Capturing Relative Importance of Customer Satisfaction Drivers Using Bayesian Dominance Hierarchy

[We’re pleased to welcome authors Philippe Duverger and Xiaoyin Wang of Towson University. Duverger and Wang recently published an article in Cornell Hospitality Quarterly entitled “Capturing Relative Importance of Customer Satisfaction Drivers using Bayesian Dominance Hierarchy,” which is currently free to read for a limited time. Below, they reflect on the inspiration for conducting this research:]


What motivated you to pursue this research?

We observed that most research on the drivers of customer satisfaction (CS) used large samples, often aggregated from several month and/or several properties. Although this is a fine method to look at CS trends it is not practical at the property level for immediate action. The current methods require large samples in order to achieve sufficient power and find significant estimates in models. Unfortunately, most hotel property monthly survey yield samples of less than 100 that will make driver analyses problematic and more likely most drivers will have non-significant estimates.

We asked ourselves if there would not be a method that could circumvent the problem of property managers that want and need to address CS drivers on a monthly basis, if not on a daily basis.

What has been the most challenging aspect of conducting your research? Were there any surprising findings?

We used a Bayesian statistical framework, borrowing from several literature areas to construct a model. Bayesian statistical analysis is still a fairly new method in practice, often not well understood, and can be computationally heavy. Therefore we first needed to explain the advantages of the method in a way that was pragmatic enough because our goal in this paper was to appeal to the hospitality manager.

Bayesian statistics work from the belief that the unknown parameter is a random variable and is associated with a probability distribution (prior distribution). The information in the sample data is used to adjust the prior perception of the unknown parameter and results in the final estimation of the parameter (posterior distribution). Therefore, even if the sample is small, significance can be determined.

Maybe more pragmatically, Bayesian analysis is “often a more direct way to tackle questions we usually want to know, such as: is the hypothesis likely to be true?” Bayesian analysis does not use double negatives, such as we often encounter, e.g., “we failed to reject the null hypothesis that there is no difference.” Bayesian analysis reports are straight forward: “given these data, it is likely that the difference is X% probable” (Chapman and McDonnell Fei 2015, p. 150).

There are many other advantages that we discuss in the paper.

In what ways is your research innovative, and how do you think it will impact the field?

We believe that our Bayesian model, for which we share the code at, could be used by hospitality properties or hospitality corporate departments, to enhance monthly reporting along with other marketing metrics, and shared via dashboards.


Stay up-to-date with the latest research from Cornell Hospitality Quarterly and sign up for email alerts today through the homepage!

Contemporary Careers and Portable Selves

Author Gianpiero Petriglieri recently published an article in the Harvard Business Review, promoting his research. His most recent publication, “Fast Tracks and Inner Journeys: Crafting Portable Selves for Contemporary Careers” was featured in Administrative Science Quarterly. For more details, the abstract for Petriglieri’s research is below:

ASQ_72ppiRGB_powerpointThrough a longitudinal, qualitative study of 55 managers engaged in mobile careers across organizations, industries, and countries, and pursuing a one-year international master’s of business administration (MBA), we build a process model of the crafting of portable selves in temporary identity workspaces. Our findings reveal that contemporary careers in general, and temporary membership in an institution, fuel people’s efforts to craft portable selves: selves endowed with definitions, motives, and abilities that can be deployed across roles and organizations over time. Two pathways for crafting a portable self—one adaptive, the other exploratory—emerged from the interaction of individuals’ aims and concerns with institutional resources and demands. Each pathway involved developing a coherent understanding of the self in relation to others and to the institution that anchored participants to their current organization while preparing them for future ones. The study shows how institutions that host members temporarily can help them craft selves that afford a sense of agentic direction and enduring connection, tempering anxieties and bolstering hopes associated with mobile working lives. It also suggests that institutions serving as identity workspaces for portable selves may remain attractive and extend their cultural influence in an age of workforce mobility.

For more updates on ASQ articles check out their homepage and sign up for notifications! 

Are We Teaching What Employers Want?

