Statistics – A Basic (and Gentle) Look


Introduction: The study of statistics in the context of computers and databases comprises only a small subset of the field of statistics. In general, one is concerned with what are termed "Descriptive Statistics". As the name implies these statistical analyses provide a descriptive view of the data. The table below summarizes the major types of analyses.


Statistical Test

Description

Mean

Also known as average the mean is the sum of the values divided by the number of cases.

Median

Similar to the mean the median indicates the middle number when the data set is arranged in either ascending or descending order.

Range

Shows the difference between the largest value and the smallest value in the data set.

Standard Deviation

Shows the measure of variability of a data set. The larger the standard deviation the higher the variability of the data. A useful tool in using the standard deviation is Chebyshev's Rule which states that at least 75% of the data will fall within two standard deviations of the mean, regardless of the shape of the frequency distribution. Also, the rule states, that at least 89% will fall with three standard deviations of the mean.


Histogram (Bar Chart)

There are several types of ways to represent the data set graphically. The most common one dimensional type is known as the histogram (or frequency distribution). This graph will show the number of cases corresponding to a given range of values. This graphical tool will allow one to determine the distribution of values and to assess the "normality" of the data set.

XY Plot

A common two-dimensional graph is the XY plot, where one value in the distribution (the X value) is plotted against another (the Y value). A plot of this type will show if the data set is linearly dependent. A common XY plot for our purposes is to plot the two dimension (size) variables of a building or lot. The "tighter" the spread of the plot the more linear the relationship between the variables.

PREVIOUS: Introduction to Data

NEXT: Data and Computers

HOME: Computers in Historical/Architectural Research

©2001, Richard E. Stevens
Math Sciences, University of Delaware

Comments? rstevens@math.udel.edu