Abstract
For the slope parameter of the classical errors-in-variables model, existing interval estimations with finite length will have confidence level equal to zero because of the Gleser–Hwang effect. Especially when the reliability ratio is low and the sample size is small, the Gleser–Hwang effect is so serious that it leads to the very liberal coverages and the unacceptable lengths of the existing confidence intervals. In this paper, we obtain two new fiducial intervals for the slope. One is based on a fiducial generalized pivotal quantity and we prove that this interval has the correct asymptotic coverage. The other fiducial interval is based on the method of the generalized fiducial distribution. We also construct these two fiducial intervals for the other parameters of interest of the classical errors-in-variables model and introduce these intervals to a hybrid model. Then, we compare these two fiducial intervals with the existing intervals in terms of empirical coverage and average length. Simulation results show that the two proposed fiducial intervals have better frequency performance. Finally, we provide a real data example to illustrate our approaches.
Similar content being viewed by others
References
Adcock RJ (1877) Note on the method of least squares. Analyst 4:183–184
Adcock RJ (1878) A problem in least squares. Analyst 5:53–54
Buonaccorsi JP (2010) Measurement error: models, methods, and applications. Chapman and Hall/CRC Press, London
Carroll RJ, Ruppert D, Stefanski LA, Crainiceanu CM (2006) Measurement error in nonlinear models: a modern perspective. Chapman and Hall/CRC Press, London
Casella G, Berger RL (2002) Statistical inference. Duxbury, Pacific Grove
Cheng CL, Ness JWV (1999) Statistical regression with measurement error. Arnold, London
Cox DR, Reid N (1987) Parameter orthogonality and approximate conditional inference. J R Stat Soc Ser B 49:1–39
Creasy MA (1956) Confidence limits for the gradient in the linear functional relationship. J R Stat Soc Ser B 18:65–69
Dunn G (2004) Statistical evaluation of measurement errors: design and analysis of reliability studies. Arnold, London
Durrett R (2010) Probability: theory and examples. Cambridge University Press, Cambridge
Francq BG, Govaerts BB (2014) Measurement methods comparison with errors-in-variables regressions. From horizontal to vertical OLS regression, review and new perspectives. Chemometr Intell Lab Syst 134:123–139
Fuller WA (1987) Measurement error models. Wiley, New York
Gelman A, Carlin JB, Stern HS, Rubin DB (2014) Bayesian data analysis. Taylor & Francis, Boca Raton
Gillard J (2010) An overview of linear structural models in errors in variables regression. Revstat Stat J 8:57–80
Gillard J, Iles T (2006) Variance covariance matrices for linear regression with errors in both variables. Cardiff University School of Mathematics Technical Report
Gleser LJ (1987) Confidence intervals for the slope in a linear errors-in-variables regression model. In: Gupta A (ed) Advances in multivariate statistical analysis, vol 5, pp 85–109
Gleser LJ, Hwang JT (1987) The nonexistence of \(100(1-\alpha )\)% confidence sets of finite expected diameter in errors-in-variables and related models. Ann Stat 15:1351–1362
Hannig J, Iyer H, Patterson P (2006) Fiducial generalized confidence intervals. J Am Stat Assoc 101:254–269
Hannig J (2009) On generalized fiducial inference. Stat Sin 19:491–544
Hannig J (2013) Generalized fiducial inference via discretization. Stat Sin 23:489–514
Kendall MG, Stuart A (1979) The advanced theory of statistics. Hafner, New York
Li X, Xu X, Li G (2007) A fiducial argument for generalized p-value. Sci China Ser A 50:957–966
Patefield W (1981) Confidence intervals for the slope of a linear functional relationship. Commun Stat Theory Methods 10:1759–1764
Reiersøl O (1950) Identifiability of a linear relation between variables which are subject to error. Econometrica 18:375–389
Schneeweiss H (1982) Note on creasy’s confidence limits for the gradient in the linear functional relationship. J Multivar Anal 12:155–158
Stefanski LA (2000) Measurement error models. J Am Stat Assoc 95:1353–1358
Strike PW (2014) Statistical methods in laboratory medicine. Butterworth-Heinemann, Oxford
Thompson JR, Carter RL (2007) An overview of normal theory structural measurement error models. Int Stat Rev 75:183–198
Tsai JR (2010) Generalized confidence interval for the slope in linear measurement error model. J Stat Comput Simul 80:927–936
Tsai JR (2013) Interval estimation for fitting straight line when both variables are subject to error. Comput Stat 28:219–240
Tsai JR, Liao CT (2011) Method comparison on confidence interval construction for the slope in a linear measurement model with heteroscedastic errors. J Chemom 25:506–513
Tsui KW, Weerahandi S (1989) Generalized p-values in significance testing of hypotheses in the presence of nuisance parameters. J Am Stat Assoc 84:602–607
Wandler DV, Hannig J (2011) Fiducial inference on the largest mean of a multivariate normal distribution. J Multivar Anal 102:87–104
Wang G (2004) Some bayesian methods in the estimation of parameters in the measurement error models and crossover trial. Ph.D. thesis, University of Cincinnati
Wang G, Sivaganesan S (2013) Objective priors for parameters in a normal linear regression with measurement error. Commun Stat Theory Methods 42:2694–2713
Weerahandi S (1993) Generalized confidence intervals. J Am Stat Assoc 88:899–905
Williams EJ (1959) Regression analysis. Wiley, New York
Williams E (1973) Tests of correlation in multivariate analysis. Bull Int Stat Inst Proc 45:218–232 39th Session
Wong MY (1989) Likelihood estimation of a simple linear regression model when both variables have error. Biometrika 76:141–148
Xu X, Li G (2006) Fiducial inference in the pivotal family of distributions. Sci China Ser A 49:410–432
Acknowledgments
The authors are very thankful to two anonymous referees for their valuable comments and suggestions which resulted in significant improvement of this paper. They also thank the Editor for encouraging comments. This study was supported by the National Natural Science Foundation of China. (No. 11471035).
