Impact of individual and organizational factors on job satisfaction: A comparison of multilevel models and multiple regression models using different data arrangements

2013 ◽  
Vol 19 (1) ◽  
pp. 44-59 ◽  
Author(s):  
Jun Yi Hsieh

AbstractTypically most studies of individual employees perceptions of the work place adopt multiple regression models (ordinary least squares [OLS]) which ignore inherent clustering in their data. However, such an approach does not supply unbiased and accurate answers to research questions. This study intends to simulate three data alternatives – weighted, disaggregated (individual level), and aggregated (organizational level) using the OLS and multilevel models to compare the results of different research designs. To answer the research questions, the current study investigates the impact of individual and organizational factors on job satisfaction, using a 2000 USA National Partnership for Reinventing Government survey. This study presents the methodological misuse and measurement errors of the previous research and presents guidelines for future research.

2015 ◽  
Vol 60 (02) ◽  
pp. 1550019 ◽  
Author(s):  
IRENE WEI KIONG TING ◽  
HOOI HOOI LEAN

This study investigates whether government participation in firm ownership leads to better firm performance of publicly listed companies in Malaysia. The sample covers 257 companies listed on the Bursa Malaysia from 1997 to 2009. Multiple regression models with balanced panel data are used to examine the impact of government ownership (GOVN) on firm performance. We find a negative relationship between GOVN and firm performance, a finding that supports the negative public perception of government-linked companies (GLCs) in Malaysia. We conclude that government ownership is not an effective tool for improvement of firm performance in Malaysia.


2021 ◽  
Vol 11 (12) ◽  
pp. 163
Author(s):  
Patrick Allen Rose ◽  
Suzana Brown

This article explores how after almost two years of government-imposed work from home (WFH) for the purpose of curbing the spread of COVID-19, South Korean managers’ general attitudes towards WFH may have been reconstructed and if this change influenced their expectations that WFH would persist for the long run. Before COVID-19, WFH was rare, and the country was well known for having one of the most hierarchical and rigid work cultures, with long hours at the office being the norm. The results of this study are based on survey responses from 229 South Korean managers and executives. Using means comparisons and hierarchical linear multiple regression models to answer three research questions, the present study evaluates theorized predictors of WFH take-up, general attitudes towards WFH, and the likelihood that WFH will continue post-COVID-19. The results indicate that forced WFH adoption during COVID-19 had statistically significant positive effects on the attitudes of South Korean managers and their intentions to continue working from home in the future. This study has practical implications for companies and governments that are interested in taking advantage of WFH and implementing it more permanently. It provides interesting findings on how managers from a country with minimal WFH prior to COVID-19 perceive the benefits of WFH and how they respond to its mandated adoption.


2021 ◽  
Vol 5 ◽  
Author(s):  
Jan Vanhove

Once they have learnt about the effects of collinearity on the output of multiple regression models, researchers may unduly worry about these and resort to (sometimes dubious) modelling techniques to mitigate them. I argue that, to the extent that problems occur in the presence of collinearity, they are not caused by it but rather by common mental shortcuts that researchers take when interpreting statistical models and that can also lead them astray in the absence of collinearity. Moreover, I illustrate that common strategies for dealing with collinearity only sidestep the perceived problem by biasing parameter estimates, reformulating the model in such a way that it maps onto different research questions, or both. I conclude that collinearity in itself is not a problem and that researchers should be aware of what their approaches for addressing it actually achieve.


2019 ◽  
Vol 2 (1) ◽  
pp. 47
Author(s):  
Angrian Permana

The purpose of this study was to know the effect of motivation on the job satisfaction of lecturers at Bina Bangsa University Faculty of Economics and Business, to know the effect of compensation on lecturer satisfaction at Bina Bangsa University Faculty of Economics and Business, and to know the effect of motivation and compensation together on lecturers satisfaction at Bina Bangsa University Faculty of Economics and Business. This research method used quantitative methods with multiple regression models. The populations of this study were 98 lecturers and the samples used in this study were all lecturers. The results showed that motivation had an effect on lecturers job satisfaction, compensation did not affect on lecturers job satisfaction, also motivation and compensation had an effect on the work satisfaction of lecturers together


2021 ◽  
pp. 1

Background and objective: Assessing the impact of different factors on anxiety level is a complex and challenging problem, especially during pandemic or similar life threatening situations. Stress can affect dietary and eating behaviors. The aim of this study is to extend knowledge concerning the relation between increased anxiety level during pandemic and attitude towards dietary and eating behaviors in the context of social situation and support of relatives and friends. This study was conducted in 2020 during COVID-19 pandemic. Methods: State-Trait Anxiety Inventory alongside auxiliary questions about social relations and eating habits were asked to the male students from different universities and courses in Eastern Europe. To assess differences and dynamics of anxiety level, multiple regression models were used. Results: Multiple regression models between state anxiety level with context to the following factors: paying particular attention to one's diet, namely, the way of nutrition during severe anxiety felt during the pandemic and factors such as strong social support and type of university course was R = 0.41 (p = 0.00). For trait-anxiety the same model returned R = 0.39 (p = 0.00). Analysis of variance revealed that support of relatives is significant factor for state anxiety level, whereas this factor is insignificant for trait anxiety level. Conclusions: Models obtained from this study indicated that there are significant relations between anxiety level of male students and social support, which is expressed in the form of proper eating, therefore pro-health habits are revealed during elevated prolonged stress state such as COVID-19 pandemic.


2013 ◽  
Vol 2 (3) ◽  
pp. 79 ◽  
Author(s):  
Nai-Yng Liu ◽  
Hsuan-Lien Chu ◽  
Chiu-Chuo Liao

The objective of this study is to investigate the influence of a physician incentive plan based upon treatment of patients in a large private non-for-profit hospital in Taiwan. We examine the relationship between physicians’ bonuses and departmental performance to assess the impact of the physician incentive plan in the case hospital. The multiple regression models are used to examine the relationship between physicians’ bonuses and departmental profitability. In addition, we use Data Envelopment Analysis (DEA) model to measure the operational efficiency of each department in the case hospital. Then, a multi-factor tobit model is used to examine the relationship between physicians’ bonuses and departmental efficiency. The results indicate that physicians’ bonuses in the case hospital are negatively correlated with departmental profitability and efficiency. That is, the performance measurement of current incentive plan may not be appropriate and it does not induce physicians to increase departmental profitability and improve efficiency. Our results suggest that the incentive plan is flawed and might fail to hold physicians accountable for improving departmental performance in the case hospital.  


2020 ◽  
Author(s):  
Jan Vanhove

Once they have learnt about the effects of collinearity on the output of multiple regression models, researchers may unduly worry about these and resort to (sometimes dubious) modelling techniques to mitigate them. I argue that, to the extent that problems occur in the presence of collinearity, they are not caused by it but rather by common mental shortcuts that researchers take when interpreting statistical models and that can also lead them astray in the absence of collinearity. Moreover, I illustrate that common strategies for dealing with collinearity only sidestep the perceived problem by biasing parameter estimates, reformulating the model in such a way that it maps onto different research questions, or both. I conclude that collinearity in itself is not a problem and that researchers should be aware of what their approaches for addressing it actually achieve.


Sign in / Sign up

Export Citation Format

Share Document