In this article, we investigate the robust optimal design problem for the prediction of response when the fitted regressionmodels are only approximately specified, and observations might be missing completely at rand...
详细信息
In this article, we investigate the robust optimal design problem for the prediction of response when the fitted regressionmodels are only approximately specified, and observations might be missing completely at random. The intuitive idea is as follows: We assume that data are missing at random, and the complete case analysis is applied. To account for the occurrence of missing data, the design criterion we choose is the mean, for the missing indicator, of the averaged (over the design space) mean squared errors of the predictions. To describe the uncertainty in the specification of the real underlying model, we impose a neighborhood structure on the deterministic part of the regression response and maximize, analytically, the Mean of the averaged Mean squared Prediction Errors (MMPE), over the entire neighborhood. The maximized MMPE is the "worst" loss in the neighborhood of the fitted regressionmodel. Minimizing the maximum MMPE over the class of designs, we obtain robust "minimax" designs. The robust designs constructed afford protection from increases in prediction errors resulting from model misspecifications.
Achieving gender well-being and equality is one of the 17 Sustainable Development Goals of the United Nations. A close examination of female livelihood time allocation can reveal gender inequality in livelihood choice...
详细信息
Achieving gender well-being and equality is one of the 17 Sustainable Development Goals of the United Nations. A close examination of female livelihood time allocation can reveal gender inequality in livelihood choices between males and females. Using the feminist political ecology framework, this paper examines how gendered knowledge, roles, and responsibilities influence female livelihood time use in a patriarchal society like Bangladesh. We use a nationally representative household survey data to create multiple linear regression model to understand the association between economic, cultural, and environmental shocks with the total time allocation toward livelihood activities by women. Our results suggest that use of 'Purdah' by Muslim women acts as a negative detrimental factor towards their livelihood time allocation, thus affirming the complex role of culture and gendered economic activities. Women also allocate less time toward livelihood activities during pregnancy and/or breastfeeding. We find that female livelihood time use also depends on their ability to speak in public, their autonomy in livelihood decision processes, and their ownership in business enterprises. This research suggests creating more robust and gender sensitive policies in Bangladesh that can help achieve the United Nation's goals of Sustainable Development.
In order to conduct a study of Wordle's development, firstly, forecasts were made using an ARIMA time series analysis model, and the data were further processed using a weighted moving average method so that the f...
详细信息
Using Eviews software, this paper makes an empirical analysis on the two kinds of factors that affect the housing price of 31 key cities in China: internal direct factors and external indirect factors, in order to rev...
详细信息
Using Eviews software, this paper makes an empirical analysis on the two kinds of factors that affect the housing price of 31 key cities in China: internal direct factors and external indirect factors, in order to reveal the reasons for the high housing price. A multivariate linearregressionmodel was established in which the explanatory variables were land purchase price and residents' disposable income, and the explanatory variables were the average selling price of residential commercial housing. The research shows that the land purchase price has a greater positive impact on the average selling price of residential commercial housing, compared with residents' disposable income although also a positive impact but less impact. (C) 2021 The Authors. Published by Elsevier B.V.
Popularity prediction of online video is widely used in many different scenarios. It can not only help video service providers to schedule video web sites,but also bring considerable profits on investment for both pro...
详细信息
Popularity prediction of online video is widely used in many different scenarios. It can not only help video service providers to schedule video web sites,but also bring considerable profits on investment for both providers and advertisers if popularity of online video is predicted accurately. However, online video popularity prediction still cannot have a satisfactory result, due to the complexity of many crucial factors especially of video distribution network. In this article, we extract seven factors from huge amounts of data about user behavior,establishing a new multiple linear regression model to initially predict online video popularity. After that, a multichannel video popularity dynamic scheduling model is proposed to schedule videos on which channel and what time to be broadcast, according to its popularity predicted by multiple linear regression model, ensuring that maximum the sum value of online video popularity of each channel. Experimental results on dataset obtained from Sohu Video, a video service provider in China, and real-world video flow in Sohu Video demonstrate that the proposed model is robust and has promising performance in predicting online video popularity, which is helpful for video service providers to schedule videos on web sites effectively in the future.
In this paper, we introduce the median-of-means approach for estimating unknown parameters in multiple linear regression model and the regressionmodel with autocorrelated error. The proposed estimators are not only r...
详细信息
In this paper, we introduce the median-of-means approach for estimating unknown parameters in multiple linear regression model and the regressionmodel with autocorrelated error. The proposed estimators are not only robust against the outliers of data but also proved to be consistent. Extensive numerical simulations and one real dataset are presented to show the performances of new estimators.
Suitable agro ecology and tremendous soybean potential of Ethiopia is the key to produce the crop in large-scale and maintaining a steady supply on the market. Although its demand rises quickly for export and local pr...
