Optimal subsample selection for massive logistic regression with distributed data

Zuo, Lulu; Zhang, Haixiang; Wang, Haiying; Sun, Liuquan

doi:10.1007/s00180-021-01089-0

Cited by 14 publications

(5 citation statements)

References 16 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Shi et al (2019) studied the distributed logistic regression based on the classical ADMM algorithm (Boyd et al, 2011). Zuo et al (2021) proposed a distributed subsampling procedure to approximate the maximum likelihood estimator. A cost-sensitive algorithm was developed by Wang et al (2016) for the linear SVM problem.…”

Section: Introductionmentioning

confidence: 99%

Distributed Logistic Regression for Massive Data with Rare Events

Li¹,

Zhu²,

Wang³

2025

STAT SINICA

View full text Add to dashboard Cite

Large-scale rare events data are commonly encountered in practice. To tackle the massive rare events data, we propose a novel distributed estimation method for logistic regression in a distributed system. For a distributed framework, we face the following two challenges. The first challenge is how to distribute the data. In this regard, two different distribution strategies (i.e., the RANDOM strategy and the COPY strategy) are investigated. The second challenge is how to select an appropriate type of objective function so that the best asymptotic efficiency can be achieved. Then, the under-sampled (US) and inverse probability weighted (IPW) types of objective functions are considered. Our results suggest that the COPY strategy together with the IPW objective function is the best solution for distributed logistic regression with rare events. The finite sample performance of the distributed methods is demonstrated by simulation studies and a real-world Sweden Traffic Sign dataset.

show abstract

Section: Introductionmentioning

confidence: 99%

Distributed Logistic Regression for Massive Data with Rare Events

Li¹,

Zhu²,

Wang³

2025

STAT SINICA

View full text Add to dashboard Cite

show abstract

“…In addition, a multiple logistic regression model was used to examine the relationship between anxiety and other covariates [18,19]. Model coefficients were calculated using several methods, including the Bayesian, the maximum likelihood, and the least squares method [20][21][22][23]. Bhandari et al [24] used logistic regression analysis to predict the risk of mortality in patients with COVID-19 based on routine hematologic parameters.…”

Section: Introductionmentioning

confidence: 99%

The Role of Vaccination and Face Mask Wearing on COVID-19 Infection and Hospitalization: A Cross-Sectional Study of the MENA Region

et al. 2023

View full text Add to dashboard Cite

Since the emergence of the Coronavirus disease (COVID-19) pandemic, the disease has affected more than 675 million people worldwide, including more than 6.87 million deaths. To mitigate the effects of this pandemic, many countries established control measures to contain its spread. Their riposte was based on a combination of pharmaceutical (vaccination) and non-pharmaceutical (such as facemask wearing, social distancing, and quarantine) measures. In this way, cross-sectional research was conducted in Algeria from 23 December 2021 to 12 March 2022 to investigate the effectiveness of preventative interventions in lowering COVID-19 infection and severity. More specifically, we investigated the link between mask-wearing and infection on one side, and the relationship between vaccination and the risk of hospitalization on the other. For this purpose, we used binary logistic regression modeling that allows learning the role of mask-wearing and vaccination in a heterogeneous society with respect to compliance with barrier measures. This study determined that wearing a mask is equally important for people of all ages. Further, findings revealed that the risk of infection was 0.79 times lower among those who were using masks (odds ratio (OR) = 0.79; confidence interval (CI) 95% = 0.668–0.936; p-value = 0.006). At the same time, vaccination is a necessary preventive measure as the risk of hospitalization increases with age. Compared with those who did not get vaccinated, those who got vaccinated were 0.429 times less likely to end up in the hospital (OR = 0.429; CI95% = 0.273–0.676; p < 0.0001). The model performance demonstrates significant relationships between the dependent and independent variables, with the absence of over-dispersion in both studied models, such as the Akaike Information Criterion (AIC) scores. These findings emphasize the significance of preventative measures and immunization in the battle against the COVID-19 pandemic.

show abstract

“…Multiple logistic regression model was used to evaluate the association between anxiety and various factors during COVID-19 [16] , [17] , [18] , [19] . Models’ coefficients were estimated by utilizing different methods such as maximum likelihood method, Bayesian method and least square method [9] , [20] , [21] , [22] , [23] .…”

Section: Introductionmentioning

confidence: 99%

Logistic regression analysis for studying the impact of home quarantine on psychological health during COVID-19 in Saudi Arabia

Jawa¹

2022

Alexandria Engineering Journal

View full text Add to dashboard Cite

During the Coronavirus disease (COVID-19) period, the world witnessed a complete closure of all aspects of social life, and people must go for home quarantine to limit the spread of Corona virus disease. This study aims to use multiple logistic regression model (MLR) to identify the impact of home quarantine on psychological stability of individuals and its relationship to various factors. Maximum likelihood is used to estimate the parameters of MLR. Hosmer-Lemeshow method and Wald statistic are calculated to assess the significance of MLR. Cross sectional study was carried out and MLR was fitted to the collected data. This study applied to 846 residents of Makkah region during the COVID-19 period. High percentage of respondents felt psychological stability during the period of home quarantine. Logistic regression model showed that education level and psychological disorders during home quarantine were the significant risk factors for psychological stability during COVID-19. In addition, the positive impact of the home quarantine that people became more attention to their health, more interested to self-development and the families become close to each other. On the other hand, people on private employee or unemployed had psychological disorders more than others due to home quarantine and decrease their income.

show abstract

Optimal subsample selection for massive logistic regression with distributed data

Cited by 14 publications

References 16 publications

Distributed Logistic Regression for Massive Data with Rare Events

Distributed Logistic Regression for Massive Data with Rare Events

The Role of Vaccination and Face Mask Wearing on COVID-19 Infection and Hospitalization: A Cross-Sectional Study of the MENA Region

Logistic regression analysis for studying the impact of home quarantine on psychological health during COVID-19 in Saudi Arabia

Contact Info

Product

Resources

About