New Page 1

[ Home ] [ People ] [ Projects ] [ Publications ] [ Directions ]


Lateral Collinearity and Misleading Results in Variance-Based SEM

Variance-based structural equation modeling is extensively used in information systems research, and many related findings may have been distorted by hidden collinearity. This is a problem that may extend to multivariate analyses in general, in the field of information systems as well as in many other fields. In multivariate analyses, collinearity is usually assessed as a predictor-predictor relationship phenomenon, where two or more predictors are checked for redundancy. This type of assessment addresses vertical, or “classic”, collinearity. However, another type of collinearity may also exist, called here “lateral” collinearity. It refers to predictor-criterion collinearity. Lateral collinearity problems are exemplified based on an illustrative variance-based structural equation modeling analysis. The analysis employs WarpPLS 2.0, with the results double-checked with other statistical analysis software tools. It is shown that standard validity and reliability tests do not properly capture lateral collinearity. A new approach for the assessment of both vertical and lateral collinearity in variance-based structural equation modeling is proposed and demonstrated in the context of the illustrative analysis.


Exploring Free Questionnaire Data with Anchor Variables with IT in Healthcare Applications

This project aims to makes an important methodological contribution regarding the use of free questionnaires, illustrated through a study that shows that a healthcare professional’s propensity to use electronic communication technologies creates opportunities for interaction with other professionals, which would not otherwise be possible only via face-to-face interaction. This in turn appears to increase mutual trust, and eventually improve the quality of group outcomes. Free questionnaires are often used by healthcare information management researchers. They yield datasets without clear associations between constructs and related indicators. If such associations exist, they must first be uncovered so that indicators can be grouped within latent variables referring to constructs, and structural equation modeling analyses be conducted. A novel methodological contribution is made here through the proposal of an anchor variable approach to the analysis of free questionnaires. Unlike exploratory factor analyses, the approach relies on the researcher’s semantic knowledge about the variables stemming from a free questionnaire. The use of the approach is demonstrated using the multivariate statistical analysis software WarpPLS 2.0. The study leads to a measurement model that passes comprehensive validity, reliability, and collinearity tests. It also appears to yield practically relevant and meaningful results.


Redesigning Acquisition Processes Focusing on the Flow of Knowledge and Information

Current business process redesign practices, in the defense sector as well as in business in general, are based on several assumptions inherited from Taylor’s scientific management method, including the key assumption that activity-flow representations should provide the basis for business process redesign. While this assumption was probably correct for most organizations in the early 1900s, it is clearly inconsistent with the fact that, currently “information” is what flows the most in business processes, even in manufacturing organizations. This project is based on the key assumption that the current focus of business process redesign approaches should be on information flows rather than activity flows. The main goal of this project is to refine a methodology for redesigning acquisition processes based on knowledge and information-flow analysis, whose original proposal was published in 2001 as a book by the Defense Acquisition University Press. The methodology, called InfoDesign, focuses on the knowledge embedded in a business process, the information processing resources involved in execution of the process, and the information flowing through the process. The InfoDesign methodology was developed and partially validated during a one-year project. The validation of the methodology was conducted as an action research study in which one acquisition process involving the U.S. Government and one key supplier was analyzed and redesigned. The results of the study support the key assumption on which InfoDesign was built — that current business process redesign approaches should focus on information flows rather than activity flows.


Teaching the Use of Complex and Domain-specific IT Applications

Previous research on IT fluency points at the increasing need for more “realistic” courses teaching the use of complex and domain-specific IT applications. That research also suggests certain desirable course design characteristics, of which one of the most important is the close integration of realistic case study-based material into one single course (as opposed to the less costly alternative of inserting single case study-based material into other courses). This project is aimed at testing this and other related hypotheses. A study was conducted in which the use of case study-based learning modules in an integrated way (i.e., as part of one main course) was compared against the use of those modules in isolation (i.e., inserted into other courses). The modules were designed to teach complex and domain-specific IT applications in three main domains – anthropology, sociology, and chemistry. The study, which involved 76 undergraduate students, suggests that the integration of modules into one single course, when compared with the option of using the modules in isolation, significantly increased the level of perceptions of IT's potential for solving complex problems, perceived learning about specialized IT applications, and perceived learning about IT issues in general. The key conclusion of the study is that integration may be a desirable option regardless of the potential extra costs involved.


