\sigma }^{(0)}\cup \{s_{2}\}\), where \(I_{\sigma }^{(0)} \subsetneq \{1, \ldots , q\}\) and \(s_{1}, s_{2} \not \in I_{\sigma }^{(0)}\) satisfy s1 < s2. When s1 < s2, it holds that \(\lambda _{s_{1}}^{(12)} \geq \lambda _{s_{2}}^{(12)}\). Thus, it also holds from Eq. B.4 that \(\hat {\delta }^{2}(I_{\sigma }^{(1)}, I_{\psi }) \leq \hat {\delta }^{2}(I_{\sigma }^{(2)}, I_{\psi })\) and \(\hat {\sigma }_{s_{2}}^{2}(I_{\sigma }^{(2)}, I_{\psi }) \leq \hat {\sigma }_{s_{1}}^{2}(I_{\sigma }^{(1)}, I_{\psi })\). Suppose that the estimators based on \(I_{\sigma }^{(2)}\) satisfies (B.2), i.e., \(\hat {\delta }^{2}(I_{\sigma }^{(2)}, I_{\psi }) \leq \hat {\sigma }_{s}^{2}(I_{\sigma }^{(2)}, I_{\psi })\) for all \(s \in I_{\sigma }^{(2)}\). Then, it follows that
Hence, \(\hat {\delta }^{2}(I_{\sigma }^{(1)}, I_{\psi }) \leq \hat {\sigma }_{s}^{2}(I_{\sigma }^{(1)}, I_{\psi })\) is established for all \(s \in I_{\sigma }^{(1)}\), that is, the estimators based on \(I_{\sigma }^{(1)}\) satisfy (B.2).
Now we want to show that \(-2\ell (I_{\sigma }^{(1)}, I_{\psi }) \leq -2\ell (I_{\sigma }^{(2)}, I_{\psi })\), which indicates that \(I_{\sigma }^{(1)}\) is better than \(I_{\sigma }^{(2)}\) in terms of the likelihood function. To simplify notation, we denote
Here, we use the inequality that for a,b,c,d > 0,
Let a = M − n, \(b=K-\lambda _{s_{2}}^{(12)}\), c = n and \(d=\lambda _{s_{2}}^{(12)}\). Because \(b/a=\hat {\delta }^{2}(I_{\sigma }^{(2)}, I_{\psi }) \leq \hat {\sigma }_{s_{2}}^{2}(I_{\sigma }^{(2)}, I_{\psi })=\lambda _{s_{2}}^{(12)}/n=d/c\) is established from Eq. B.6, it follows from Eq. B.7 that
where the last inequality follows from the assumption that s1 < s2. For x ∈ (0,K/n), denote
which satisfies \(f(\lambda _{s_{m}}^{(12)}/n) = -2\ell (I_{\sigma }^{(m)}, I_{\psi })\) for m = 1,2. It is easy to show that f is concave and its critical point is given by x = K/M, which implies that f is monotonically decreasing when x ≥ K/M. This and Eq. B.8 clarify that \(-2\ell (I_{\sigma }^{(1)}, I_{\psi }) \leq -2\ell (I_{\sigma }^{(2)}, I_{\psi })\) when the estimators based on \(I_{\sigma }^{(2)}\) satisfies (B.2).
Hence, there exists a non-negative integer qσ such that the optimum set for Iσ is obtained by \(\hat {I}_{\sigma }\equiv \{1, \ldots , q_{\sigma }\}\). In a similar way, we can show that an optimal index set of Iψ can be expressed by \(\hat {I}_{\psi }\equiv \{1, \ldots , k_{\psi }\}\), where kψ is a non-negative integer. Note that qσ = 0 and kψ = 0 imply \(\hat {I}_{\sigma }\) and \(\hat {I}_{\psi }\) are empty, respectively. Thus, the proof is completed. □
Appendix C. Proof of Theorem 2
Proof
Let \(I_{\sigma }^{(0)}=\{1, \ldots , q_{\sigma }\}\), \(I_{\sigma }^{(1)}=\{1, \ldots , q_{\sigma }+1\}\), \(I_{\psi }^{(0)}=\{1, \ldots , k_{\psi }\}\) and \(I_{\psi }^{(1)}=\{1, \ldots , k_{\psi }+1\}\). At first, we show that \(-2\ell (I_{\sigma }^{(1)}, I_{\psi }^{(0)}) \leq -2\ell (I_{\sigma }^{(0)}, \\I_{\psi }^{(0)})\) when \((q_{\sigma }+1, k_{\psi }) \in {\mathscr{L}}\). Denoting K, L and M as in Appendix B, we can see that
Note that since (qσ + 1,kψ) belongs to \({\mathscr{L}}\), it holds that \(\{K-\lambda _{q_{\sigma }+1}^{(12)}\}/(M-n) = \hat {\delta }^{2}(I_{\sigma }^{(1)}, I_{\psi }^{(0)}) \leq \hat {\sigma }^{2}_{q_{\sigma }+1}(I_{\sigma }^{(1)}, I_{\psi }^{(0)}) = \lambda _{q_{\sigma }+1}^{(12)}/n\). From Eq. B.7 with a = M − n, \(b=K-\lambda _{q_{\sigma }+1}^{(12)}\), c = n and \(d=\lambda _{q_{\sigma }+1}^{(12)}\), it follows that \(K/M = (b+d)/(a+c) \leq d/c = \lambda _{q_{\sigma }+1}^{(12)}/n < K/n\). Here, for x ∈ (0,K/n), denote
Because g is convex and its critical point is given by K/M, we can see that
Likewise, it can be seen that \(-2\ell (I_{\sigma }^{(0)}, I_{\psi }^{(1)}) \leq -2\ell (I_{\sigma }^{(0)}, I_{\psi }^{(0)})\) when \((q_{\sigma }, k_{\psi }+1) \in {\mathscr{L}}\). Hence, the proof is completed. □
Appendix D. Proofs of Lemmas 1 and 2
Proof
Firstly, we prepare the following lemma to show Lemma 1.