Author information
Authors and Affiliations
Corresponding author
Appendix 1: The derivation of FGPQ for \(\beta _1\)
Appendix 1: The derivation of FGPQ for \(\beta _1\)
Since the structural equation is \((n-1)\mathbf{T }=\mathbf{KWK }^T\), it turns out that
Let \(\varvec{\eta }\triangleq (\sigma _{xx},\sigma _{xy},\sigma _{yy})^T\), \(\mathbf{S }\triangleq (S_{xx},S_{xy},S_{yy})^T\) and \(\mathbf{E }\triangleq (E_{11},E_{12},E_{22})^T\). On the one hand, we can obtain \(\mathbf{E }\) from the above structural equation, i.e.,
On the other hand, we can derive \(\varvec{\eta }\) from (15), that is
Due to \(\lambda =1\) and (2), we have
Thus,
Combining (15), (16) and (17) with the structural method, we get the FGPQ of \(\beta _1\). Let \((E_{11}^*,E_{12}^*,E_{22}^*)\) be the independent copy of \((E_{11},E_{12},E_{22})\). Replacing \((E_{11},E_{12},E_{22})\) in (16) by \((E_{11}^*,E_{12}^*,E_{22}^*)\), we can get \(\sigma _{xx}^*,\sigma _{xy}^*\) and \(\sigma _{yy}^*\). Note that \(P(\mathscr {\sigma }_{xy}^*=0)=0\), the case of \(\beta _1=0\) in (17) need not to be considered.
1.1 Appendix 2: Proof of the lemma and theorem
Let \(\overset{P}{\longrightarrow }\) denote that a sequence of random variables converges in probability, \(\overset{a.e}{\longrightarrow }\) denote that a sequence of random variables converges almost everywhere, \(\overset{W}{\longrightarrow }\) denote that a sequence of distribution functions converges weakly and \(\overset{L}{\longrightarrow }\) denote that a sequence of random variables converges in law.
Lemma 1
Let \(\{A_n,n=1,\ldots \}\) be a sequence of real random vector and \(A_n\overset{L}{\rightarrow }A\sim N(\mathbf{0 },\varvec{\varOmega })\). \( Z_n\) is a scalar function of \(A_n\) with \(Z_n=f(A_n)\), where f is a continuous function. \(A_n^*\) is an independent copy of \(A_n\), \( Z_n^*=f({A_n^*}') \) and \(\epsilon _n(A_n^*,A_n)\overset{P}{\longrightarrow }0\). Then
where U(0, 1) denotes a uniform distribution on interval (0, 1).
Proof
Because \(A_n\overset{L}{\rightarrow }A\sim N(\mathbf{0 },\varvec{\varOmega })\), so there exist \(F_n\) and F, such that \(A_n\sim F_n\) and \( A\sim F\) with \(F_n \overset{W}{\longrightarrow } F\), where F is the distribution of \(N(\mathbf{0 },\varvec{\varOmega })\). Let \( A_n^* \) and \( A^* \) be the independent copy of \( A_n \) and A , respectively. Then \((A_n^*,A_n)\overset{L}{\longrightarrow }(A^*,A)\), where \( (A_n^*,A_n)\sim F_n\times F_n \) and \( (A^*,A)\sim F\times F \). Together with Skorokhod representation theorem, there exist \(A',~{A^*}',~A_n'\) and \({A_n^*}' \), such that \( ({A_n^*}',A_n')\sim F_n\times F_n\) and \(({A^*}',A')\sim F\times F \) with \(({A_n^*}',A_n') \overset{a.e}{\longrightarrow }({A^*}',A') \). Let \(\mathscr {F}_n\triangleq \sigma (A_1', A_2', \ldots , A_n')\), i.e, the minimum \(\sigma \)-field such that \(A'_1, A'_2, \ldots , A'_n\) are measurable. And let \(Z=f(A),Z^*=f(A^*),Z'=f(A'),{Z^*}'=f({A_n^*}'),Z_n'=f(A_n'),{Z_n^*}'=f({A_n^*}') \), then
where \(\overset{d}{=}\) denotes that both sides of the equality have the same distribution and \(\epsilon _n'({A_n^*}',A_n')=\epsilon _n({A_n^*}',A_n')+Z_n'-Z'-({Z_n^*}'-{Z^*}')\overset{P}{\longrightarrow } 0\). The last but one formula is given by a version of convergence in probability of Theorem 5.5.9 in Durrett (2010) with \(h_n=I({Z^*}'\le Z'+\epsilon _n'({A_n^*}',A_n'))\), \(h=I({Z^*}'\le Z')\) and \(g=1\). It remains to prove that \( h_n\overset{P}{\longrightarrow } h \).
