Introduction to Research Design and Statistics

Measurement Scales


ScaleDefinitionExample
NominalMeasures without order, simply indicates that two or more classifications are different. Numbers are used to name categories. Types of schools; comprehensive, vocational, private, college prep, etc.
OrdinalMeasures with order, indicates that the measurement classifications are different and can be ranked. No information about the distance between values. The letter grading system.
IntervalMeasures with order and establishes numerically equal distances on the scale. Performance on a standardized achievement test.
RatioMeasures have equal intervals and a 'true' zero point. Number of correct items on a test.
Quasi-intervalAn unofficial type of scaling that falls between ordinal and interval. Technically ordinal but can be analyzed as if it were interval. Usually there are five or more levels of the variable.Some Likert scaled items: (strongly agree) 7 6 5 4 3 2 1 (strongly disagree)

Note: Variables that are nominal or ordinal scaled are said to be discrete, while interval and ratio scaled variables are considered to be continuous.

Here are several examples:

age --  mean: 44.415 range: 18/89

marital
1  never married
2  married
3  divorced
4  separated
5  widowed

education 
1  less than high school
2  some high school
3  finished high school
4  some college
5  graduate college

employ
1  full time
2  part time
3  unemployed
4  retired
5  houseperson
6  in school
7  other

income -- mean: 20.5748  range: 2/65

religion
1  protestant
2  catholic
3  jewish
4  none

ses
1 low
2 middle
3 high

health
1  excellent
2  good
3  fair
4  poor

iq -- mean: 107  range: 89/134

like_math
1 strongly disagree
2 disagree
3 undecided
4 agree
5 agree strongly

age_group
 1 18/25
 2 26/35
 3 36/45
 4 46/55
 5 56/65
 6 66/70
 7 71/75
 8 76/80
 9 81/85
10 86/90

like_my_job
1 strongly disagree
2 disagree
3 undecided
4 agree
5 agree strongly
6 not applicable


Intro Home Page

Phil Ender, 30Jun98