The adoption, diffusion, and evaluation of IT in healthcare continue to present challenges to organizations and society, as well as to researchers. IT is seen as an enabler of change both nationally and locally in healthcare organizations. However, IT adoption decisions in healthcare are complex because of the uncertainty of benefits and the rate of change of technology.

Background: Lung disease is a severe problem in the United States. Despite the decreasing rates of cigarette smoking, chronic obstructive pulmonary disease (COPD) continues to be a health burden in the United States. In this paper, we focus on COPD in the United States from 2016 to 2019. Objective: We gathered a diverse set of non-personally identifiable information from public data sources to better understand and predict COPD rates at the core-based statistical area (CBSA) level in the United States. Our objective was to compare linear models with machine learning models to obtain the most accurate and interpretable model of COPD. Methods: We integrated non-personally identifiable information from multiple Centers for Disease Control and Prevention sources and used them to analyze COPD with different types of methods. We included cigarette smoking, a well-known contributing factor, and race/ethnicity because health disparities among different races and ethnicities in the United States arealso well known. The models also included the air quality index, education, employment, and economic variables. We fitted models with both multiple linear regression and machine learning methods. Results: The most accurate multiple linear regression model has variance explained of 81.1%, mean absolute error of 0.591, and symmetric mean absolute percentage error of 9.666. The most accurate machine learning model has variance explained of 85.7%, mean absolute error of 0.456, and symmetric mean absolute percentage error of 6.956. Overall, cigarette smoking and household income are the strongest predictor variables. Moderately strong predictors include education level and unemployment level, as well as American Indian or Alaska Native, Black, and Hispanic population percentages, all measured at the CBSA level. Conclusions:This research highlights the importance of using diverse data sources as well as multiple methods to understand and predict COPD. The most accurate model was a gradient boosted tree, which captured nonlinearities in a model whose accuracy is superior to the best multiple linear regression. Our interpretable models suggest ways that individual predictor variables can be used in tailored interventions aimed at decreasing COPD rates in specific demographic and ethnographic communities. Gaps in understanding the health impacts of poor air quality, particularly in relation to climate change, suggest a need for further research to design interventions and improve public health.

The abundance of data available to researchers has led to increasing interest in data-derived theoretical development. Although this is a valid method of deriving theoretical models, it is subject to numerous limitations and hazards that may threaten the validity and usefulness of the models. The purpose of this paper is to critique empirically driven theoretical development. Our goal is to offer a cautionary tale about the limits of derivation of theory from empirical analysis in the hopes that our analysis and critique can strengthen empirical derivation of theory. In this paper, we use the empirical derivation of the Unified Model of Information Security Policy Compliance (UMISPC) as a research case study to illustrate some of these limitations and risks. For example, we critique the opportunistic dropping of theoretical paths based on statistical results, cautioning that doing so is insufficient for forming new theory. We also report several attempts at validating UMISPC through replication, including our own, which used data from a survey of 525 employed American adults. Comparison of the replications and original model indicates a general failure to replicate substantial portions of the original paper. We discuss five specific pitfalls associated with empirically driven model development and make recommendations for future studies that use inductive, data-driven approaches to derive theoretical models.

In this paper, we develop several predictive models pertaining to Electric Vehicles in the United States. We set out to understand three phenomena: Public Charging Units, Electric Vehicle Jobs, and Electric Vehicle Registrations. To model them, we include variables from various categories – demographics, economics, education, environment, finance, geographics, public health, and technographics – in the timespan of 2010–2020. We integrate data from multiple data sources and use them to understand, explain, and predict the Electric Vehicle phenomena combining state and county level data. We obtain three random effects linear regression models having variance explained of 51.5–62.4%. We also fit several machine learning models to improve the accuracy of the models, highlighting nonlinearities, to provide additional insights. The overall predictive accuracy of each Gradient Boosted Tree model is far superior to that of each linear regression model and significantly better than the other machine learning models. Our core contribution is that, spanning all three phenomena, the three most important predictor variables are solar generation of electricity, high school graduation rates, and air quality. We interpret the models and discuss their implications for research and practice.

Presents the introduction the conference track.

This is an applied econometric analysis of labour market data for the United States. We study the impact of several factors on overflow of overeducated employees into various job categories. We use panel data regression analysis with fixed and random effects. We also use data visualisation to investigate the overeducation trends during 2002-2016 for various occupation categories. Our dataset consists of seven sets of annual data for 704 occupations. We investigate this phenomenon at two levels: 1) overflow of university graduates into occupations that do not require a university degree, and 2) overflow of Masters and PhD degree holders into occupations that require a bachelor's degree or less. We observe that the overeducation has increased in most occupations and it causes a crowding out effect; an adequately educated worker might be outcompeted by an overeducated worker. While the income premium of a university education has decreased over time, the income advantage of university education over a high school degree has persisted. Furthermore, our regression analysis has shown that the overeducation ratio has a positive correlation with the median earnings of an occupation and its opportunities for self-employment. The results hold for both college graduates and holders of graduate degrees.

