Measurement Scales

The type of data collected determines the appropriate measurement scale, and the measurement
scale, in turn, determines the appropriate statistical procedure for analyzing particular data and
drawing conclusions from that data. Each type of measurement scale has a specific use.

Nominal scales. Nominal scales are composed of sets of categories in which objects are
classified. For example, a nominal scale dealing with household pets might include the
categories dogs, cats, birds, and fish. Data used in the construction of a nominal scale are
frequency data, the number of subjects in each category (in this case, the number of animals for
each type of pet).

Ordinal scales. Ordinal scales indicate the order of the data according to some criterion. For
example, a researcher might ask people to rank their preference for types of household pets, with
1 as the most preferred and 4 as the least preferred (resulting in, perhaps, 1‐dogs, 2‐cats, 3‐birds,
4‐fish). Ordinal scales tell nothing about the distance between units of the scale (for example,
although dogs may be preferred to cats, no information is available about the extent of that
preference) and supply information only about order of preference.

Interval scales. Interval scales have equal distances between scale units and permit statements
to be made about those units as compared to other units (that is, one unit may be a certain
number of units higher or lower than another), but they do not allow conclusions that one unit is
a particular multiple of another because on interval scales there is no zero. That is, the scale does
not allow for the complete absence of the phenomenon being measured. For example, if you
refer to the interval scale used on a thermometer, you can say that 88 degrees is 2 degrees higher
than 86 degrees, but you cannot accurately say that 88 degrees is twice as hot as 44 degrees
because there is never a situation of no heat at all. (The zero on a thermometer doesn't indicate a
complete lack of heat, only one more unit on the scale, which continues downward.) Interval
scales, then, permit a statement of “more than” or “less than” but not of “how many times more.”

Ratio scales. Ratio scales have equal distances between scale units as well as an absolute zero.
If you're measuring the height of two trees and tree A is 36 inches tall and tree B is 72 inches tall,
you can accurately say that B is twice as tall as A. There is a condition of zero height. Most
measures encountered in daily living are based on a ratio scale.

Continuous and discontinuous scales. Measures may also be categorized according to

continuity and discontinuity. A continuous scale is one in which the variable under
consideration can assume an infinite number of values. A person's height, for example, might be
expressed in an infinite number of ways, ranging from feet, to inches, to tenths of inches, to
hundredths of inches, and so forth according to how small or large a measurement one wants to
make. On the other hand, discontinuous, or discrete, scales express the measurement of the
variable under consideration in a finite number of ways, as, for example, in a frequency
distribution such as the number of students in a psychology department or the number of players
on a team.

1|Page
Levels of measurement

Most texts on marketing research explain the four levels of measurement: nominal, ordinal,
interval and ratio and so the treatment given to them here will be brief. However, it is an
important topic since the type of scale used in taking measurements directly impinges on the
statistical techniques which can legitimately be used in the analysis.

Nominal scales

This, the crudest of measurement scales, classifies individuals, companies, products, brands or
other entities into categories where no order is implied. Indeed it is often referred to as a
categorical scale. It is a system of classification and does not place the entity along a continuum.
It involves a simply count of the frequency of the cases assigned to the various categories, and if
desired numbers can be nominally assigned to label each category as in the example below:

Figure 3.1 An example of a nominal scale

Which of the following food items do you tend to buy at least once per month? (Please tick)
Okra Palm Oil Milled Rice
Peppers Prawns Pasteurised milk

The numbers have no arithmetic properties and act only as labels. The only measure of average
which can be used is the mode because this is simply a set of frequency counts. Hypothesis tests
can be carried out on data collected in the nominal form. The most likely would be the Chi-
square test. However, it should be noted that the Chi-square is a test to determine whether two or
more variables are associated and the strength of that relationship. It can tell nothing about the
form of that relationship, where it exists, i.e. it is not capable of establishing cause and effect.