[We’re pleased to welcome author Ellen McArthur of Griffith University, who recently published an article in the Journal of Marketing Education entitled, “The Employers’ View of “Work-Ready” Graduates: A Study of Advertisements for Marketing Jobs in Australia.” The article is co-authored by Krzysztof Kubacki, Bo Pang, and Celeste Alcaraz, also of Griffith University. Below, McArthur discusses key findings of the study:]

Innovative research by Griffith University into graduate job advertisements in Australia shows employers value the personal traits of job candidates more highly than degree qualifications. The study, which is the largest of its kind into graduate jobs in marketing, raises questions about the purpose of a degree, and whether universities are preparing students to be “work-ready”.

While the study focussed on marketing jobs, the findings have relevance for all academic disciplines. The most frequently required attributes were “soft skills” that are not specific to marketing, including motivation, time management, attention to detail, and teamwork. Superior communication skill, particularly writing talent, was also highly demanded, and it was only after the calls for these generic abilities that occupation-specific skills began to rank.



Among occupation-specific abilities, digital marketing was the most needed, including search engine optimisation, Google Analytics, AdWords, and creating and curating social media content for a range of platforms. Other demanded skills included project management, marketing communications, sales, and customer service and customer relationship management (CRM).


Some 48.5% of ads called for applicants with experience. This significant figure suggests the need for far greater integration of undergraduate study with initiatives that deliver hands-on practice, including internships, work integrated learning, and practice-based assessments.

General IT skills and a high level of computer literacy are important pre-requisites for applying for marketing positions. Experience in MS Office, including Word, Excel, and PowerPoint, was specified in almost one in three ads, followed by Adobe Suite, InDesign, Illustrator, and Photoshop. Though students may use these programs ad hoc, such strong demand suggests the need to embed this software use into courses as explicit learning outcomes.

A marketing degree specifically was required in only half the sample of advertisements, with communication, psychology, science, technology, engineering, and mathematics also providing pathways into marketing roles. This reflects the cross-disciplinary nature of marketing careers in the twenty-first century.


The Employers’ View of “Work-Ready” Graduates: A Study of Advertisements for Marketing Jobs in Australia’, content analysed 359 graduate advertisements (83,000 words) for careers in marketing posted on Australia’s top jobs website in a six-month period in 2016. Full time employment rates for Australian graduates have dropped to new lows, and the research aimed to identify the specific skills and attributes demanded by employers for graduate level jobs in marketing.

The study won a Best Paper Award at ANZMAC in 2016. Click here to read the full article for a limited time.

Griffith University is based in South-east Queensland, Australia, and ranks in the top 3% of universities globally, with more than 50,000 students across five campuses.

Dr. Ellen McArthur, who led the research project, said “large samples of job advertisements are perhaps the most valid way to study employers’ needs, but they are rarely used for employability research.”

Sign up for email alerts through the journal homepage so you never miss the latest articles like this one!

On SAGE Insight: The link between superbugs and hospital outsourced cleaners

[The following post is re-blogged from SAGE Insight. Click here to view the original post.]

Article title: Superbugs versus outsourced cleaners: Employment Arrangements and the Spread of Health Care–Associated Infections
From ILR Review

On any given ILR_72ppiRGB_powerpoint.jpgday, one in every 25 patients in U.S. hospitals has a health care–associated or hospital-acquired infection (HAI)—one of a handful of so-called superbugs that contribute to the deaths of 75,000 of these patients. Not surprisingly, health care practitioners and scholars have turned their attention to clinical and delivery-of-care factors that might account for HAIs. This article provides novel, quantitative, empirical evidence linking a specific type of employment arrangement—outsourcing—to patient safety. It shows that in addition to the more widely examined clinical culprits, the HAI challenges plaguing the U.S. health care system are also a function of the strategic employment choices that organizations make in relating to their nonclinical staff. The findings have important implications for health care scholars, practitioners, and policymakers.


On any given day, about one in 25 hospital patients in the United States has a health care–associated infection (HAI) that the patient contracts as a direct result of his or her treatment. Fortunately, the spread of most HAIs can be halted through proper disinfection of surfaces and equipment. Consequently, cleaners—“environmental services” (EVS) in hospital parlance—must take on the important task of defending hospital patients (as well as staff and the broader community) from the spread of HAIs. Despite the importance of this task, hospitals frequently outsource this function, increasing the likelihood that these workers are under-rewarded, undertrained, and detached from the organization and the rest of the care team. As a result, the outsourcing of EVS workers could have the unintended consequence of increasing the incidence of HAIs. The authors demonstrate this relationship empirically, finding support for their theory by using a self-constructed data set that marries infection data to structural, organizational, and workforce features of California’s general acute care hospitals. The study thus advances the literature on nonstandard work arrangements—outsourcing in particular—while sounding a cautionary note to hospital administrators and health care policymakers.