The purpose of this paper is to model the cases of COVID-19 in the United States from 13 March 2020 to 31 May 2020. Our novel contribution is that we have obtained highly accurate models focused on two different regimes, lockdown and reopen, modeling each regime separately. The predictor variables include aggregated individual movement as well as state population density, health rank, climate temperature, and political color. We apply a variety of machine learning methods to each regime: Multiple Regression, Ridge Regression, Elastic Net Regression, Generalized Additive Model, Gradient Boosted Machine, Regression Tree, Neural Network, and Random Forest. We discover that Gradient Boosted Machines are the most accurate in both regimes. The best models achieve a variance explained of 95.2% in the lockdown regime and 99.2% in the reopen regime. We describe the influence of the predictor variables as they change from regime to regime. Notably, we identify individual person movement, as tracked by GPS data, to be an important predictor variable. We conclude that government lockdowns are an extremely important de-densification strategy. Implications and questions for future research are discussed.

In this research, we take a multivariate, multi-method approach to predicting the incidence of lung cancer in the United States. We obtain public health and ambient emission data from multiple sources in 2000–2013 to model lung cancer in the period 2013–2017. We compare several models using four sources of predictor variables: adult smoking, state, environmental quality index, and ambient emissions. The environmental quality index variables pertain to macro-level domains: air, land, water, socio-demographic, and built environment. The ambient emissions consist of Cyanide compounds, Carbon Monoxide, Carbon Disulfide, Diesel Exhaust, Nitrogen Dioxide, Tropospheric Ozone, Coarse Particulate Matter, Fine Particulate Matter, and Sulfur Dioxide. We compare various models and find that the best regression model has variance explained of 62 percent whereas the best machine learning model has 64 percent variance explained with 10% less error. The most hazardous ambient emissions are Coarse Particulate Matter, Fine Particulate Matter, Sulfur Dioxide, Carbon Monoxide, and Tropospheric Ozone. These ambient emissions could be curtailed to improve air quality, thus reducing the incidence of lung cancer. We interpret and discuss the implications of the model results, including the tradeoff between transparency and accuracy. We also review limitations of and directions for the current models in order to extend and refine them.

ABSTRACT In this study we investigate the educational attainment of the labour force in the United States. Our data analysis, based on Bureau of Labour Statistics data in more than 700 occupations, produced two important findings. First, we observed that the Overeducation Ratio (share of employees that are overeducated), which began to rise in the United States as early as 1970, continued its positive trend in many occupations during 2002–2016. Second, our regression analysis revealed a positive correlation between the overeducation ratio and the median earnings of an occupation. Since a larger overeducation ratio implies that a larger share of adequately educated individuals are crowded out, this result suggests that the displacement of adequately educated individuals is more severe in better paying occupations. Third, we analysed the overflow of graduate degree holders into occupations that require a bachelor’s degree. We observe that graduate degree holders are crowding out the bachelor’s degree holders from better paying bachelor’s occupations. The bachelor’s degree holders, in turn, are crowding out high school graduates from better paying high school jobs.

Vaccinating adults against influenza remains a challenge in the United States. Using data from the Centers for Disease Control and Prevention, we present a model for predicting who receives influenza vaccination in the United States between 2012 and 2014, inclusive. The logistic regression model contains nine predictors: age, pneumococcal vaccination, time since last checkup, highest education level attained, employment, health care coverage, number of personal doctors, smoker status, and annual household income. The model, which classifies correctly 67 percent of the data in 2013, is consistent with models tested on the 2012 and 2014 datasets. Thus, we have a multiyear model to explain and predict influenza vaccination in the United States. The results indicate room for improvement in vaccination rates. We discuss how cognitive biases may underlie reluctance to obtain vaccination. We argue that targeted communications addressing cognitive biases could be useful for effective framing of vaccination messages, thus increasing the vaccination rate. Finally, we discuss limitations of the current study and questions for future research.

