Online Program

Return to main conference page

All Times ET

Program is Subject to Change

Wednesday, June 16
Wed, Jun 16, 10:30 AM - 12:00 PM
TBD
Dealing with Missing and Erroneous Data in Establishment Statistics

Clean, Rinse, Repeat: Student Perceptions of Dirty Data (308032)

*Elizabeth Keiffer, University of Arkansas 

Keywords: Missing Data, Education

The increasing need for data driven decision making in all areas of commerce has increased the number of analytically experienced and inexperienced employees interacting with establishment data. Perceptions of these decision makers, especially those not experienced with dirty data and its effect on decisions, are the topic of interest in this study. Analytics programs, especially in business schools, have an opportunity to identify and then, if needed, attempt to modify student perceptions of dirty data and its potential effects on business decisions. Data were collected from graduate business students, mostly working professionals (mean work experience = 7 years), in a masters of information systems program. Multiple methods including class assignments, class discussions, surveys and interviews were used to discover perceptions. Initial perceptions vary widely from removing all dirty data to researching and correcting all dirty data and seem to change depending on the size of the data set under consideration. A brief discussion of current curriculum from one large university business analytics program and how it attempts to modify those perceptions will be addressed.