Response surface methodology (RSM) is an important tool for process parameter optimization, robust design and other quality improvement efforts. When the relationship between influential input variables and output res...Response surface methodology (RSM) is an important tool for process parameter optimization, robust design and other quality improvement efforts. When the relationship between influential input variables and output response is very complex, it’s hard to find the real response surface using RSM. In recent years artificial neural network(ANN) has been used in RSM. But the classical ANN does not work well under the constraints of real applications. An algorithm of regression-based ANN(R-ANN) is proposed in this paper, which is a supplement to the classical ANN methodology. It makes network closer to the response surface, so that training time is reduced and robustness is strengthened. The procedure of improving ANN by regressions is described and the comparisons among R-ANN,RSM and classical ANN are computed graphically in three examples. Our research shows that the R-ANN methodology is a good supplement to the RSM and classical ANN methodology, which can yield lower standard error of prediction under conditions that the scope of experiment is rigidly restricted.展开更多
To adapt to the unique demand-supply features of accessory parking lots at passenger transport hubs,a mixed parking demand assignment method based on regression modeling is proposed.First,an optimal model aiming to mi...To adapt to the unique demand-supply features of accessory parking lots at passenger transport hubs,a mixed parking demand assignment method based on regression modeling is proposed.First,an optimal model aiming to minimize total time expenditure is constructed.It incorporates parking search time,walking time,and departure time,focusing on short-term parking features.Then,the information dimensions that the parking lot can obtain are evaluated,and three assignment strategies based on three types of regression models-linear regression(LR),extreme gradient boosting(XGBoost),and multilayer perceptron(MLP)-are proposed.A parking process simulation model is built using the traffic simulation package SUMO to facilitate data collection,model training,and case studies.Finally,the performance of the three strategies is com-pared,revealing that the XGBoost-based strategy performs the best in case parking lots,which reduces time expendi-ture by 29.3%and 37.2%,respectively,compared with the MLP-based strategy and LR-based strategy.This method offers diverse options for practical parking manage-ment.展开更多
This study proposes a regression-based estimation method in difference-in-differences settings in the presence of time-varying covariates-a scenario commonly encountered in applications.We impose only a conditional pa...This study proposes a regression-based estimation method in difference-in-differences settings in the presence of time-varying covariates-a scenario commonly encountered in applications.We impose only a conditional parallel trends assumption with timevarying covariates and plausible assumptions on the conditional expectation functions.We show that a family of causal effect parameters is exactly the coefficient estimators from our proposed regressions even in the presence of staggered treatment timing and treatment effect heterogeneity across cohorts,time periods,and covariates.These parameters can be further aggregated to the dynamic treatment effects and the overall effect of being treated.We establish the corresponding asymptotic properties.Simulation studies suggest that our proposed regression-based estimators successfully outperform in estimating the causal parameters.Finally,we apply this method to evaluate the effect of intrastate bank deregulation on income inequality in the United States in the setting of Beck et al.(2010).We find substantially different results based on our proposed method.展开更多
Although China is experiencing a deterioration in wealth distribution where housing is playing a dominant role,this issue has received scant research attention despite its importance.Combining four rounds of the China...Although China is experiencing a deterioration in wealth distribution where housing is playing a dominant role,this issue has received scant research attention despite its importance.Combining four rounds of the China Household Finance Survey(CHFS)data,this paper measures and discusses wealth inequality in China,with a special emphasis on the contribution of housing.Our analysis reveals that housing is the largest contributor to wealth inequality,responsible for around 70 percent of total wealth inequality,and its contribution has been increasing over time.Our research ejforts have focused on the housing wealth disparity,exploring its composition from alternative perspectives.The results show that housing wealth inequality has also been rising over time and an absolute majority of housing wealth inequality is due to within-group gaps.Finally,we employ Wan's(2004)regression-based decomposition methodology to quantify the contributions of dijferent determinants to housing wealth disparity in China,and to demonstrate serious biases in the conventional approach that is often used to analyze housing wealth inequality.展开更多
文摘Response surface methodology (RSM) is an important tool for process parameter optimization, robust design and other quality improvement efforts. When the relationship between influential input variables and output response is very complex, it’s hard to find the real response surface using RSM. In recent years artificial neural network(ANN) has been used in RSM. But the classical ANN does not work well under the constraints of real applications. An algorithm of regression-based ANN(R-ANN) is proposed in this paper, which is a supplement to the classical ANN methodology. It makes network closer to the response surface, so that training time is reduced and robustness is strengthened. The procedure of improving ANN by regressions is described and the comparisons among R-ANN,RSM and classical ANN are computed graphically in three examples. Our research shows that the R-ANN methodology is a good supplement to the RSM and classical ANN methodology, which can yield lower standard error of prediction under conditions that the scope of experiment is rigidly restricted.