Simulated Web-based Threats and Their Impact on Knowledge Communication Effectiveness

Arguably it is evolutionarily adaptive for humans to have enhanced memories of events surrounding surprise situations, because in our ancestral past surprise situations were often associated with survival threats. Vividly remembering memories immediately before and after a snake attack, for example, allowed our hominid ancestors to be better prepared to avoid and deal with future attacks, which in turn enhanced their chances of survival. The goal of this project is to show that such enhanced memorization capacity likely endowed on us by evolution can be exploited for knowledge communication through computer interfaces. A pilot knowledge communication experiment was conducted in which subjects were asked to review Web-based learning modules about International Commercial Terms (Incoterms), and then take a test on what they had learned. Data from six learning modules in two experimental conditions were contrasted. In the treatment condition a Web-based screen with a snake picture in attack position, displayed together with a hissing background noise, was used to create a simulated threat that surprised the subjects. In the control condition the simulated threat was absent. As expected based on the evolutionary psychological view that surprise can enhance learning, the subjects in the treatment condition (i.e., with the snake screen) did approximately 28 % better than those in the control condition (i.e., without the snake screen) at learning about Incoterms. This improvement occurred only for the two Web-based modules immediately before and after the snake screen. Those two modules comprise what is referred to as the surprise zone. There were no significant differences in learning performance between the two experimental conditions for modules outside the surprise zone.


Media Naturalness and Compensatory Encoding

Compensatory adaptation theory makes two key predictions. On one hand, the theory predicts that electronic communication media in general will pose obstacles to complex communication between collaborators, when compared with the face-to-face medium, which will lead to an increase in cognitive effort and communication ambiguity. On the other hand, the theory also predicts that those obstacles will be met with compensatory adaptation, whereby electronic communication users will attempt to make up for the obstacles by modifying their communication behavior. This will in turn lead to a reduction in communication fluency. The goal of this project is to extend compensatory adaptation theory by also predicting that the burden of compensating for electronic communication media obstacles will fall primarily on those who attempt to convey information, as opposed to those who receive it. Those predictions were tested through an experiment involving university students, and whose data were analyzed through nonparametric tests. All predictions are generally supported by the data analysis results. The use of a Web-based quasi-synchronous electronic communication medium, when compared with the face-to-face medium, increased perceived cognitive effort by approximately 12% and perceived communication ambiguity by about 19%. Communication fluency was reduced by about 90%. Perceived compensatory encoding effort (i.e., the effort spent by information givers) was increased by approximately 26%, and perceived compensatory decoding effort (i.e., the information receivers’ effort) by a statistically insignificant percentage.


Business Processes Improvement by Virtual Teams Interacting through Electronic Media

Behavior toward electronic communication media continues to present contradictory characteristics that often puzzle researchers. A review of past research on electronic communication suggests two possible reasons for this: a dearth of studies addressing complex problems faced by organizations through the use of electronic communication, and a lack of theoretical frameworks that incorporate apparent contradictions in electronic communication behavior. The goal of this project is to address these two limitations. The first limitation is addressed through the choice of an applied field research approach, namely action research. The second limitation is addressed through the use of a theoretical model to guide our study, the compensatory adaptation model, which addresses contradictory characteristics associated with behavior toward electronic communication media found in past research. A study was conducted in which we investigated the impact of the use of an asynchronous and distributed electronic communication tool on 8 business process improvement groups, 4 in New Zealand and 4 in the USA. The study suggests that even though the use of electronic communication media seems to increase the cognitive effort required from group members, it has a positive impact on knowledge sharing among group members and group outcome quality. These results are consistent across countries, and generally support predictions based on the compensatory adaptation model.


Communication Flow Orientation in Business Process Modeling and Its Effect on Redesign Success

Business process redesign has been intensely studied, particularly since the mid 1990s. One aspect that received little attention, however, is the relationship between business process modeling choices and redesign success. This project aims at addressing this research gap. A multi-methods pilot study of 18 business process redesign projects was conducted in 18 different organizations as part of this project. A structural equation model was developed and tested based on data collected from those projects; and the results were then triangulated with qualitative data. The structural equation model depicted relationships between the following broad perceptual constructs: communication flow orientation of a business process model, quality of a business process model, and business process redesign success. The communication flow orientation of a business process model is defined as the extent to which a model explicitly shows how communication interactions take place in a process. A model’s perceived quality is defined as the degree to which the model presents the following perceptual sub-constructs: ease of generation, ease of understanding, completeness, and accuracy. The results of the study suggest that the degree of communication flow orientation of a business process model is significantly related to the model’s perceived quality. Perceived model quality, in turn, is significantly related to perceived business process redesign success. Interestingly, a business process model’s perceived completeness does not seem to be influenced by a model’s communication flow orientation. The structural equation model accounted for 56 percent of the explained variance in the business process redesign success construct. The main implication of this study is that a focus on communication flows in business processes is an important ingredient in successful business process redesign projects.