An Examination of Using EWMA Charts for Monitoring United States Geospatial Data
Presentation Type
Oral and/or Visual Presentation
Presenter Major(s)
Statistics
Mentor Information
Paul Stephenson, stephenp@gvsu.edu
Department
Statistics
Location
Kirkhof Center 2259
Start Date
13-4-2011 2:00 PM
End Date
13-4-2011 2:30 PM
Keywords
Health and Wellness, Health, Illness, and Healing, Mathematical Science, Technology
Abstract
Geographic Information Systems (GIS) are a very helpful tool used to accumulate and present data. Although they are useful in displaying patterns and making inference about them, they can be misleading without the proper statistical methods. The authors will examine how Moran's I statistic changes for patterns of increasing spatial depression. They will also demonstrate how to create an "Exponentially Weighted Moving Average" (EWMA) control chart for global spatial statistics and monitor these charts over time. In the event that a control chart signals [WHAT?], one can then examine the local spatial statistics to determine the source of the signal. In an effort to examine the power associated with these monitoring procedures, the authors will also simulate the effect of an increase in one, two or three regions in the United States. The results of these simulations will be used to characterize the effects of shifts in the spatial dispersion across the United States.
An Examination of Using EWMA Charts for Monitoring United States Geospatial Data
Kirkhof Center 2259
Geographic Information Systems (GIS) are a very helpful tool used to accumulate and present data. Although they are useful in displaying patterns and making inference about them, they can be misleading without the proper statistical methods. The authors will examine how Moran's I statistic changes for patterns of increasing spatial depression. They will also demonstrate how to create an "Exponentially Weighted Moving Average" (EWMA) control chart for global spatial statistics and monitor these charts over time. In the event that a control chart signals [WHAT?], one can then examine the local spatial statistics to determine the source of the signal. In an effort to examine the power associated with these monitoring procedures, the authors will also simulate the effect of an increase in one, two or three regions in the United States. The results of these simulations will be used to characterize the effects of shifts in the spatial dispersion across the United States.