Varying-Coefficient Semiparametric Model Averaging Prediction

Abstract

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.

Improving Stock Price Prediction Using Combining Forecasts Methods

“…Therefore, constituent ARIMA method contributed more time to the proposed method. Thus, the proposed or other EMDbased similar methods can further be improved using a suitable and effective combination of parametric, nonparametric and semi-parametric methods (e.g., as presented by [25]) with EMD components. However, this study aimed to find an EMD-based better forecasting method which approach can further be extended to develop hybrid methods that will be optimized with forecast accuracy and computation time.…”

Jackknife model averaging for high‐dimensional quantile regression

“…One example is Schorning et al (2016), who applied FMA in selecting suitable dose-response relationships to decide subsequent dose choices. More recently, Li et al (2018) applied FMA within the framework of the varying coefficient partially linear model to analyze two biomedical data sets on body mass index and the disease severity of patients based on a skin score.…”

Semiparametric Model Averaging Prediction for Lifetime Data via Hazards Regression

“…Li et al. (2018) developed a flexible varying‐coefficient model averaging in which each candidate has a nonlinear dynamic interactive structure. The correlation structure in generalized estimating equations was addressed in Fang et al.…”

“…Huang and Li (2018) considered local linear estimation for each submodel and extended earlier results to panel data. Li et al (2018) developed a flexible varying-coefficient model averaging in which each candidate has a nonlinear dynamic interactive structure. The correlation structure in generalized estimating equations was addressed in Fang et al (2019).…”