基金The National Natural Science Foundation of China(No.52302388)the Natural Science Foundation of Jiangsu Province(No.BK20230853).
文摘To adapt to the unique demand-supply features of accessory parking lots at passenger transport hubs,a mixed parking demand assignment method based on regression modeling is proposed.First,an optimal model aiming to minimize total time expenditure is constructed.It incorporates parking search time,walking time,and departure time,focusing on short-term parking features.Then,the information dimensions that the parking lot can obtain are evaluated,and three assignment strategies based on three types of regression models-linear regression(LR),extreme gradient boosting(XGBoost),and multilayer perceptron(MLP)-are proposed.A parking process simulation model is built using the traffic simulation package SUMO to facilitate data collection,model training,and case studies.Finally,the performance of the three strategies is com-pared,revealing that the XGBoost-based strategy performs the best in case parking lots,which reduces time expendi-ture by 29.3%and 37.2%,respectively,compared with the MLP-based strategy and LR-based strategy.This method offers diverse options for practical parking manage-ment.
基金supported by the Special Project for Training Young Science and Technology Talents in Early Career Development of Jiangxi Province,China(Grant No.20244BCE52087).
文摘This study proposes a regression-based estimation method in difference-in-differences settings in the presence of time-varying covariates-a scenario commonly encountered in applications.We impose only a conditional parallel trends assumption with timevarying covariates and plausible assumptions on the conditional expectation functions.We show that a family of causal effect parameters is exactly the coefficient estimators from our proposed regressions even in the presence of staggered treatment timing and treatment effect heterogeneity across cohorts,time periods,and covariates.These parameters can be further aggregated to the dynamic treatment effects and the overall effect of being treated.We establish the corresponding asymptotic properties.Simulation studies suggest that our proposed regression-based estimators successfully outperform in estimating the causal parameters.Finally,we apply this method to evaluate the effect of intrastate bank deregulation on income inequality in the United States in the setting of Beck et al.(2010).We find substantially different results based on our proposed method.
基金Financial support from the Natural Science Foundation of China(Nos.71833003 and 72073091)the Higher Education Discipline Innovation Project(111 Project)(No.B16040)is acknowledged.
文摘Although China is experiencing a deterioration in wealth distribution where housing is playing a dominant role,this issue has received scant research attention despite its importance.Combining four rounds of the China Household Finance Survey(CHFS)data,this paper measures and discusses wealth inequality in China,with a special emphasis on the contribution of housing.Our analysis reveals that housing is the largest contributor to wealth inequality,responsible for around 70 percent of total wealth inequality,and its contribution has been increasing over time.Our research ejforts have focused on the housing wealth disparity,exploring its composition from alternative perspectives.The results show that housing wealth inequality has also been rising over time and an absolute majority of housing wealth inequality is due to within-group gaps.Finally,we employ Wan's(2004)regression-based decomposition methodology to quantify the contributions of dijferent determinants to housing wealth disparity in China,and to demonstrate serious biases in the conventional approach that is often used to analyze housing wealth inequality.