Lemma 3.
For any a ≥ 0 and symmetric matrices \(A_{1}, A_{2} \in \mathbb {R}^{m \times m}\) such that A1 and A2 are positive and non-negative definite, respectively, it holds that for all ℓ ∈ 1,…,m,
It follows from some linear algebra (see e.g., Siotani et al. 1985) that for all ℓ ∈ 0,…,m − 1,
where \(F_{\ell } \in \mathbb {R}^{m \times \ell }\). Because eigenvalues of \(A_{1}^{-1}\) are inverse of eigenvalues of A1, which is positive definite, for all \(y \in \mathbb {R}^{m}\),
Note that
Hence, the proof is completed. □
Proof of Lemma 1
Proof
At first, we show \(Pr((q_{\sigma }^{*}, k_{\sigma }^{*}) \in {\mathscr{L}}) \rightarrow 1\) for all asymptotic frameworks (i)–(iii) of the lemma, that is,
We firstly show that for all \(q_{\sigma } \geq q_{\sigma }^{*}\) and \(k_{\psi } \geq k_{\psi }^{*}\), \(\hat {\delta }^{2}(q_{\sigma }, k_{\psi })\) converges to δ2 in probability. By considering the transformation in Appendix A, we can see that
Splitting the error matrix E into four parts like X, i.e.,
then
where \(\tilde {X}=\tilde {A}\tilde {B}\tilde {C}+\tilde {D}E\tilde {F}\). Hence, X12 and X21 can be expressed as
with \(E_{12} \sim N_{q, n-k}(O_{q, n-k}, I_{q}, I_{n-k})\) and \(E_{21} \sim N_{p-q, k}(O_{p-q, k}, I_{p-q}, I_{k})\). Note that \(\tilde {{\varSigma }}=(A^{\top } A)^{1/2}{\varSigma }(A^{\top } A)^{1/2}\) and \(\tilde {{\varPsi }}=(CC^{\top })^{1/2}{\varPsi }(CC^{\top })^{1/2}\). Define
Then, \(\lambda _{q_{\sigma }}^{(12)}\) and \(\lambda _{k_{\psi }}^{(21)}\) can be expressed as follows:
Here, let us fix \(q_{\sigma } > q_{\sigma }^{*}\) and \(k_{\psi } > k_{\psi }^{*}\). Because \(\lambda _{q_{\sigma }}({\varSigma })=\lambda _{k_{\psi }}({\varPsi })=0\), Lemma 3 yields that \(\lambda _{q_{\sigma }}(\tilde {{\varSigma }})=\lambda _{k_{\psi }}(\tilde {{\varPsi }})=0\). Combining this result, Eq. D.2 and Lemma 3, we have
Because \(W_{12}/n \overset {p}{\rightarrow } I_{q}\) as \(n \rightarrow \infty \) and \(W_{21}/p \overset {p}{\rightarrow } I_{k}\) as \(p \rightarrow \infty \), we can see that λ1(W12)/n, \(\lambda _{q}(W_{12})/n \overset {p}{\rightarrow } 1\) and λ1(W21)/p, \(\lambda _{k}(W_{21})/p \overset {p}{\rightarrow } 1\) when n and p go to infinity, respectively. Therefore, Eq. D.3 indicates that
On the other hand, \(\text {tr}(X_{22}X_{22}^{\top })/\delta ^{2} \sim \chi ^{2}_{(n-k)(p-q)}\) and \(\chi ^{2}_{(n-k)(p-q)}/(n-k)(p-q) \overset {p}{\rightarrow } 1\) for (i)–(iii). Hence, it holds that
for (i)–(iii) when \(q_{\sigma } \geq q_{\sigma }^{*}\) and \(k_{\psi } \geq k_{\psi }^{*}\).