Read this article for free

Article details
Superbugs versus outsourced cleaners: Employment Arrangements and the Spread of Health Care–Associated Infections
Adam Seth Litwin, Ariel c. avgar, and Edmund E. Becker
ILR Review
May 2017
DOI: 10.1177/0019793916654482

For more of the latest research from ILR Review, be sure to visit the Table of Contents for the latest May issue.  Included in the newly released issue are papers that discuss the debate on the effects of minimum wage, recent labor market topics, employment effects of healthcare reform, and how underemployment will continue to affect labor market opportunities.

Sign up for email alerts through the journal homepage so you never miss the latest research.

Income Inequality and Subjective Well-Being: Assessing the Relationship

[We’re pleased to welcome author Ivana Katic of the Yale School of Management.  Katic recently published an article in Business & Society entitled, “Income Inequality and Subjective Well-Being: Toward an Understanding of the Relationship and Its Mechanisms,” co-authored by Paul Ingram of Columbia Business School. Below, Katic details the inspiration for the study:]

What inspired you to be interested in this topic? Inequality has always been a major topic in sociology. In the academic community and beyond, this interest in inequality simply exploded in the wake of the financial crisis of 2008, as well as the Occupy protests around the world. Despite the amount of attention that income inequality has been receiving in empirical studies across psychology, sociology, economics as well as political science, my co-author Paul Ingram and I noticed that the literature was still quite mixed in regards to the effects of income inequality. In fact, extant studies had found positive, negative and neutral effects of income inequality on the subjective wellbeing and happiness levels of individuals. This lack of a consensus, we thought, was quite interesting, especially in contrast to the commonly held belief that inequality has exclusively negative consequences for individuals, as well as communities—ranging from lowered trust and health and increased crime levels to, ultimately, lower overall wellbeing. We decided that the time was ripe to pursue a comprehensive study that would allow us to better understand how income inequality affects subjective wellbeing (SWB). Such a study would also allow us to better understand the channels through which income inequality may affect SWB. We set out to answer these important, and particularly timely questions, by constructing a rich cross-country dataset including 65 countries from 1995 to 201B&S_72ppiRGB_powerpoint.jpg1.

Were there findings that were surprising to you?Given the common notion that income inequality is always detrimental to human flourishing, we were initially surprised to see that income inequality had a strong and very robust effect on SWB in our analysis. On the other hand, this was not the first time a study had found a positive effect—so there was clearly precedent for our finding in previous literature on the topic. However, to be quite certain, we threw everything we could at our results in a variety of robustness tests (including different operationalizations of our key independent variable and our dependent variable, as well as a series of different estimation techniques). Our results never budged.

How might one use the study’s main finding of a positive main effect of income inequality on SWB to create policy? While our main effect suggests that decreasing income inequality may not increase SWB, we caution against using our study as justification for lowering taxes and increasing inequality. First, our results do not necessarily indicate that income inequality is never a negative for a variety of other life outcomes. Second, we cannot rule out that income inequality may increase beyond the range studied in our paper, and we similarly cannot guarantee that it would not have negative effects beyond that range. Third, in a separate working paper, we find that any changes in the level of income inequality are uniquely damaging to SWB, suggesting that fluctuating levels of inequality may be particularly psychologically taxing for individuals to adjust to.

However, our study has another way forward for policy. A particularly important aspect of our study is that it sheds light on the mechanisms of income inequality’s relationship with SWB. Specifically, we found that income inequality has more positive effects on individuals who are relatively better off, those that perceive the income generation process to be fair, and surprisingly, those that do not perceive a lot of social mobility in their society. It is with these mechanisms in mind that we suggest constructing policies that focus on increasing perceptions of fairness and reducing social comparisons to the superrich.