Ordinal scales

Ordinal scales involve the ranking of individuals, attitudes or items along the continuum of the
characteristic being scaled. For example, if a researcher asked farmers to rank 5 brands of
pesticide in order of preference he/she might obtain responses like those in table 3.2 below.

2|Page
Figure 3.2 An example of an ordinal scale used to determine farmers' preferences among 5
brands of pesticide.

Order of preference Brand

1 Rambo
2 R.I.P.
3 Killalot
4 D.O.A.
5 Bugdeath

From such a table the researcher knows the order of preference but nothing about how much
more one brand is preferred to another, that is there is no information about the interval between
any two brands. All of the information a nominal scale would have given is available from an
ordinal scale. In addition, positional statistics such as the median, quartile and percentile can be
determined.

It is possible to test for order correlation with ranked data. The two main methods are Spearman's
Ranked Correlation Coefficient and Kendall's Coefficient of Concordance. Using either
procedure one can, for example, ascertain the degree to which two or more survey respondents
agree in their ranking of a set of items. Consider again the ranking of pesticides example in
figure 3.2. The researcher might wish to measure similarities and differences in the rankings of
pesticide brands according to whether the respondents' farm enterprises were classified as
"arable" or "mixed" (a combination of crops and livestock). The resultant coefficient takes a
value in the range 0 to 1. A zero would mean that there was no agreement between the two
groups, and 1 would indicate total agreement. It is more likely that an answer somewhere
between these two extremes would be found.

The only other permissible hypothesis testing procedures are the runs test and sign test. The runs
test (also known as the Wald-Wolfowitz). Test is used to determine whether a sequence of
binomial data - meaning it can take only one of two possible values e.g. African/non-African,
yes/no, male/female - is random or contains systematic 'runs' of one or other value. Sign tests are
employed when the objective is to determine whether there is a significant difference between
matched pairs of data. The sign test tells the analyst if the number of positive differences in
ranking is approximately equal to the number of negative rankings, in which case the distribution
of rankings is random, i.e. apparent differences are not significant. The test takes into account

3|Page
only the direction of differences and ignores their magnitude and hence it is compatible with
ordinal data.

Interval scales

It is only with an interval scaled data that researchers can justify the use of the arithmetic mean
as the measure of average. The interval or cardinal scale has equal units of measurement, thus
making it possible to interpret not only the order of scale scores but also the distance between
them. However, it must be recognized that the zero point on an interval scale is arbitrary and is
not a true zero. This of course has implications for the type of data manipulation and analysis we
can carry out on data collected in this form. It is possible to add or subtract a constant to all of
the scale values without affecting the form of the scale but one cannot multiply or divide the
values. It can be said that two respondents with scale positions 1 and 2 are as far apart as two
respondents with scale positions 4 and 5, but not that a person with score 10 feels twice as
strongly as one with score 5. Temperature is interval scaled, being measured either in Centigrade
or Fahrenheit. We cannot speak of 50°F being twice as hot as 25°F since the corresponding
temperatures on the centigrade scale, 10°C and -3.9°C, are not in the ratio 2:1.

Interval scales may be either numeric or semantic. Study the examples below in figure 3.3.

Figure 3.3 Examples of interval scales in numeric and semantic formats

Please indicate your views on Balkan Olives by scoring them on a scale of 5 down to 1 (i.e. 5 =
Excellent; = Poor) on each of the criteria listed
Balkan Olives are: Circle the appropriate score on each line
Succulence 5 4 3 2 1
Fresh tasting 5 4 3 2 1
Free of skin blemish 5 4 3 2 1
Good value 5 4 3 2 1
Attractively packaged 5 4 3 2 1
(a)

Please indicate your views on Balkan Olives by ticking the appropriate responses below:

4|Page
 Excellent Very Good Good Fair Poor
Succulent
Freshness
Freedom from skin blemish
Value for money
Attractiveness of packaging
(b)

Most of the common statistical methods of analysis require only interval scales in order that they
might be used. These are not recounted here because they are so common and can be found in
virtually all basic texts on statistics.