Next, we obtain the lower bounds of \(\lambda _{q_{\sigma }^{*}}^{(12)}\) and \(\lambda _{k_{\psi }^{*}}^{(21)}\). Using Lemma 3 and the condition (13), we have
By applying this evaluation and Lemma 3 into Eq. D.2, it follows that
If \(\lambda _{q}(W_{12})/n \geq \{\zeta _{a}\lambda _{q_{\sigma }^{*}}({\varSigma })/2+\delta ^{2}\}/\{p\zeta _{a}\lambda _{q_{\sigma }^{*}}({\varSigma })+\delta ^{2}\}\), then it follows from Eq. D.5 that \(\lambda _{q_{\sigma }^{*}}^{(12)}/n \geq \zeta _{a}\lambda _{q_{\sigma }^{*}}({\varSigma })/2+\delta ^{2}\). Here, we consider the case when \(n \rightarrow \infty \), i.e., (i) and (ii). Because \(\{\zeta _{a}\lambda _{q_{\sigma }^{*}}({\varSigma })/2+\delta ^{2}\}/\{p\zeta _{a}\lambda _{q_{\sigma }^{*}}({\varSigma })+\delta ^{2}\} \leq 1 + \zeta _{a}\lambda _{q_{\sigma }^{*}}({\varSigma })/(2\delta ^{2}) < 1\) and \(\lambda _{q}(W_{12})/n \overset {p}{\rightarrow } 1\), it holds that for (i) and (ii),
Hence, we can see that
for (i) and (ii). In the case (iii), because \(\lambda _{q_{\sigma }^{*}}({\varSigma }) > 0\),
Hence (D.6) holds for (iii). In a similar way, for (i)–(iii), it follows that
Combining (D.4), (D.6) and (D.7), it can be seen that \(Pr((q_{\sigma }^{*}, k_{\psi }^{*}) \in {\mathscr{L}}) \rightarrow 1\) for (i)–(iii). Thus, for all \(q_{\sigma } < q_{\sigma }^{*}\) and \(k_{\psi } < k_{\psi }^{*}\), \(Pr((q_{\sigma }, k_{\psi }) \not \in {\mathscr{L}}_{R}) \rightarrow 1\) for all (i)–(iii).
For the proof of the lemma, it suffices to show that (qσ,kψ), which satisfies \(q_{\sigma } \geq q_{\sigma }^{*}, k_{\psi } < k_{\psi }^{*}\) or \(q_{\sigma } < q_{\sigma }^{*}, k_{\psi } \geq k_{\psi }^{*}\), does not belong to \({\mathscr{L}}_{R}\) with a probability tending to 1. Because of symmetry, we only consider the case \(q_{\sigma } \geq q_{\sigma }^{*}\) and \(k_{\psi } < k_{\psi }^{*}\). Suppose that there exists \((q_{\sigma }, k_{\psi }) \in {\mathscr{L}}\) such that \(q_{\sigma } \geq q_{\sigma }^{*}\) and \(k_{\psi } < k_{\psi }^{*}\). Then, from the definition of \({\mathscr{L}}\), it follows that
On the other hand, because \(k_{\psi } < k_{\psi }^{*}\) is assumed, if \((q_{\sigma }, k_{\psi }^{*}) \in {\mathscr{L}}\), that is,
then \((q_{\sigma }, k_{\psi }) \not \in {\mathscr{L}}_{R}\). From the previous result presented in Eq. D.4, \(\hat {\delta }^{2}(q_{\sigma }, k_{\psi }^{*})\\ \overset {p}{\rightarrow } \delta ^{2}\). This and Eq. D.7 indicate that
for (i)–(iii). Moreover, it follows from Eq. B.7 with \(a=np-nq_{\sigma }-k_{\psi }^{*} p\), \(b=\text {tr}(X_{22}X_{22}^{\top })+{\sum }_{s > q_{\sigma }}\lambda _{s}^{(12)}+{\sum }_{t > k_{\psi }^{*}}\lambda _{t}^{(21)}\), \(c=(k_{\psi }-k_{\psi }^{*})p\) and \(d={\sum }_{k_{\psi } < t \leq k_{\psi }^{*}} \lambda _{t}^{(21)}\) that
Hence, Eq. D.8 implies that \(Pr(\hat {\delta }^{2}(q_{\sigma }, k_{\psi }^{*}) \leq \hat {\delta }^{2}(q_{\sigma }, k_{\psi })) \rightarrow 1\) for (i)–(iii). Since the assumption \((q_{\sigma }, k_{\psi }) \in {\mathscr{L}}\) indicates that \(\hat {\delta }^{2}(q_{\sigma }, k_{\psi }) \leq \lambda _{q_{\sigma }}^{(12)}/n\), the inequality \(\hat {\delta }^{2}(q_{\sigma }, k_{\psi }^{*}) \leq \hat {\delta }^{2}(q_{\sigma }, k_{\psi })\) yields \(\hat {\delta }^{2}(q_{\sigma }, k_{\psi }^{*}) \leq \lambda _{q_{\sigma }}^{(12)}/n\). From Eq. D.8, it follows that