Software as a service (SaaS) offers an innovative way to deliver software over the Internet to distributed organizations. While more and more SaaS providers are joining the market and competition among providers becomes more intense, we need to understand the considerations of potential clients. Built on transaction cost theory and social exchange theory, this study empirically investigates, with a national survey of IT/IS executives, the role of economic factors and the impact of social relationships on the economic factors in firms' deciding to adopt SaaS. We found that cost savings are a critical consideration in SaaS and that social relationships exert a strong, positive direct impact on cost savings and positively moderate the impact of cost savings on SaaS. This paper expands our theoretical understanding of the SaaS phenomenon and provides some managerial insights.

Although the Internet is in its second decade of wide-spread adoption, many patient-centered health websites are still in a phase of early adoption, scrambling to define and defend market segments in a shifting healthcare information landscape. Consequently, healthcare and health information providers are jockeying for position in a dynamic industry trying to serve different patients’ needs. To understand the situation, this article takes the approach of Patient-centered e-Health (PCEH) and makes three contributions. One, we empirically test the PCEH framework on patient-focused websites. Two, given the PCEH framework, we identify five categories of websites that serve different segments of the patient-centered health information market. Three, we analyze the five categories in terms of different features and derive a classification model. This article helps us better understand PCEH websites and guide the future development of online healthcare and health information services.

Objective To optimize a new visit-independent, population-based cancer screening system (TopCare) by using operations research techniques to simulate changes in patient outreach staffing levels (delegates, navigators), modifications to user workflow within the information technology (IT) system, and changes in cancer screening recommendations.Materials and methods TopCare was modeled as a multiserver, multiphase queueing system. Simulation experiments implemented the queueing network model following a next-event time-advance mechanism, in which systematic adjustments were made to staffing levels, IT workflow settings, and cancer screening frequency in order to assess their impact on overdue screenings per patient.Results TopCare reduced the average number of overdue screenings per patient from 1.17 at inception to 0.86 during simulation to 0.23 at steady state. Increases in the workforce improved the effectiveness of TopCare. In particular, increasing the delegate or navigator staff level by one person improved screening completion rates by 1.3% or 12.2%, respectively. In contrast, changes in the amount of time a patient entry stays on delegate and navigator lists had little impact on overdue screenings. Finally, lengthening the screening interval increased efficiency within TopCare by decreasing overdue screenings at the patient level, resulting in a smaller number of overdue patients needing delegates for screening and a higher fraction of screenings completed by delegates.Conclusions Simulating the impact of changes in staffing, system parameters, and clinical inputs on the effectiveness and efficiency of care can inform the allocation of limited resources in population management.

There have been few studies investigating the effects of collaboration on online shopping. In this paper, we consider an online shopping scenario where the user and a partner, who are not collocated, plan the travel collaboratively. We develop a research model based on Website Trust to explain the user's Website Intentions. To test the model, we conducted a field experiment with 605 individuals and a partner using LiveLook, an online co-browsing platform. A PLS analysis of the influence of advice sharing showed the following variance explained: Website Trust 20.6 percent, Website Enjoyment 55.2 percent, Perceived Control 59.4 percent, and Website Intentions 55.3 percent. We also show separate models for two different user interfaces: one for packaged travel and one for customizable travel. The resulting models show the packaged travel interface to have greater website intentions while the customizable travel interface has greater variance explained. Overall, the results shed light on the network of influences that advice sharing has in online travel planning.

Security researchers and managers would like to know the best ways of introducing new innovations and motivating their use. This study applies Protection Motivation Theory to model the coping and threat appraisals that motivate Millennials, who are early technology adopters, to adopt or resist biometric security for system access. One hundred fifty-nine Millennials were given a hypothetical scenario in which system access would be enhanced by biometric security to strengthen user authentication. The authors model the results with PLS and find that Protection Motivation Theory provides a good explanation of the user's perceptions of biometric security. The model suggests that the users' protection motivation is influenced directly by the Perceived System Response Efficacy of the biometric system and indirectly by Perceived Effort Expectancy, Perceived Computer Self-Efficacy, Perceived Privacy Invasion and Perceived System Vulnerability. Implications and limitations of the model are discussed.

This article offers a review of three software packages that estimate directed acyclic graphs (DAGs) from data. The three packages, MIM, Tetrad and WinMine, can help researchers discover underlying causal structure. Although each package uses a different algorithm, the results are to some extent similar. All three packages are free and easy to use. They are likely to be of interest to researchers who do not have strong theory regarding the causal structure in their data. DAG modeling is a powerful analytic tool to consider in conjunction with, or in place of, path analysis, structural equation modeling, and other statistical techniques.