In terms of future research, we hope that our study paves the way for other work that might further unravel the complexity of income inequality’s effects. In particular, future scholars should continue to investigate how income inequality may impact individuals differently depending on who they are, and where they live. Finally, the role of organizations in affecting levels of income inequality (and consequently, SWB) is also a very promising area of study. Given the complexity of this social phenomenon, as well as its highly significant implications for policy, future work on all of these topics is direly needed.

Sign up to receive notifications about the latest published research from Business & Society.

Relying on Social Media to Assess Job Applicants: The Limitations

Recruiters rely heavily on technology and social media to promote new job openings, so then what happens when a promising candidate applies? Social media once again plays a role where the organization is tempted to locate the candidate’s profile on or other sites. Ultimately, the strategy creates an intercha5624177651_5393210133_z.jpgngeable lens from personnel  to personal selection.

The study, “Social Media for Selection? Validity and Adverse Impact Potential of a Facebook-Based Assessment,” published in the Journal of Management examines how recruiters evaluate a candidate’s social media profile, and what those limitations are. The JOM study was also recently featured in an article from the Society for Industrial and Organizational Psychology, naming it one of the top 10 most significant studies with practical utility in 2016. Click here to view the original post from SIOP.

Below, please find the abstract to the article:

Recent reports suggest that an increasing number of organizations are using information from social media platforms such as to screen job applicants. Unfortunately, empirical research concerning the potential implications of this practice is extremely limited. We address the use of social media for selection by examining how recruiter ratings of Facebook profiles fare with respect to two important criteria on which selection procedures are evaluated: criterion-related validity and subgroup differences (which can lead to adverse impact). We captured Facebook profiles of college students who were applying for full-time jobs, and recruiters from various organizations reviewed the profiles and provided evaluations. We then followed up with applicants in their new jobs. Recruiter ratings of applicants’ Facebook information were unrelated to supervisor ratings of job performance (rs = −.13 to –.04), turnover intentions (rs = −.05 to .00), and actual turnover (rs = −.01 to .01). In addition, Facebook ratings did not contribute to the prediction of these criteria beyond more traditional predictors, including cognitive ability, self-efficacy, and personality. Furthermore, there was evidence of subgroup difference in Facebook ratings that tended to favor female and White applicants. The overall results suggest that organizations should be very cautious about using social media information such as Facebook to assess job applicants.

The article is co-authored by Chad H. Van Iddekinge, Stephen E. Lanivich, Philip L. Roth, and Elliott Junco. It is currently free to read for a limited time, by clicking here.

Don’t forget to sign up for email alerts through the Journal of Management homepage so you never miss the latest research.

Facebook photo attributed to Pascal Paukner (CC).


Does using clickers in class help students engage and succeed?

With the growing technology advances and integration of new technology into classrooms, professors across the nation have adopted clickers as a means of participation in lectures. Of course, with new engagement strategies comes pros and cons, including how students must remember to bring the clickers, and if lost, will have to pay to replace the unit. The clickers can also prompt students to pay more attention in class, sinJME(D)_72ppiRGB_powerpoint.jpgce clickers can be used to take quizzes, and in turn, keep an online record of attendance.

A recent article in the Journal of Marketing Education entitled “Using Clickers in a Large Business Class: Examining Use Behavior and Satisfaction,” analyzes the use of clickers in the classroom which yields overall positive responses in content engagement. Authors Nripendra P. Rana and Yogesh K. Dwivedi also provide data on the behavioral intentions of the students in their study. The abstract for their article is below:

As more and more institutions are integrating new technologies (e.g., audience response systems such as clickers) into their teaching and learning systems, it is becoming increasingly necessary to have a detailed understanding of the underlying mechanisms of these advanced technologies and their outcomes on student learning perceptions. We proposed a conceptual model based on the technology acceptance model to understand students’ use behavior and satisfaction with clickers. The valid response from 138 second-year business students of Digital Marketing module taught in a British university, where clickers are extensively used in the teaching and learning process, made the basis for data analysis. The results provided a strong support for the proposed model with a reasonably adequate variance (i.e., adjusted R2) of 67% on behavioral intentions and sufficiently high variance on use behavior (i.e., 86%) and user satisfaction (i.e., 89%).

The article is free to read for a limited time, and don’t forget to sign up for email alerts through the homepage so you never miss a new issue.