Understanding and predicting the quality determinants of e-government services: A two-staged regression-neural network model

Research output: Contribution to journalArticle

7 Citations (Scopus)

Abstract

Purpose – The purpose of this paper is to investigate the quality determinants influencing the adoption of e-government services in Oman and compare the performance of multiple regression and neural network models in identifying the significant factors influencing adoption in Oman. Design/methodology/approach – Primary data concerning service quality determinants and demographic variables were collected using a structured questionnaire survey. The variables selected in the design of the questionnaire were based on an extensive literature review. Factor analysis, multiple linear regression and neural network models were employed to analyze data. Findings – The study found that quality determinants: responsiveness, security, efficiency and reliability are statistically significant predictors of adoption. The neural network model performed better than the regression model in the prediction of e-government services’ adoption and was able to characterize the non-linear relationship of the aforementioned predictors with the adoption of e-government services. Further, the neural network model was able to identify demographic variables as significant predictors. Practical implications – This study highlights the importance of service quality in the adoption of e-government services and suggests that an enhanced focus and investment on improving quality of the design and delivery of e-government services can have a positive impact on the usage of the services, thereby enabling the Oman Government in achieving the governance objectives for which these technologies were employed. Originality/value – Studies in the area of e-government typically focus either on technology adoption problems or service quality problems. The role of service quality in adoption is rarely addressed. The research presented in this paper is of great value to the institutions that are involved in the development of technology-based e-government services in Oman.

Original languageEnglish
Pages (from-to)325-340
Number of pages16
JournalJournal of Modelling in Management
Volume10
Issue number3
DOIs
Publication statusPublished - Nov 1 2015

Fingerprint

Electronic government
Network model
Neural networks
Government services
Oman
Predictors
Demographic variables
Service quality
Quality of service
Factor analysis
Responsiveness
Multiple linear regression
Prediction
Literature review
Questionnaire
Government
Questionnaire survey
Multiple regression
Nonlinear relationships
Technology adoption

Keywords

  • e-Government
  • Modeling
  • Neural networks
  • Oman
  • Regression model
  • Service quality

ASJC Scopus subject areas

  • Strategy and Management
  • Management Science and Operations Research

Cite this

@article{f0d89b03096e44ec8994ba2ebdb4482b,
title = "Understanding and predicting the quality determinants of e-government services: A two-staged regression-neural network model",
abstract = "Purpose – The purpose of this paper is to investigate the quality determinants influencing the adoption of e-government services in Oman and compare the performance of multiple regression and neural network models in identifying the significant factors influencing adoption in Oman. Design/methodology/approach – Primary data concerning service quality determinants and demographic variables were collected using a structured questionnaire survey. The variables selected in the design of the questionnaire were based on an extensive literature review. Factor analysis, multiple linear regression and neural network models were employed to analyze data. Findings – The study found that quality determinants: responsiveness, security, efficiency and reliability are statistically significant predictors of adoption. The neural network model performed better than the regression model in the prediction of e-government services’ adoption and was able to characterize the non-linear relationship of the aforementioned predictors with the adoption of e-government services. Further, the neural network model was able to identify demographic variables as significant predictors. Practical implications – This study highlights the importance of service quality in the adoption of e-government services and suggests that an enhanced focus and investment on improving quality of the design and delivery of e-government services can have a positive impact on the usage of the services, thereby enabling the Oman Government in achieving the governance objectives for which these technologies were employed. Originality/value – Studies in the area of e-government typically focus either on technology adoption problems or service quality problems. The role of service quality in adoption is rarely addressed. The research presented in this paper is of great value to the institutions that are involved in the development of technology-based e-government services in Oman.",
keywords = "e-Government, Modeling, Neural networks, Oman, Regression model, Service quality",
author = "Sharma, {Sujeet Kumar} and Govindaluri, {Srikrishna Madhumohan} and Said Gattoufi",
year = "2015",
month = "11",
day = "1",
doi = "10.1108/JM2-12-2013-0069",
language = "English",
volume = "10",
pages = "325--340",
journal = "Journal of Modelling in Management",
issn = "1746-5664",
publisher = "Emerald Group Publishing Ltd.",
number = "3",

}

TY - JOUR

T1 - Understanding and predicting the quality determinants of e-government services

T2 - A two-staged regression-neural network model

AU - Sharma, Sujeet Kumar

AU - Govindaluri, Srikrishna Madhumohan

AU - Gattoufi, Said

PY - 2015/11/1

Y1 - 2015/11/1

N2 - Purpose – The purpose of this paper is to investigate the quality determinants influencing the adoption of e-government services in Oman and compare the performance of multiple regression and neural network models in identifying the significant factors influencing adoption in Oman. Design/methodology/approach – Primary data concerning service quality determinants and demographic variables were collected using a structured questionnaire survey. The variables selected in the design of the questionnaire were based on an extensive literature review. Factor analysis, multiple linear regression and neural network models were employed to analyze data. Findings – The study found that quality determinants: responsiveness, security, efficiency and reliability are statistically significant predictors of adoption. The neural network model performed better than the regression model in the prediction of e-government services’ adoption and was able to characterize the non-linear relationship of the aforementioned predictors with the adoption of e-government services. Further, the neural network model was able to identify demographic variables as significant predictors. Practical implications – This study highlights the importance of service quality in the adoption of e-government services and suggests that an enhanced focus and investment on improving quality of the design and delivery of e-government services can have a positive impact on the usage of the services, thereby enabling the Oman Government in achieving the governance objectives for which these technologies were employed. Originality/value – Studies in the area of e-government typically focus either on technology adoption problems or service quality problems. The role of service quality in adoption is rarely addressed. The research presented in this paper is of great value to the institutions that are involved in the development of technology-based e-government services in Oman.

AB - Purpose – The purpose of this paper is to investigate the quality determinants influencing the adoption of e-government services in Oman and compare the performance of multiple regression and neural network models in identifying the significant factors influencing adoption in Oman. Design/methodology/approach – Primary data concerning service quality determinants and demographic variables were collected using a structured questionnaire survey. The variables selected in the design of the questionnaire were based on an extensive literature review. Factor analysis, multiple linear regression and neural network models were employed to analyze data. Findings – The study found that quality determinants: responsiveness, security, efficiency and reliability are statistically significant predictors of adoption. The neural network model performed better than the regression model in the prediction of e-government services’ adoption and was able to characterize the non-linear relationship of the aforementioned predictors with the adoption of e-government services. Further, the neural network model was able to identify demographic variables as significant predictors. Practical implications – This study highlights the importance of service quality in the adoption of e-government services and suggests that an enhanced focus and investment on improving quality of the design and delivery of e-government services can have a positive impact on the usage of the services, thereby enabling the Oman Government in achieving the governance objectives for which these technologies were employed. Originality/value – Studies in the area of e-government typically focus either on technology adoption problems or service quality problems. The role of service quality in adoption is rarely addressed. The research presented in this paper is of great value to the institutions that are involved in the development of technology-based e-government services in Oman.

KW - e-Government

KW - Modeling

KW - Neural networks

KW - Oman

KW - Regression model

KW - Service quality

UR - http://www.scopus.com/inward/record.url?scp=84954543910&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84954543910&partnerID=8YFLogxK

U2 - 10.1108/JM2-12-2013-0069

DO - 10.1108/JM2-12-2013-0069

M3 - Article

AN - SCOPUS:84954543910

VL - 10

SP - 325

EP - 340

JO - Journal of Modelling in Management

JF - Journal of Modelling in Management

SN - 1746-5664

IS - 3

ER -