Let \( W={Z^*}'-Z' \), then \( h_n=I(W\le \epsilon _n') \) and \( h=I(W\le 0) \). Because W is a continuous random variable, for any fixed \( b>0 \), there exists a \( c>0 \), such that \( P\{|W|\le c\}<b \). For every \( \delta >0 \),
Let \( b\rightarrow 0 \), and the proof is complete.
Lemma 2
(Fuller 1987, Theorem 1.C.1) Let \(\{\mathbf{Z}_n\}\) be a sequence of independent identically distributed p-dimensional random vectors with mean \(\varvec{\mu }_{\mathbf{Z }}\), covariance matrix \(\varvec{\varSigma }_{\mathbf{ZZ }}\), and finite fourth moments. Let \(\bar{\mathbf{Z }}=n^{-1}\sum _{t=1}^n \mathbf{Z }_t\) be the sample mean, \(m_{\mathbf{ZZ }}=(n-1)^{-1}\sum _{t=1}^n (\mathbf{Z }_t-\bar{\mathbf{Z }})(\mathbf{Z }_t-\bar{\mathbf{Z }})^T\) the sample covariance matrix,
and \(\varvec{\varOmega }=E\{\mathbf{a}_t \mathbf{a}_t^T\}\), where vech denotes half-vectorization. Then
Proof of Theorem
Proof
Because \(P_{\beta _1}(\hat{\beta }_{1_{\alpha /2}}\le \beta _1 \le \hat{\beta }_{1_{1-\alpha /2}})=P_{\beta _1}(\beta _1 \le \hat{\beta }_{1_{1-\alpha /2}})-P_{\beta _1}(\beta _1<\hat{\beta }_{1_{\alpha /2}})\), if we prove that as \(n\rightarrow \infty \),
the assertion follows. Let \(F(r,\mathbf{s })\) be the distribution function of \(\mathscr {R}_{\beta _1}\) conditional on \(\mathbf{S }=\mathbf{s }\). Taking \(F(r,\mathbf{s })\) on both sides of the inequality in (18), that is,
What is left is to show that \(P_{\beta _1}(P(\mathscr {R}_{\beta _1}\le \beta _1|\mathbf{S })\le \gamma )\rightarrow \gamma \), i.e.,
In particular, by (7), we have
Let \(f\triangleq 2\mathscr {R}_{xy}-\beta _1\left[ \sqrt{(\mathscr {R}_{yy}- \mathscr {R}_{xx})^2+4 \mathscr {R}_{xy}^2}-(\mathscr {R}_{yy}-\mathscr {R}_{xx})\right] \). By first order Taylor expansion of f at \(\mathbf{S }=\mathbf{S }^*=\varvec{\eta }=(\sigma _{xx},\sigma _{xy},\sigma _{yy})\) with
where
Therefore, the probability in (19) is equivalent to
where
Thus, (20) is equivalent to
By Lemma 2, we conclude that
where \(\varvec{\varOmega }_{ss}\) is a \(3\times 3\) matrix formed by taking a block of the entries of the last three rows and columns from \(\varvec{\varOmega }\) in Lemma 2 with \(\mathbf{Z }_t=(x_t,~y_t)^T\).
Finally, let \(f(u,v,w)=u+\frac{\sigma _{yy}-\sigma _{xx}}{\sigma _{xy}}v-w\), \(\epsilon _n'(A_n^*,A_n)=\frac{\sqrt{n}\epsilon _n}{C}\overset{P}{\longrightarrow }0\). By Lemma 1, we see at once that (21) converges to U(0, 1) in law.
Rights and permissions
About this article
Cite this article
Yan, L., Wang, R. & Xu, X. Fiducial inference in the classical errors-in-variables model. Metrika 80, 93–114 (2017). https://doi.org/10.1007/s00184-016-0593-9
Received:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s00184-016-0593-9