Ratio scales

The highest level of measurement is a ratio scale. This has the properties of an interval scale
together with a fixed origin or zero point. Examples of variables which are ratio scaled include
weights, lengths and times. Ratio scales permit the researcher to compare both differences in
scores and the relative magnitude of scores. For instance the difference between 5 and 10
minutes is the same as that between 10 and 15 minutes, and 10 minutes is twice as long as 5
minutes.

Given that sociological and management research seldom aspires beyond the interval level of
measurement, it is not proposed that particular attention be given to this level of analysis. Suffice
it to say that virtually all statistical operations can be performed on ratio scales.

Levels of Measurement

The Level of measurement of a variable is a critical factor in determining what kinds of tools
may be used to describe the variable, and what means of analysis may be used for inference

5|Page
about the variable. In short, the level of measurement determines or constrains the types of
descriptive and inferential statistics that may be applied to the variable.

Levels of Measurement

 Nominal
 Ordinal
 Interval

In addition, there are two other categories that often get used

 Dictotomous (often treated as Nominal)

 Ratio (often treated as Interval)

Dichotomous variables are variables that only have two values. This level of measurement may
be treated as nominal, however, sometimes an ordinal quality may exist.

Some examples

 Gender - male, female

 Race - black, white
 Agreement - yes, no
 T/F - true, false
 Value - high, low
 and others less easy to name
o war, no war
o vote, no vote

Nominal Variables

Nominal variables are those which can be named, but not quantified. Examples include

 Religion (Protestant Catholic, Hebrew, Buddhist, etc)

 Race (Caucasian, African-American, Hispanic,Asian, etc)
 Linguistic Group
 Marital Status (Married, Single, Divorced)

Nominal variables may be coded with numbers, but the magnitude of the number assigned is
arbitrary. Changing the coding scheme will not change the inference.

Ordinal Variables

6|Page
With ordinal variables, there is a rough quantitative sense to their measurement, but the
differences between scores are not necessarily equal. They are thus in order, but not fixed.

 Rankings (1st, 2nd, 3rd, etc)

 Grades (A, B, C, D. F)
 Evaluations
o Hi, Medium, Low
o Likert Scales
 5 pt (Strongly Agree, Agree, Neither Agree nor Disagree, Disagree,
Strongly Disagree)
 7 pt liberalism scale (Strongly Liberal, Liberal, Weakly Liberal, Moderate,
Weakly Conservative, Conservative, Strongly Conservative)

Interval Variables

Variables or measurements wghere the difference between values is measured by a fixed scale.

 Money
 People
 Education (in years)

Ratio variables on the other hand are at the other end of the scale. Ratio variables are numbers
with some base value. Percentages are perhaps the best indicator here.

Types of Data & Measurement Scales: Nominal, Ordinal, Interval and Ratio
November 28, 2012 - Data Analysis - Tagged: data analysis, statistics - 5 comments

There are four measurement scales (or types of data): nominal, ordinal, interval and ratio.  These
are simply ways to categorize different types of variables.  This topic is usually discussed in the
context of academic teaching and less often in the “real world.”  If you are brushing up on this
concept for a statistics test, thank a psychologist researcher named Stanley Stevens for coming
up with these terms.  These four measurement scales (nominal, ordinal, interval, and ratio) are
best understood with example, as you’ll see below.

Nominal
Let’s start with the easiest one to understand.  Nominal scales are used for labeling variables,
without any quantitative value.  ”Nominal” scales could simply be called “labels.”  Here are
some examples, below.  Notice that all of these scales are mutually exclusive (no overlap) and
none of them have any numerical significance.  A good way to remember all of this is that
“nominal” sounds a lot like “name” and nominal scales are kind of like “names” or labels.

7|Page
 Examples of Nominal Scales

Note: a sub-type of nominal scale with only two categories (e.g. male/female) is called
“dichotomous.”  If you are a student, you can use that to impress your teacher.