This paper investigates how e-Business can benefit from serving students with social decision and service customization support. We test whether the social richness of online shopping in pairs, connected by screen sharing technology, contributes to a greater intent to book vacation travel. Furthermore, we test the value of allowing for high customization. We conducted a controlled laboratory experiment and a field experiment with a total of 391 subjects. A Partial Least Squares analysis of Perceived Effectiveness, Perceived Enjoyment, Perceived Partner Quality, Opinion Seeker and Opinion Leader, combined to explain Intent to Purchase with high variance explained (61.6%). We found significant differences between high-customization and low-customization groups. The high-customization group had a lower intent to purchase, but with greater variance explained (73.7%). The low-customization group had greater intent to purchase, but with lesser variance explained (50.0%). The results shed light on the value proposition for offering social and customization support to students. Future research will extend the results to other populations, task domains and devices.Keywords: Social decision support, customization support, student travel, intent to purchaseIntroductionGeneration Y Students (born between 1981 and 1990) are online up to three hours per day for entertainment, peer communication, shopping and entertainment (Interactive 2006). They tend to shop socially, relying on friends and family for advice and approval, more so than any other age group (Sirgy, Grewal and Mangleburg 2000; Johnstone and Conroy 2006).Social decision support is one way to reach students. Customization support, a growing trend in electronic business (Pine 1993; Tu, Vonderembse, Ragu-Nathan and Ragu-Nathan 2004; Tu, Vondermebse and Ragu-Nathan 2004; Tu, Xie and K. Fung 2007), is another way. Generation Y Students are the most likely age group to customize products online, particularly automobiles, computer hardware, greeting cards, apparel and consumer electronics (Johnson and Huit 2007). Socially-based computing is a phenomenon which appears to have strong promise in online retailing (Tedeschi 2006).This study examined the intersection of Social and Customization factors among Generation Y students. Our purpose is to address how social and customization factors interplay to affect intention to purchase. The results of this study shed light on their online travel planning, and it provides guidance to web site designers incorporating various kinds of decision support into online travel planning applications. Future research will extend the results to other task domains and devices, e.g., the mobile telephone.Literature ReviewFundamentally, effort is the key factor in decision making (Davis 1989; Todd and Benbasat 1992; Benbasat and Todd 1996). Decision makers tend to adapt their strategy selection to the type of decision aids available in such a way as to reduce effort (Todd and Benbasat 1991). Spending extensive time and effort without converging upon an adequate choice can easily lead to uncertainty and abandonment of the search process. In a study of college students' online vacation travel planning, the more time that was used to search for an online vacation, the less the likelihood of achieving higher levels of satisfaction (Bai, Hu, Eisworth and Countryman 2005).With socially well-connected individuals, such as Generation Y students, the converging to a desirable choice can be achieved simply by sufficient social validation. That is, if a small number of trusted friends validate the individual's tentative choice, it becomes acceptable. Travel planning in pairs can decrease the real and perceived search effort. In the case of student travel, customers' satisfaction derives from low effort as much as discounted price (Kim, Kim and Han 2007).Students are particularly sensitive to peer pressure (Johnson and Huit 2007; Temkin, Popoff-Walker, Melnikova and Geller 2007; Temkin and Popoff-Walker 2007), since social validation is important to them (Lueg and Ponder 2006). …

This paper investigates how online travel can benefit from serving Millennials with collaboration support. We test whether the decision support of online shopping in pairs, connected by screen sharing technology, contributes to a greater intent to purchase vacation travel. We conducted a field experiment with 150 subjects. A Partial Least Squares analysis of Collaboration, Ease of Use, Trust, and Perceived Effectiveness combined to explain Intent to Purchase with 42.5% variance explained. The results shed light on the value proposition for offering collaboration support to Millennials. Future research will extend the results to other populations, task domains and devices.

User-customization is increasingly common in electronic commerce, because both the buyer and seller potentially benefit. The user interface to implement and the influence of the interface on various process and outcome measures, however, are not well understood. We developed a Flow-based model consisting of seven hypotheses regarding the user interface and its consequents. We conducted a field experiment to test an attribute-based interface vs. a question-based interface on three variables (perceived control, shopping enjoyment and choice satisfaction) as well as two web site intentions: intention to return and intention to purchase. Six of the seven hypotheses were supported in a parsimonious model. Variance explained was 16.3% for perceived control, 45.6% for shopping enjoyment, 59.3% for choice satisfaction and 63.1% for web site intentions. The main finding is that an attribute-based interface for retail e-shopping increases the shopper’s sense of control and feeling of enjoyment in the process more than a question-based interface, and thereby increases satisfaction with the outcome. This combination of influences increases the intention of the shopper to return to the web site and to purchase the item. We discuss the results and suggest areas for future research in user-customization, which may apply to many different industries that engage in online commerce.