Making Statistics More Effective for Schools of Business sessions for DSI 2013
This page last updated on February 27, 2014 by Robert L. Andrews, Department of Supply Chain Management and Analytics, Virginia Commonwealth University
General information about Making Statistics More Effective in Schools of Business

Click the link associated with a presenter's name to download their presentations. Not all presenters provided their presentations.

Increase Relevance by Shifting Focus Away from Classical Statistical Mechanics & Hypothesis Testing
8:30 to 10:00, Saturday, November 16, 2013; Session Chair: Robert Andrews (Virginia Commonwealth University)
Abstract: Instruction that focuses on statistical mechanics and hypothesis testing does not fully prepare students for a future that will use a wide variety and volume of data to provide information for strategic and tactical decision making. This session will discuss ways to better prepare students to do analysis for decision making; effectively interpret and communicate analysis results to be useful to a decision maker; understand data mining analysis tools and how they can be used; as well as introducing students to analysis of text data in addition to categorical and quantitative data.
Wilma Andrews (Virginia Commonwealth University) [session intro]
Webster West (Integrated Analytics LLC/North Carolina State University) [What Should We Teach in an Intro Stat Course?]
Malliaris (Loyola University Chicago) [Data Mining Tools for Decision Making]
Kellie B Keeling (University of Denver) [Intro to Analsis of Text Data]
Thomas W. Jones (University of Arkansas) [How Students Have Difficulty in Applying Statistical Thinking]

Developing Studentsí Communications Skills
10:30 to 12:00, Saturday, November 16, 2013; Session Chair: Keith Ord (Georgetown University)
Abstract: When recruiters are asked about the skills they are looking for in prospective employees, communications skills often feature near the top of the list. The first statistics course typically occurs early in a degree program and so it offers an opportunity to enable students to develop communications skills along with the ability to present technical material in a non-technical way. The panel provides an employer's eye view of the skills required in the workplace, along with two examples of classroom pedagogy designed to emphasize applied statistical design and analyses by promoting communication of statistical results using real life data.
David R. Morganstein (Westat) [What Does the Workplace Need?]
Amy Luginbuhl Phelps (Duquesne University) [Write What? I thought this was a Math class.]
Mark Ferris (Saint Louis University)

Should B-Schools Embrace AP Statistics?
1:30 to 3:00 Saturday, November 16, 2013; Session Chair: John McKenzie (Babson College)
Abstract: The number of high-schoolers taking AP Statistics continues to rise dramatically and many of these students are among the best applicants to our programs. One response is to ignore the qualification and have all students complete the same core course(s) in statistics. Another approach is to provide a special course for suitably qualified candidates. We describe one such course and discus show well it has met the needs of both students and the program. This session will examine the impact AP statistics has on a student's academic success in college, as well as share the success of a course designed especially for students who have taken AP statistics. These initial presentations are designed to promote active audience participation.
Keith Ord, (Georgetown University) [What is AP Statistics?]
Norean Sharpe (Georgetown University) [AP Credit Impact on GPA]
Victor Richmond Jose (Georgetown University)

A Course in Data Discovery and Predictive Analytics
3:30 to 5:00pm, Saturday, November 16, Session Chair: Robert Andrews (V.C.U.)
Abstract: Presentation will lay out general principles of using big data and data discovery and include a detailed week by week list of topics and recommend software for the course. It will include discussion of how Excel can be used for part of the course and the remainder will address predictive analytical methods such as classification and regression trees, chi-square interaction detectors, neural nets, cluster analysis and multidimensional scaling.
Presenters: David M. Levine (Baruch College (CUNY), Kathryn Szabat (LaSalle University) & David Stephan (Two Bridges Instructional Technology)
Session PowerPoint

Creating a Business Analytics Class
8:30 to 10:00am, Sunday, November 17, Session Chair: Robert Andrews (V.C.U.)
Abstract:† This session will feature a discussion of four institution's recently developed analytics courses that include delivery at both the undergraduate and master's levels and both face-to-face and as a hybrid course. These courses use a variety of analysis tools including Excel and Excel add-ins, SAS Academic Enterprise Miner and JMP. Topics covered include data visualization, dashboards, big data, probability modeling, simulation and optimization.
Presenters: Kirk Karwan (Furman University) [Creating Analytics Class at Furman]
James R Evans (University of Cincinnati) Session PowerPoint
Bob McQuaid (Pepperdine University)
Mark L Berenson (Montclair State University) [Stat Course for Big Data & Analytics]

Sports Analytics (DSI Keynote Speech),
10:30 to 12:00,Sunday, November 17, Session Chair: Funda Sahin (U. Houston)
Beginning with Michael Lewis' Moneyball there has been increasing interest in how analytics can improve performance of sports teams. We will give a primer describing the analytics used by baseball, football, and basketball teams to improve player selection, lineup selection, and in game decision making.
Speaker: Wayne Winston (Indiana University)