Continue reading about types of data and measurement scales: nominal, ordinal, interval, and
ratio…

Ordinal
With ordinal scales, it is the order of the values is what’s important and significant, but the
differences between each one is not really known.  Take a look at the example below.  In each
case, we know that a #4 is better than a #3 or #2, but we don’t know–and cannot quantify–how
much better it is.  For example, is the difference between “OK” and “Unhappy” the same as the
difference between “Very Happy” and “Happy?”  We can’t say.

Ordinal scales are typically measures of non-numeric concepts like satisfaction, happiness,
discomfort, etc.

“Ordinal” is easy to remember because is sounds like “order” and that’s the key to remember
with “ordinal scales”–it is the order that matters, but that’s all you really get from these.

Advanced note: The best way to determine central tendency on a set of ordinal data is to use the
mode or median; the mean cannot be defined from an ordinal set.

Example of Ordinal Scales

8|Page
Interval
Interval scales are numeric scales in which we know not only the order, but also the exact
differences between the values.  The classic example of an interval scale is Celsius temperature
because the difference between each value is the same.  For example, the difference between 60
and 50 degrees is a measurable 10 degrees, as is the difference between 80 and 70 degrees.  Time
is another good example of an interval scale in which the increments are known, consistent, and
measurable.

Interval scales are nice because the realm of statistical analysis on these data sets opens up.  For
example, central tendency can be measured by mode, median, or mean; standard deviation can
also be calculated.

Like the others, you can remember the key points of an “interval scale” pretty easily.  ”Interval”
itself means “space in between,” which is the important thing to remember–interval scales not
only tell us about order, but also about the value between each item.

Here’s the problem with interval scales: they don’t have a “true zero.”  For example, there is no
such thing as “no temperature.”  Without a true zero, it is impossible to compute ratios.  With
interval data, we can add and subtract, but cannot multiply or divide.  Confused?  Ok, consider
this: 10 degrees + 10 degrees = 20 degrees.  No problem there.  20 degrees is not twice as hot as
10 degrees, however, because there is no such thing as “no temperature” when it comes to the
Celsius scale.  I hope that makes sense.  Bottom line, interval scales are great, but we cannot
calculate ratios, which brings us to our last measurement scale…

Example of Interval Scale

Ratio

Ratio scales are the ultimate nirvana when it comes to measurement scales because they tell us
about the order, they tell us the exact value between units, AND they also have an absolute zero–
which allows for a wide range of both descriptive and inferential statistics to be applied.  At the
risk of repeating myself, everything above about interval data applies to ratio scales + ratio scales
have a clear definition of zero.  Good examples of ratio variables include height and weight.

9|Page
Ratio scales provide a wealth of possibilities when it comes to statistical analysis.  These
variables can be meaningfully added, subtracted, multiplied, divided (ratios).  Central
tendency can be measured by mode, median, or mean; measures of dispersion, such as standard
deviation and coefficient of variation can also be calculated from ratio scales.

This Device Provides Two Examples of Ratio Scales (height and weight)

Summary
In summary, nominal variables are used to “name,” or label a series of values.  Ordinal scales
provide good information about the order of choices, such as in a customer satisfaction survey.
Interval scales give us the order of values + the ability to quantify the difference between each
one.  Finally, Ratio scales give us the ultimate–order, interval values, plus the ability to
calculate ratios since a “true zero” can be defined.

Summary of data types and scale measures

10 | P a g e
Measurement scales
A topic which can create a great deal of confusion in social and educational research is
that of types of scales used in measuring behavior.

It is critical because it relates to the types of statistics you can use to analyze your data.
An easy way to have a paper rejected is to have used either an incorrect scale/statistic
combination or to have used a low powered statistic on a high powered set of data.

 Nominal
 Ordinal
 Interval
 Ratio

Nominal

The lowest measurement level you can use, from a statistical point of view, is a
nominal scale.

A nominal scale, as the name implies, is simply some placing of data into
categories, without any order or structure.

A physical example of a nominal scale is the terms we use for colours. The
underlying spectrum is ordered but the names are nominal.