for (i)–(iii). It is established from Eqs. D.8 and D.9 that
for (i)–(iii). Thus, the proof is completed. □
Proof of Lemma 2
Proof
Fix \(q_{\sigma } \geq q_{\sigma }^{*}\) and \(k_{\psi } \geq k_{\psi }^{*}\). Recall that
where Q12 is an orthogonal matrix, which is used to diagonalize: \(n\hat {{\varSigma }}_{*}(q, k)=(\tilde {{\varSigma }}+\delta ^{2}I_{q})^{1/2}W_{12}(\tilde {{\varSigma }}+\delta ^{2}I_{q})^{1/2} = Q_{12}^{\top }\text {diag}\{\lambda _{1}^{(12)}, \ldots , \lambda _{q}^{(12)}\}Q_{12}\). Note that \(\tilde {{\varSigma }}=(A^{\top } A)^{1/2}{\varSigma } (A^{\top } A)^{1/2}\) and \(W_{12} \sim W_{q}(I_{q}, n-k)\) defined in Eq. D.1. Here, \(\hat {{\varSigma }}(q_{\sigma }, k_{\psi })-{\varSigma }\) is evaluated by
Therefore, an upper bound of \(\|\hat {{\varSigma }}(q_{\sigma }, k_{\psi })-{\varSigma }\|_{2}\) can be obtained as follows:
For (i) and (ii), the limits \(\hat {\delta }^{2}(q_{\sigma }, k_{\psi }) \overset {p}{\rightarrow } \delta ^{2}\) (\(q_{\sigma } \geq q_{\sigma }^{*}\), \(k_{\psi } \geq k_{\psi }^{*}\)) and \(\lambda _{s}^{(12)}/n \overset {p}{\rightarrow } \delta ^{2}\) (\(s > q_{\sigma }^{*}\)) have been shown in the proof of Lemma 1. Moreover, because \(W_{12}/n \overset {p}{\rightarrow } I_{q}\), it holds that
Hence, for (i) and (ii), \(\|\hat {{\varSigma }}(q_{\sigma }, k_{\psi })-{\varSigma }\|_{2} \overset {p}{\rightarrow } 0\).
In a similar way to the above presentation, we can verify the convergence of \(\hat {{\varPsi }}(q_{\sigma }, k_{\psi })\) to Ψ for (i) and (iii). Hence, the proof is completed. □
Appendix E. Figures for the Simulation Results
In this section, we show the transition of MSEs of \(\hat {B}\), \(\hat {{\varSigma }}\), \(\hat {{\varPsi }}\) and \(\hat {\delta }^{2}\) in graphs in order to make it clear, where the MSEs by Tables 1, 2 and 3 are given in the simulation study in Section 5. Figures 1, 2, 3 and 4 are the graphs of MSEs of \(\hat {B}\), \(\hat {{\varSigma }}\), \(\hat {{\varPsi }}\) and \(\hat {\delta }^{2}\), respectively, for the cases 1–3 with p = n and p = 20. In all figures, the solid line means that p = n whereas the dashed lines indicates that p = 20. Note that several lines in Figs. 2 and 4 are overlapped. This implies that the value of Ψ does not much affect estimation of Σ and δ2. We can see from the figures that \(\hat {B}\) converges to B except for case 1, \(\hat {{\varPsi }}\) converges to Ψ except for case 1 with p = 20, and \(\hat {{\varSigma }}\) and \(\hat {\delta }\) converge to Σ and δ, respectively, in all cases, with n tending to infinity. These results enhance understanding of the simulation results.
Rights and permissions
About this article
Cite this article
Imori, S., von Rosen, D. & Oda, R. Growth Curve Model with Bilinear Random Coefficients. Sankhya A 84, 477–508 (2022). https://doi.org/10.1007/s13171-020-00204-5
Received:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s13171-020-00204-5