scholarly journals Robust Regression Models for Load Forecasting

2019 ◽  
Vol 10 (5) ◽  
pp. 5397-5404 ◽  
Author(s):  
Jian Luo ◽  
Tao Hong ◽  
Shu-Cherng Fang
Author(s):  
Jieying Jiao ◽  
Zefan Tang ◽  
Peng Zhang ◽  
Meng Yue ◽  
Jun Yan

2018 ◽  
Vol 52 (2) ◽  
pp. 233-264 ◽  
Author(s):  
Jiwon Jung ◽  
Barry Bozeman ◽  
Monica Gaughan

When employees fear punishment for taking initiative, organizations are likely to be less effective and, equally important, such fear extracts a human toll, often contributing to a variety of manifestations of unhappiness including diminished health. We focus on two different types of fears of punishment, fear of being punished for presenting new ideas and for bending organizational rules. Employing Mechanical Turk crowdsourcing data from 1,189 participants in the 2015 survey of National Administrative Studies Project Citizen, we test hypotheses about possible differences in fear of punishment according to sector (government vs. business), general risk propensity, views about coworkers, job clarity, gender, and whether respondents are members of an underrepresented racial or ethnic minority. Using nested robust regression models, we find that the two different types of fear of punishment are predicted by different variables. Sector has no bearing on fear of punishment for presenting new ideas but is a major predictor of differences in fear of bending the rules, with government employees being more fearful. While gender has no significant effects, being a racial minority is closely related to fear of presenting new ideas. Having a negative view of one’s fellow workers, particularly one’s supervisor, is associated with greater fear of punishment from both rule bending and presenting new ideas. Those with a clear organization mission and job clarity are less likely to be afraid of punishment for proposing innovative ideas but not necessarily for bending rules. We suggest that the results have implications for managerial practice and human resource reform.


2020 ◽  
Vol 16 (5) ◽  
pp. 155014772092163
Author(s):  
Xianfei Yang ◽  
Xiang Yu ◽  
Hui Lu

Power load forecasting is an important guarantee of safe, stable, and economic operation of power systems. It is appropriate to use interval data to represent fuzzy information in power load forecasting. The dual possibilistic regression models approximate the observed interval data from the outside and inside directions, respectively, which can estimate the inherent uncertainty existing in the given fuzzy phenomenon well. In this article, efficient dual possibilistic regression models of support vector machines based on solving a group of quadratic programming problems are proposed. And each quadratic programming problem containing fewer optimization variables makes the training speed of the proposed approach fast. Compared with other interval regression approaches based on support vector machines, such as quadratic loss support vector machine approach and two smaller quadratic programming problem support vector machine approach, the proposed approach is more efficient on several artificial datasets and power load dataset.


Sign in / Sign up

Export Citation Format

Share Document