详细信息
Suitable agro ecology and tremendous soybean potential of Ethiopia is the key to produce the crop in large-scale and maintaining a steady supply on the market. Although its demand rises quickly for export and local processing, the current production status is much below the market demand. The factors influencing the supply of soybeans in Northwestern Ethiopia were the main subject of this study. The sample households were chosen using a multistage sampling technique. In this study, data were gathered from 228 respondents that were randomly drawn. The data were obtained mainly from sampled soybean growers via structured interviews with key informant interviews and focus groups for triangulation. Descriptive statistics and multiple linear regression models were employed to analyze the data including one way ANOVA and t-tests. The findings showed that soybean producers' average productivity was 1.21 tons ha(-1), much below the national average of 2.15 tons ha(-1), due to the sparse usage of improved seed, fertilizer, and other recommended packages. According to the model results, productivity, lagged price, market information, prior experience with soybean farms, cultivated land, weekly extension contacts, education (preparatory school completion), and credit access all had a positive and significant impact on the quantity of soybean market supply. The results showed that soybeans are the most lucrative and important cash crop for producers in the study area. The availability of improved soybean technologies with full recommended packages boosts their productivity and enables them to guarantee sustainable market supply in order to meet the increased market demand.
Goals: The present study was conducted to clarify predictive factors related to procedure time for closure of a mucosal defect following colorectal endoscopic submucosal dissection. Background: To prevent complication...
详细信息
Goals: The present study was conducted to clarify predictive factors related to procedure time for closure of a mucosal defect following colorectal endoscopic submucosal dissection. Background: To prevent complications following a colorectal endoscopic submucosal dissection (ESD) procedure, closure of the resultant mucosal defect is considered to be most effective. However, closure after colorectal ESD is challenging, and technical difficulties can lead to a longer procedure time. Although it is important to clarify predictive factors related to the time needed for effective treatment planning, no such validated data obtained prior to the present study have been reported. Study: Overall, 61 consecutive patients who underwent colorectal ESD for a colorectal neoplasm sized greater than 20 mm were enrolled. Immediately after performing colorectal ESD, closure of the mucosal defect was implemented using a loop clip closure method. Factors with influence on closure procedure time were evaluated using multiplelinearregression analyses. Results: Results obtained with a multiple linear regression model demonstrated that resected specimen size (beta = 0.690, p < 0.01) and colon site (beta = -0.209, p = 0.027) were factors with influence on the closure procedure. Those results were considered relevant to explain the 50.5% variance in time until completion of closure;thus, goodness of fit was considered to be high. Conclusions: Findings obtained in this study were helpful to clarify predictive factors with influence on procedure time. The fit of the model was good, thus allowing for closure performance based on outcome prediction.
This study aims to evaluate the effect of water quality on species richness and population distribution of waterbirds in the Ahlat Marshes. Water quality values of temperature, pH level, dissolved oxygen total dissolv...
详细信息
This study aims to evaluate the effect of water quality on species richness and population distribution of waterbirds in the Ahlat Marshes. Water quality values of temperature, pH level, dissolved oxygen total dissolved solids, salinity, and conductivity were measured. The waterbird species richness was assessed using the Shannon-Wiener and Simpson indices. The results of the prediction model in the Generalized linearmodel showed water temperature to be an important environmental variable to explain the richness of waterbird species. However, a meaningful relationship was not identified to support the relationship between the richness of the waterbird species and other water quality variables. In addition, the multiple linear regression model determined that pH level together with water temperature has a positive effect on the waterbird species in the Ahlat Marshes. The marshes exhibit "low variety" according to the Shannon-Wiener Diversity Index, with the highest value at observation point A6 surrounded by protected dense marshland. At the same observation point, we also found "highest dominance" based on the Simpson Index. During the study, it was recorded 1128 individuals belonging to 15 resident species were identified. The Rallidae waterbird family represented the highest species composition (41.5%). Water temperature, pH level, and DO parameters between the independent variables affected the waterbird abundance by 20%.
This paper focused on the performance monitoring and modeling of a 6.0 kW, 2000 L hybrid direct expansion solar assisted heat pump (DX-SAHP) water heater used for the production of hot water in a university students&#...
详细信息
This paper focused on the performance monitoring and modeling of a 6.0 kW, 2000 L hybrid direct expansion solar assisted heat pump (DX-SAHP) water heater used for the production of hot water in a university students' accommodation with 123 females. The data of total electrical energy consumed, volume of hot water consumed, ambient temperature, relative humidity, and solar irradiance were obtained from the data acquisition systems and analyzed in conjunction with the energy factor (EF) of the system. A multiple linear regression model was developed to predict the EF. The EF of the hybrid DX-SAHP water heater was determined from the summation of the coefficient of performance (COP) of the heat pump unit and the solar fraction (SF) of the solar collectors. The operations of the hybrid energy system were analyzed based on three phases (first phase from 00:00-08:00, second phase from 08:30-18:30, and third phase from 19:00-23:30) over 24 h for the entire monitoring period. The average EF of the hybrid energy system per day during the second phase of operation was 4.38, while the SF and COP were 0.697 and 3.683, respectively. The developed multiple linear regression model for the hybrid DX-SAHP water heater accurately predicted the determined EF.
暂无评论