A flexible semiparametric forecasting model for time series

Li, Degui; Linton, Oliver; Lu, Zudi

doi:10.1016/j.jeconom.2015.02.025

Cited by 56 publications

(50 citation statements)

References 30 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Li et al. () first proposed to approximate

m false(Z false)

by a weighted average of nonparametric regression models. Although their resulting semiparametric model average prediction (SMAP) on the response allows nonlinear structure for predictors, each of the models is marginal and completely ignores the presence of other factors.…”

Section: Methods and Estimationmentioning

confidence: 99%

“…Such a model allows discrete as well as continuous covariates to be considered while only continuous terms are allowed under Li et al. ()s approach. On the other hand, the overall combined model can be rewritten as a fully varying‐coefficient model

m false(Z false) = \sum_{j = 1}^{p} a_{j} false(U false) X_{j},

where

a_{j} false(U false) = w_{j} α_{j} false(U false) + \sum_{k \neq j} w_{k} β_{kj}

.…”

Section: Methods and Estimationmentioning

confidence: 99%

“…Li et al. () developed a flexible prediction approach by averaging a set of nonparametric models obtained from local constant smoothing. Their numerical works suggest that the nonparametric averaging approach may perform better than the traditional parametric averaging approach.…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Varying-Coefficient Semiparametric Model Averaging Prediction

Xia

Wong

et al. 2018

Biometrics

View full text Add to dashboard Cite

Forecasting and predictive inference are fundamental data analysis tasks. Most studies employ parametric approaches making strong assumptions about the data generating process. On the other hand, while nonparametric models are applied, it is sometimes found in situations involving low signal to noise ratios or large numbers of covariates that their performance is unsatisfactory. We propose a new varying-coefficient semiparametric model averaging prediction (VC-SMAP) approach to analyze large data sets with abundant covariates. Performance of the procedure is investigated with numerical examples. Even though model averaging has been extensively investigated in the literature, very few authors have considered averaging a set of semiparametric models. Our proposed model averaging approach provides more flexibility than parametric methods, while being more stable and easily implemented than fully multivariate nonparametric varying-coefficient models. We supply numerical evidence to justify the effectiveness of our methodology.

show abstract

“…Li et al. () first proposed to approximate

m false(Z false)

Section: Methods and Estimationmentioning

confidence: 99%

m false(Z false) = \sum_{j = 1}^{p} a_{j} false(U false) X_{j},

where

a_{j} false(U false) = w_{j} α_{j} false(U false) + \sum_{k \neq j} w_{k} β_{kj}

.…”

Section: Methods and Estimationmentioning

confidence: 99%

See 1 more Smart Citation

Varying-Coefficient Semiparametric Model Averaging Prediction

Xia

Wong

et al. 2018

Biometrics

View full text Add to dashboard Cite

show abstract

“…We do not require the sum of weights to equal one. It has been shown that under some mild conditions, the estimated weights without constraint are asymptotically normal (Li, Linton & Lu ). The asymptotic normality of the unconstrained estimated weights is not hard to obtain by their proof in this paper.…”

Section: Model and Methodsmentioning

confidence: 99%

Semiparametric model averaging prediction: a Bayesian approach

Wang

2018

Aus NZ J of Statistics

View full text Add to dashboard Cite

Summary We present a novel model averaging method to construct a prediction function in semi‐parametric form. The weighted sum of candidate semi‐parametric models is taken as a prediction of the mean response. Marginal non‐parametric regression models are approximated by spline basis functions and we apply a Bayesian Monte Carlo approach to fit such models. The optimal model weight parameters are estimated by minimising the least squares criterion with an explicit form. We implement our method in extensive simulation studies and illustrate its use with two real medical data examples. Our methods are demonstrated to be more accurate than both classical parametric model averaging methods and existing semi‐parametric regression models.

show abstract

“…By Theorem 2(ii), we have ∂Q n ŵ n ∂w j = ∂Q n ŵ 0 (n) ∂w j = 0 (B.23) and Φ n w * (n) be the s n × s n matrix whose (j, k)-th component is where ω n is defined in Section 3.1. On the other hand, we can also show that 1 n Φ n w * (n) 27) where Λ n1 and Ω n are defined in Section 3. which can be proved by using the central limit theorem for the stationary α-mixing sequence. The proof of Theorem 2(iii) has thus been completed.…”

Section: Proof Of Theorem 2 (I)mentioning

confidence: 99%

Semiparametric model averaging of ultra-high dimensional time series

Chen¹,

Li²,

Linton³

et al. 2015

Self Cite

View full text Add to dashboard Cite

Standard-Nutzungsbedingungen:Die Dokumente auf EconStor dürfen zu eigenen wissenschaftlichen Zwecken und zum Privatgebrauch gespeichert und kopiert werden.Sie dürfen die Dokumente nicht für öffentliche oder kommerzielle Zwecke vervielfältigen, öffentlich ausstellen, öffentlich zugänglich machen, vertreiben oder anderweitig nutzen.Sofern die Verfasser die Dokumente unter Open-Content-Lizenzen (insbesondere CC-Lizenzen) zur Verfügung gestellt haben sollten, gelten abweichend von diesen Nutzungsbedingungen die in der dort genannten Lizenz gewährten Nutzungsrechte. Terms of use: Documents in AbstractIn this paper, we consider semiparametric model averaging of the nonlinear dynamic time series system where the number of exogenous regressors is ultra large and the number of autoregressors is moderately large. In order to accurately forecast the response variable, we propose two semiparametric approaches of dimension reduction among the exogenous regressors and auto-regressors (lags of the response variable). In the first approach, we introduce a Kernel Sure Independence Screening (KSIS) technique for the nonlinear time series setting which screens out the regressors whose marginal regression (or auto-regression) functions do not make significant contribution to estimating the joint multivariate regression function and thus reduces the dimension of the regressors from a possible exponential rate to a certain polynomial rate, typically smaller than the sample size; then we consider a semiparametric method of Model Averaging MArginal Regression (MAMAR) for the regressors and auto-regressors that survive the screening procedure, and propose a penalised MAMAR method to further select the regressors which have significant effects on estimating the multivariate regression function and predicting the future values of the response variable. In the second approach, we impose an approximate factor modelling structure on the ultra-high dimensional exogenous regressors and use a well-known principal component analysis to estimate the latent common factors, and then

show abstract

A flexible semiparametric forecasting model for time series

Cited by 56 publications

References 30 publications

Varying-Coefficient Semiparametric Model Averaging Prediction

Varying-Coefficient Semiparametric Model Averaging Prediction

Semiparametric model averaging prediction: a Bayesian approach

Semiparametric model averaging of ultra-high dimensional time series

Contact Info

Product

Resources

About