2014
DOI: 10.1080/10967494.2014.997906
|View full text |Cite
|
Sign up to set email alerts
|

Common Method Bias in Public Management Studies

Abstract: The questionnaire survey is one of the most commonly used methods of data collection in public management research. These surveys often provide the information used to measure both the independent and dependent variables in an analysis. However, this introduces the risk of common method bias-a serious methodological challenge that has not received much attention as a distinct topic in public management research. We discuss the challenge of common method bias in relation to public management studies and illustr… Show more

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...
2
2
1

Citation Types

5
334
2
7

Year Published

2016
2016
2024
2024

Publication Types

Select...
8

Relationship

0
8

Authors

Journals

citations
Cited by 509 publications
(350 citation statements)
references
References 55 publications
5
334
2
7
Order By: Relevance
“…Yet we are especially interested in examining interaction effects, and it has recently been argued that this is a case where common source bias is typically of less concern (Jakobsen & Jensen, 2015). Siemsen, Roth, and Oliveira (2010) have thus shown that when true interaction effects exist, common method variance tends to attenuate these effects.…”
Section: Discussionmentioning
confidence: 99%
“…Yet we are especially interested in examining interaction effects, and it has recently been argued that this is a case where common source bias is typically of less concern (Jakobsen & Jensen, 2015). Siemsen, Roth, and Oliveira (2010) have thus shown that when true interaction effects exist, common method variance tends to attenuate these effects.…”
Section: Discussionmentioning
confidence: 99%
“…perceived strategic-decision quality), common method bias might be less of a concern (Favero & Bullock, 2014;Meier & O'Toole, 2013). Nevertheless, we tried to minimize issues of common method bias through our survey design and by identifying its impact through a statistical test (Jakobsen & Jensen, 2014). First, our survey design followed recommendations of MacKenzie and Podsakoff (2012) and Podsakoff, MacKenzie, and Podsakoff (2012).…”
Section: Common Methods Biasmentioning
confidence: 99%
“…In order to emphasize the importance and accuracy of responses, we explained the central objectives of the survey in the introduction mail and we offered full anonymity. The dependent and independent variables were separated in the survey by placing them on different pages, which creates a time lag between the respondent's answers (Jakobsen & Jensen, 2014;Podsakoff et al, 2012). Second, we identified the impact of common method bias via the statistical test developed by Harman (1976).…”
Section: Common Methods Biasmentioning
confidence: 99%
“…Also, although other studies have used similar strategies Kim 2005) there may be more variation within an organization than between them. On the other hand, this study provides a step forward by using more enhanced techniques such as fixed-effects regression which captures (and controls for) organizational levels of social desirability bias unless this changes over time (Cameron & Trivedi 2009;Jakobsen & Jensen 2015). Furthermore, individual level panels typically suffer from other methodological problems such as attrition and nonresponse bias and are substantively smaller samples than repeated cross-sectional analyses.…”
Section: Discussionmentioning
confidence: 99%
“…Panel analysis has thus been suggested as a very effective means to limit the common method bias typically associated with cross-sectional studies using self-perceived performance measures since such bias related to social desirability is assumed to be stable across time (Favero & Bullock 2014;Jakobsen & Jensen 2015). In this respect, our approach with aggregating data at the organizational level resembles Brewer's split sample method (2006) widely recognized as a means to deal with common method bias -here uniquely combined with a panel analysis (which is also the reason why we do not employ the split sample method in its original form).…”
Section: Statistical Modelsmentioning
confidence: 99%