In research activities a YES/NO scale is nominal. It has no order and there is no

distance between YES and NO.

and statistics

The statistics which can be used with nominal scales are in the non-
parametric group. The most likely ones would be:

mode
crosstabulation - with chi-square
There are also highly sophisticated modelling techniques available for
nominal data.

11 | P a g e
Ordinal

An ordinal scale is next up the list in terms of power of measurement.

The simplest ordinal scale is a ranking. When a market researcher asks you to
rank 5 types of beer from most flavorful to least flavorful, he/she is asking you
to create an ordinal scale of preference.

There is no objective distance between any two points on your subjective scale.
For you the top beer may be far superior to the second preferred beer but, to
another respondent with the same top and second beer, the distance may be
subjectively small.

An ordinal scale only lets you interpret gross order and not the relative
positional distances.

and statistics

Ordinal data would use non-parametric statistics. These would include:

Median and mode

rank order correlation
non-parametric analysis of variance
Modeling techniques can also be used with ordinal data.

Interval

The standard survey rating scale is an interval scale.

When you are asked to rate your satisfaction with a piece of software on a 7 point
scale, from Dissatisfied to Satisfied, you are using an interval scale.

It is an interval scale because it is assumed to have equidistant points between

each of the scale elements. This means that we can interpret differences in the
distance along the scale. We contrast this to an ordinal scale where we can only
talk about differences in order, not differences in the degree of order.

Interval scales are also scales which are defined by metrics such as logarithms. In
these cases, the distances are not equal but they are strictly definable based on
the metric used.

and statistics

Interval scale data would use parametric statistical techniques:

12 | P a g e
 Mean and standard deviation
Correlation - r
Regression
Analysis of variance
Factor analysis
Plus a whole range of advanced multivariate and modeling techniques

Remember that you can use non-parametric techniques with interval and
ratio data. But non-parametric techniques are less powerful than the
parametric ones.

Ratio

A ratio scale is the top level of measurement and is not often available in social
research.

The factor which clearly defines a ratio scale is that it has a true zero point.

The simplest example of a ratio scale is the measurement of length (disregarding

any philosophical points about defining how we can identify zero length).

The best way to contrast interval and ratio scales is to look at temperature. The
Centigrade scale has a zero point but it is an arbitrary one. The Fahrenheit scale
has its equivalent point at -32o. (Physicists would probably argue that Absolute
Zero is the zero point for temperature but this is a theoretical concept.) So, even
though temperature looks as if it would be a ratio scale it is an interval scale.
Currently, we cannot talk about no temperature - and this would be needed if it
were a ration scale.

and statistics

The same as for Interval data

SCALES OF MEASUREMENT

13 | P a g e
There are four scales (or levels) at which we measure. The lowest level is the nominal scale. This may be
thought of as the “naming” level. For example, when we ask subjects to name their marital status, they
will respond with words—not numbers—that describe their status such as “married,” “single,”
“divorced,” etc. Notice that nominal data do not put subjects in any particular order. There is no logical
basis for saying that one category such as “single” is higher or lower than any other.

The next level is ordinal. At this level we put subjects in order from high to low. For instance, an
employer might rank order applicants for a job on their professional appearance. Traditionally, we give a
rank of 1 to the subject who is highest, 2 to the next highest, and so on. It is important to note that ranks
do not tell us by how much subjects differ. If we are told that Janet has a rank of 1 and Frank has a rank
of 2, we do not know if Janet’s appearance is greatly superior to Frank’s or only slightly superior. To
measure the amount of difference among subjects, we use the next levels of measurement.

Measurements at the interval and ratio levels have equal distances among the scores they yield.
For example, when we say that Jill weighs 120 pounds and Sally weighs 130 pounds, we know by how
much the two subjects differ. Also, note that a 10 pound difference represents the same amount
regardless of where we are on the scale. For instance, the difference between 120 and 130 pounds is the
same as the difference between 220 and 230 pounds.

