State-Space Modeling of Shape-constrained Functional Time Series
Abstract: Functional time series data frequently appears in econometric analyses, where the functions of interest are subject to some shape constraints, including monotonicity and convexity, as typical of the estimation of the Lorenz curve. This paper proposes a state-space model for time-varying functions to extract trends and serial dependence from functional time series while imposing the shape constraints on the estimated functions. The function of interest is modeled by a convex combination of selected basis functions to satisfy the shape constraints, where the time-varying convex weights on simplex follow the dynamic multi-logit models. To enable posterior computation by an efficient Markov chain Monte Carlo method, a novel data augmentation technique is devised for the complicated likelihood of this model. The proposed method is applied to the estimation of time-varying Lorenz curves, and its utility is illustrated through numerical experiments and analysis of panel data of household incomes in Japan.
- Hierarchical Modeling and Analysis for Spatial Data. CRC Press.
- Bayesian nonparametric forecasting of monotonic functional time series. Electronic Journal of Statistics 10, 3265–3286.
- On gibbs sampling for state space models. Biometrika 81(3), 541–553.
- Chotikapanich, D. and W. E. Griffiths (2002). Estimating lorenz curves using a dirichlet distribution. Journal of Business & Economic Statistics 20(2), 290–295.
- De Jong, P. (1991). The diffuse kalman filter. The Annals of Statistics, 1073–1083.
- The simulation smoother for time series models. Biometrika 82(2), 339–350.
- Faulkner, J. R. and V. N. Minin (2018). Locally adaptive smoothing with markov random fields and shrinkage priors. Bayesian analysis 13(1), 225.
- Frühwirth-Schnatter, S. (1994). Data augmentation and dynamic linear models. Journal of time series analysis 15(2), 183–202.
- Gelfand, A. E. and S. K. Ghosh (1998). Model choice: a minimum posterior predictive loss approach. Biometrika 85(1), 1–11.
- Bayesian analysis of dynamic linear topic models. Bayesian Analysis 14(1), 53–80.
- Inference for income distributions using grouped data. Journal of Business & Economic Statistics 30(4), 563–575.
- Inference for functional data with applications, Volume 200. Springer Science & Business Media.
- Bayesian functional forecasting with locally-autoregressive dependent processes. Bayesian Analysis 14(4), 1121–1141.
- Approximate bayesian computation for lorenz curves from grouped data. Computational Statistics 34, 253–279.
- Flexible bayesian quantile curve fitting with shape restrictions under the dirichlet process mixture of the generalized asymmetric laplace distribution. Canadian Journal of Statistics 49(3), 698–730.
- Bayesian approach to lorenz curve using time series grouped data. Journal of Business & Economic Statistics 40(2), 897–912.
- Introduction to functional data analysis. Chapman and Hall/CRC.
- A bayesian multivariate functional dynamic linear model. Journal of the American Statistical Association 112(518), 733–744.
- Bayesian analysis of shape-restricted functions using gaussian process priors. Statistica Sinica 27, 43–69.
- Lin, L. and D. B. Dunson (2014). Bayesian monotone regression using gaussian process projection. Biometrika 101(2), 303–317.
- Mallick, B. K. and A. E. Gelfand (1994). Generalized linear models with unknown link functions. Biometrika 81(2), 237–245.
- Mehran, F. (1975). Bounds on the gini index based on observed points of the lorenz curve. Journal of the American Statistical Association 70(349), 64–66.
- Locally adaptive bayesian isotonic regression using half shrinkage priors. Scandinavian Journal of Statistics.
- Bayesian inference for logistic models using pólya–gamma latent variables. Journal of the American statistical Association 108(504), 1339–1349.
- Time Series: Modeling, Computation & Inference (2nd ed.). Chapman & Hall/CRC Press.
- Functional forms for estimating the lorenz curve. Econometrica 48(4), 1061.
- Efficient bayesian shape-restricted function estimation with constrained gaussian process priors. Statistics and Computing 30, 839–853.
- A bayesian approach to non-parametric monotone function estimation. Journal of the Royal Statistical Society Series B: Statistical Methodology 71(1), 159–175.
- Nonparametric function estimation subject to monotonicity, convexity and other shape constraints. Journal of Econometrics 161(2), 166–181.
- Functional horseshoe smoothing for functional trend estimation. Statistica Sinica, to appear.
- Wang, X. and J. O. Berger (2016). Estimating shape constrained functions using gaussian processes. SIAM/ASA Journal on Uncertainty Quantification 4(1), 1–25.
Paper Prompts
Sign up for free to create and run prompts on this paper using GPT-5.
Top Community Prompts
Collections
Sign up for free to add this paper to one or more collections.