An Explanation of Statistical Tools from DocumentingExcellence.com A consulting practice focusing on working with colleges', organizations', and individuals' utilization of quantitative and qualitative assessment tools to analyze and document their quality outcomes through providing staff development, research design and analysis, and psychometric evaluations.

Statistical Tools TOC Analysis Procedures Conceptual Issues Competency Learning Domains Item Construction Item Assessment Scale Construction Measurment Issues Evaluating - Single variable Descriptive statistics Validity, Reliabiltiy, Cause & Effect Reporting Modeling Correlation Regression & Correlation Statistical Control Unemployment & Crime Model Reduction Outcomes Assessment FAQ Consulting Services

Measurement issues

Measurement processes

Understand Measurement scale-characteristics

Issues of scale structure focus on critical characteristics of a scale.  They are significant because these structures limit, in part, which statistical procedures can and should be used in analyzing findings.

	Dichotomies - True/False
	Nominal, categories
	Ordinal, rank
	Interval
	Ratio, counts

	Dichotomies - True/False A scale the measure some phenomena, condition, characteristic  that can have only one of two values is a dichotomous scale.  Example: On-off, male-female, etc.
	Nominal, categories A scale that categorizes or classifies some phenomena as belonging to one and only one classification. Example: Religions: Catholic, Protestant, Jewish, Muslim, Buddhist, Taoist, etc.
	Ordinal, rank A scale that places in order some phenomena. Example: Order of finish: First, second, third Arranging in height: Shortest, 2nd shortest, tallest
	Interval A scale that measures changes in a phenomena where the exact value of 0 is not an absence of the phenomena.  There are many interval scales that we use in everyday life.  The most common is temperature.  With temperature 0 Fahrenheit is not the absence of warmth.  The temperature can go below 0 and this shows that the measurement is not anchored in a 0 that is null or true zero.  The reason this is important is that with interval scales one cannot compare two values.  35 Fahrenheit is NOT 1/2 the heat of 70 Fahrenheit.  One needs to be careful about comparing values on an interval scale with each other.   Example: Temperature scales like Fahrenheit, centigrade.  There is a temperature scale that does have a true 0, it is the Kelvin scale.  At 0 Kelvin the motion of atoms stops, and even in the deepest, coldest outer space 0 Kelvin does not occur.
	Ratio, counts A scale that measures changes in a phenomena where there is a 0 that is the absence of the phenomena, a true 0.  As the name implies, with these scales one can construct a ratio in which 100 is ten times as much of the phenomena as 10. The counts are NOT order, but rather quantity!  Example: Money Weight - a 200 pound person weighs twice as much as a 100 pound person, even though we could never find a 0 pound person.

Send mail to with questions or comments about this web site.
Copyright © 2011 by Peter T. Klassen, Ph.D. Principal, www.DocumentingExcellence.com
21 February, 2011