The ratio scale is at a higher level than the interval scale because the ratio has an absolute zero
point that we know how to measure. Thus, weight is an example of the ratio scale because it has an
absolute zero that we can measure.

The interval scale, while having equal intervals like the ratio scale, does not have an absolute zero.
The most common examples of interval scales are scores obtained using objective tests such as multiple-
choice tests of achievement. It is widely assumed that each multiple-choice test item measures a single
point’s worth of the trait being measured and that all points are equal to all other points—making it an
interval scale (just as all pounds are equal to all other pounds of weight). However, such tests do not
measure at the ratio level because the zero on such tests is arbitrary—not absolute. To see this, consider
someone who gets a zero on a multiple-choice final examination. Does the zero mean that the student
has absolutely no knowledge of or skills in the subject area? Probably not. He or she probably has some
knowledge of simple facts, definitions, and concepts, but the test was not designed to measure at the
skill level at which the student is operating. Thus, a score of zero only indicates that they know nothing
on that test — not that they have zero knowledge of the content domain.

14 | P a g e
 Here’s a summary of the levels:

__________________________________________________________

Lowest

Level Scale Characteristic

__________________________________________________________

Nominal naming

 Ordinal ordering

Interval equal interval without absolute zero

Ratio equal interval with absolute zero

__________________________________________________________

Highest

__________________________________________________________

For those of you who like to use mnemonics when memorizing material, try learning this envi-
ronmentally friendly phrase:

No Oil In Rivers

The first letters NOIR are the first letters of the scales in order from lowest to highest.

At which level should we measure? First, some variables are inherently nominal in nature. For example,
when we need to know subjects’ gender or state of residence, nominal data is the natural choice.
Second, many novice researchers overuse the ordinal scale. For instance, if we want to measure reading
ability, it usually would be much better to use a carefully constructed standardized test (which measures
at the interval level) than having teachers rank order students in terms of their reading ability.
Remember, measuring at the interval level gives you more information because it tells you by how much
students differ. Also, as you will learn when we explore statistics, you can do more interesting and
powerful types of analyses when you measure at the interval rather than the ordinal level. Thus, when
planning instruments for a research project, if you are thinking in terms of having subjects ranked (for
ordinal measurement), you would be well advised to consider whether there is an alternative at the
interval level.

The choice between interval and ratio depends solely on whether it is possible to measure with an
absolute zero. When it is possible, we usually do so. For the purposes of statistical analysis, interval and
ratio data are treated in the same way.

The level at which we measure has important implications for data analysis, so you will find
references to scales of measurement throughout our discussion of statistics.

15 | P a g e
 EXERCISE
1. If we ask subjects to name the country in which they were born, we are using what scale of
measurement?

2. Which two scales of measurement have equal distances among the scores they yield?

3. If we have a teacher rank students according to their oral language skills, we are using which scale of
measurement?

4. Which scale of measurement has an absolute zero that is measured?

5. Which scale of measurement is at the lowest level?

6. Objective, multiple choice achievement tests are usually assumed to measure at what level?

7. If we measure in such a way that we find out which subject is most honest, which is the next most
honest, and so on, we are measuring at what scale of measurement?

8. The number of minutes of overtime work that employees perform is an example of what scale of
measurement?

9. Weight measured in pounds is an example of which scale of measurement?

Questions for Discussion

10. Name a trait that inherently lends itself to nominal measurement. Explain your answer.

II. A researcher plans to rank order ten schools according to the amount of parental involvement in each
school. Could parental involvement be measured at a higher level? Explain.

ANSWERS

1. nominal
2. interval and ratio
3. ordinal
4. ratio
5. nominal
6. interval
7. ordinal
8. ratio
9. ratio
10. Sample answers: religious affiliation, employment status
11. Sample answer: One could develop a measure in which points are awarded to each school
for different types of parental involvement; if each point is assumed to be equal to each of
the other points, the measurements would be at the interval level.

16 | P a g e