Communications for Statistical Applications and Methods最新文献

Statistical network analysis for epilepsy MEG data 癫痫 MEG 数据的统计网络分析

IF 0.4

Communications for Statistical Applications and Methods Pub Date : 2023-11-30 DOI: 10.29220/csam.2023.30.6.561

Haeji Lee, Chun Kee Chung, Jaehee Kim

引用次数: 0

Two-stage imputation method to handle missing data for categorical response variable 处理分类响应变量缺失数据的两阶段估算法

IF 0.4

Communications for Statistical Applications and Methods Pub Date : 2023-11-30 DOI: 10.29220/csam.2023.30.6.577

Jong-Min Kim, Kee-Jae Lee, Seung-Joo Lee

{"title":"Two-stage imputation method to handle missing data for categorical response variable","authors":"Jong-Min Kim, Kee-Jae Lee, Seung-Joo Lee","doi":"10.29220/csam.2023.30.6.577","DOIUrl":"https://doi.org/10.29220/csam.2023.30.6.577","url":null,"abstract":"Conventional categorical data imputation techniques, such as mode imputation, often encounter issues related to overestimation. If the variable has too many categories, multinomial logistic regression imputation method may be impossible due to computational limitations. To rectify these limitations, we propose a two-stage imputation method. During the ﬁrst stage, we utilize the Boruta variable selection method on the complete dataset to identify signiﬁcant variables for the target categorical variable. Then, in the second stage, we use the important variables for the target categorical variable for logistic regression to impute missing data in binary variables, polytomous regression to impute missing data in categorical variables, and predictive mean matching to impute missing data in quantitative variables. Through analysis of both asymmetric and non-normal simulated and real data, we demonstrate that the two-stage imputation method outperforms imputation methods lacking variable selection, as evidenced by accuracy measures. During the analysis of real survey data, we also demonstrate that our suggested two-stage imputation method surpasses the current imputation approach in terms of accuracy.","PeriodicalId":44931,"journal":{"name":"Communications for Statistical Applications and Methods","volume":"150 1","pages":""},"PeriodicalIF":0.4,"publicationDate":"2023-11-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"139202273","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Counterfactual image generation by disentangling data attributes with deep generative models 通过深度生成模型分解数据属性生成反事实图像

IF 0.4

Communications for Statistical Applications and Methods Pub Date : 2023-11-30 DOI: 10.29220/csam.2023.30.6.589

Jieon Lim, Weonyoung Joo

{"title":"Counterfactual image generation by disentangling data attributes with deep generative models","authors":"Jieon Lim, Weonyoung Joo","doi":"10.29220/csam.2023.30.6.589","DOIUrl":"https://doi.org/10.29220/csam.2023.30.6.589","url":null,"abstract":"Deep generative models target to infer the underlying true data distribution, and it leads to a huge success in generating fake-but-realistic data. Regarding such a perspective, the data attributes can be a crucial factor in the data generation process since non-existent counterfactual samples can be generated by altering certain factors. For example, we can generate new portrait images by ﬂipping the gender attribute or altering the hair color attributes. This paper proposes counterfactual disentangled variational autoencoder generative adversarial networks (CDVAE-GAN), specialized for data attribute level counterfactual data generation. The structure of the proposed CDVAE-GAN consists of variational autoencoders and generative adversarial networks. Speciﬁcally, we adopt a Gaussian variational autoencoder to extract low-dimensional disentangled data features and auxiliary Bernoulli latent variables to model the data attributes separately. Also, we utilize a generative adversarial network to generate data with high ﬁdelity. By enjoying the beneﬁts of the variational autoencoder with the additional Bernoulli latent variables and the generative adversarial network, the proposed CDVAE-GAN can control the data attributes, and it enables producing counterfactual data. Our experimental result on the CelebA dataset qualitatively shows that the generated samples from CDVAE-GAN are realistic. Also, the quantitative results support that the proposed model can produce data that can deceive other machine learning classiﬁers with the altered data attributes.","PeriodicalId":44931,"journal":{"name":"Communications for Statistical Applications and Methods","volume":"55 6","pages":""},"PeriodicalIF":0.4,"publicationDate":"2023-11-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"139205791","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Identification of indirect effects in the two-condition within-subject mediation model and its implementation using SEM 双条件主体内中介模型中间接效应的识别及其利用 SEM 的实施

IF 0.4

Communications for Statistical Applications and Methods Pub Date : 2023-11-30 DOI: 10.29220/csam.2023.30.6.631

Eujin Park, Chan Park

引用次数: 0

Robust extreme quantile estimation for Pareto-type tails through an exponential regression model 通过指数回归模型对帕累托型尾部进行稳健的极值量值估计

IF 0.4

Communications for Statistical Applications and Methods Pub Date : 2023-11-30 DOI: 10.29220/csam.2023.30.6.531

R. Minkah, Tertius de Wet, Abhik Ghosh, H. Yousof

引用次数: 0

Influence diagnostics for skew-t censored linear regression models 偏t删减线性回归模型的影响诊断

IF 0.4

Communications for Statistical Applications and Methods Pub Date : 2023-11-30 DOI: 10.29220/csam.2023.30.6.605

Marcos S Oliveira, Daniela C. R. Oliveira, V. H. Lachos

引用次数: 0

Motion classification using distributional features of 3D skeleton data 利用三维骨骼数据的分布特征进行运动分类

IF 0.4

Communications for Statistical Applications and Methods Pub Date : 2023-11-30 DOI: 10.29220/csam.2023.30.6.551

Woohyun Kim, Daeun Kim, Kyoung Shin Park, Sungim Lee

引用次数: 0

Prediction of PM10 concentration in Seoul, Korea using Bayesian network 利用贝叶斯网络预测韩国首尔地区PM10浓度

Communications for Statistical Applications and Methods Pub Date : 2023-09-30 DOI: 10.29220/csam.2023.30.5.517

Minjoo Jo, Rosy Oh, Man-Suk Oh

引用次数: 0

Utilizing a unit Gompertz distorted copula to model dependence in anthropometric data 利用单位冈珀兹扭曲联结来模拟人体测量数据的依赖性

Communications for Statistical Applications and Methods Pub Date : 2023-09-30 DOI: 10.29220/csam.2023.30.5.467

Fadal Abdullah Ali Aldhufairi

引用次数: 0

Comparative analysis of model performance for predicting the customer of cafeteria using unstructured data 利用非结构化数据预测自助餐厅顾客的模型性能比较分析

Communications for Statistical Applications and Methods Pub Date : 2023-09-30 DOI: 10.29220/csam.2023.30.5.485

Seungsik Kim, Nami Gu, Jeongin Moon, Keunwook Kim, Yeongeun Hwang, Kyeongjun Lee

引用次数: 0