Problems With Using Microsoft Excel for Statistics

Short Description
formula given, the so-called “computing formula,” is. well-known to be a very poor way to compute a standard. deviation. We return to this below. Excel is …

Website: oit.utk.edu | Filesize: 412kb

Content
Problems With Using Microsoft
Excel for Statistics
Jonathan D. Cryer
(Jon-Cryer@uiowa.edu)
Department of Statistics and Actuarial Science
University of Iowa, Iowa City, Iowa
Joint Statistical Meetings
August 2001, Atlanta, GA
In this talk I will illustrate Excel’s serious deficiencies
in five areas of basic statistics:
Graphics
Help Screens
Computing Algorithms
Treatment of Missing Data
and
Regression
We begin with basic graphics.
Good Graphs Should:
4 Portray Numerical Information Visually
Without Distortion
4 Contain No Distracting Elements (e.g., no false
third dimensions nor “chartjunk”)
4 Label Axes (Scales) and Tick Marks
Appropriately
4 Have a Descriptive Title and/or Caption and
Legend
(References: Cleveland (1993, 1994) and Tufte
(1983, 1990, 1997))
However, Excel meets virtually none of these
criteria. As our first example illustrates, Excel offers
false third dimensions on the vast majority of its graphs.
(Unfortunately, this example is taken from the Journal
of Statistical Education.)
Example: Excel Graphics With False Third
Dimension (taken from JSE!)
The vast majority of Chart types offered by Excel
should NEVER be used!
Our next example shows the graph-types available as
pyramid charts. None of these choices shown below
represent…