Experiences and Advice on Including Analytics in the Curriculum
1:30 to 3:00pm, Sunday, November 17, Session Chair: Robert Andrews (V.C.U.)
Abstract: The presenters will relate their experience at their respective institutions with adding analytics to the curriculum ranging from an undergraduate analytics minor to an entire full-time analytics master's degree. Topics to be discussed include: software to be used for the program; amount of focus given to obtaining and preparing data for analysis; proper balance between using off-the-shelf software and providing mathematical understanding of techniques; amount of teamwork; amount of application domain knowledge required; and emphasis on communication skills.
Presenters: Satish Nargundkar (Georgia State University) [Georgia State Analytics]
Aric LaBarr (Institute for Advanced Analytics at North Carolina State) [Analytics Education and The Evolving Workforce]
Bob McQuaid (Pepperdine University)
Kirk Karwan (Furman University) [Analytics Curriculum]

Implications of Big Data for Statistics Instruction
3:30 to 5:00pm, Sunday, November 17, Session Chair: Robert Andrews (V.C.U.)
Abstract: Covering standard descriptive and inferential methods does not adequately prepare students to analyze 'Big Data' that come from a variety of sources such as social networking activities, on-line searches, customer purchases, financial transactions, genetic sequences, and astronomical transmissions. This session will consider proposals for better preparing students for big data in an applied statistics course. These will include lessons that can be taught with little data that matter when you model big data.
Robert A. Stine (Wharton School of the Univ. Pennsylvania) [Getting Ready for Big Data]
John McKenzie (Babson College) [Introducing Big Data into Stat101]
Mark L Berenson (Montclair State University) [Big Data Implications for Stat Analysis & Instruction]

Software Tools for Data Visualization
8:30 to 10:00am, Monday, November 18, Session Co-chairs: Kellie Keeling (U. Denver) & Robert Andrews (V.C.U.)
Abstract: Data visualization is an important if not the most important tool for effectively using data to tell a story so the desired audience gets the correct picture and understanding. This session will feature live demonstrations of the visualization capabilities of the current professional software tools JMP, IBM/Cognos and SAS visualization.
Session Organizers: Curt Hinrichs (JMP Academic Group, SAS Institute, Inc.) & Penelope Gardner (IBM)
Presenters: Mia L Stephens (SAS, JMP Division), Matt Tyler (IBM) & Michael Speed (SAS Institute)

Transforming the Data Deluge into Data-Driven Insights: Analytics that Drive Business (DSI Keynote Speech)
10:30 to 12:00pm, Monday, November 18,Session Chair: Funda Sahin(U. Houston)
Computing power and access to multi-processor hardware configurations enables us to solve increasingly complex problems in a fraction of the time it used to take earlier.
Speaker: Radhika Kulkarni (SAS Institute Inc.)

Statistics for Decision Making in the Twenty-First Century
1:30 to 3:00pm, Monday, November 18, Session Chair: Robert Andrews (V.C.U.)
Abstract: As big data become more central to commerce, our graduates need an updated view of statistics. Data management must move beyond the spreadsheet as data analysis progresses beyond trends and tests. Multivariate data and models were once regarded as too advanced for the introductory course, but to make effective decisions the modern manager needs to know how to deal with complex relationships. How can we have time to teach basic statistics as well as the formerly advanced topics that are needed in today's environment? We'll describe new approaches that make it feasible to bring seemingly advanced material into the introductory course.
Presenters: Richard DeVeaux (Williams College)
Daniel Kaplan (Macalester College)

Tips and Experiences from Efforts to Improve the Statistics Class
3:30 to 5:00pm, Monday, November 18, Session Chair: Robert Andrews (V.C.U.)
Abstract: This session presents numerous efforts used to improve the statistics class. The topics include using an introductory activity to tie together material and provide a solid foundation; using a set of mini-cases for Baltimore area data; "flipping" the classroom to a hybrid delivery format; and developing p-values using the binomial and median test rather than the usual normal based approach. Come and discuss these to see if any of these ideas can help you improve your class.
Presenters: Mark Eakin (UT - Arlington) [Simplifying Framework for an Intro Stats Class]
[Excel File for a Simplifying Framework for an Intro Stats Class]
Maria Gisela Bardossy (University of Baltimore) [Mini-Cases using Baltimore data]
Joseph G Van Matre (UAB) [Teaching Testing, P-Values, & CIs without the Normal Dist.]
Raj Sampath (DeVry University) [Class Delivery Methods]

Making Statistics More Effective in Schools of Business DSI Specific Interest Group Caucus Meeting
5 pm, Monday, November 18, Session Chair: Robert Andrews (V.C.U.)
2013 Report for the Making Statistics More Effective in Schools of Business DSI Specific Interest Group

General information about Making Statistics More Effective in Schools of Business