Download What is the Difference Between Nominal and Ordinal Data?

Nominal is categorical in nature
a.
b.
c.
d.
Name of schools
Car model you drive
Types of books people read
Easy to remember because nominal sounds like name because they have the same Latin
root.
Ordinal refers to quantities that have a natural ordering, rankings
a.
b.
c.
d.
Favorite sports
Peoples place in line
Order of runners finishing a race
Choice on a scale of 1 to 5,
a. On a scale the difference between 9 and 10 not the same as a difference between 6 and
7. or 2 and 3, and, 4 and 5 differences aren’t the same.
b. Easy to remember as ordinal sounds like order.
Interval data is like ordinal except we can say the intervals between each value equally split, so the
differences would be the same.
a. Temperature in Celsius or Fahrenheit (the differences between 29 and 30 degrees F is the
same magnitude as the difference between 78 and 79 degrees Fahrenheit.
b. One step up from an ordinal data.
Ratio Data is interval data with a natural zero point.
a. Time is a ratio since 0 time is meaningful. Maybe no movement at zero time.
b. Ratio is all of the above plus a 0 as part of the data
Who Cares?
Where did this all come from you ask and why do we care? Well, the short
answer is, we should care most about identifying nominal data--which is
categorical data. If it isn't nominal, then it's quantitative. So why all the
fuss? In the 1940's when behavioral science was in its infancy, there was
much concern about trying to make the practice as legitimate as possible.
Psychology and other Social and Behavioral Sciences are considered soft
sciences as opposed to the hard sciences of Chemistry and Physics. It was
thought that by applying some of the same thinking from the hard sciences,
it would improve the legitimacy of these soft sciences--as well as the
veracity of the claims made.
Levels of Measurement part 2 1
What is the Difference Between Nominal and Ordinal Data?
Nominal and Ordinal Data are two of the major four types of data. They’re
different ways to classify and express information. Each type tells you
different information about what you are trying to measure and allows for
various types of statistics. Choosing the most appropriate type of data for
your research is an important first step in Statistics.
Nominal Data is based on labeling or “coding” information into categories.
Generally, you are creating names for the information based on
characteristics of the category. For example, you could classify hair colors
into brunette, blonde, red, or black. When entering your data, you assign a
code, or number, to each category. For example, brunette = 1, blonde = 2.
This number is simply a shorthand that means brunette.
Ordinal Data describes the order of data based on a scale. In the scale,
there’s no way to tell the relative difference among the groups. For example,
we can say something or someone arrives 1st, 2nd, 3rd, or last, but we don’t
know the time between each place without more information. Scales are
often used for attitudes --- for example, satisfied to unsatisfied.
Interval Data is when we know the difference between groups. We know the
exact time differences between places assigned in a race, or the exact
difference between earning $20,000 and $30,000 per year.
Difference Between Types
Nominal data is only about labels, whereas ordinal data provides more
information about the rank, preference or order of the evidence. With ordinal
data, you can infer the range of opinion or order. Nominal data can not
make inferences because numbers are only codes for the assigned lables,
they don’t mean anything mathematically. For instance, you could not
calculate the difference between a brunette and a blonde if assigned the
numbers 1 and 2 respectively. Both provide general description of data, but
neither provides information about relative difference between data points.
Levels of Measurement part 2 2
Different Statistics
Because the data types are different, different statistics are possible. For
nominal data, you can only calculate the mode (most of), which is counting
the number of times each data point occurs. (how many blondes and
brunettes). For Ordinal Data, you can calculate the mode and the median,
but not the mean. The median is the middle number in the data set, so you
have information on the central tendency of the order or the rank. Interval
Data uses central tendencies of mode, median and arithmetic mean, as well
as range and standard deviation, which are important especially in money
matters and sports statistics. Ratio data uses mode, median, arithmetic
mean, geometric mean, range, standard deviation and coefficients of
variations.
With the Olympics there is a lot of good data sets.
By Country: Nominal
Finishing Place: Ordinal
Time: Interval and Ratio
Ok to compute…
Frequency
Distribution
(MODE)
Median and
percentiles
Add or Subtract
Mean, Standard
Deviation,
Standard Error of
the mean
Ratio, or
coefficient of
variation
Nominal
Yes
Ordinal
Yes
Interval
Yes
Ratio
Yes
No
Yes
Yes
Yes
No
No
No
No
Yes
Yes
Yes
Yes
No
NO
NO
Yes
Levels of Measurement part 2 3
Does it matter for data analysis?
The concepts are mostly pretty obvious, but putting names on different kinds of variables can
help prevent mistakes like taking the average of a group of zip codes, or taking the ratio of two pH
values. Beyond that, there is not much to putting labels on the different kinds of variables, but it really
helps you plan your anlyses to interpret the results. . Note that the categories are not as clear cut as
they sound. What kind of variable is color? In a psychological study of perception, different colors would
be regarded as nominal. In a physics study, color is quantified by wavelength, color could be a ratio
variable as well as nominal. What about counts? If your dependent variable is the number of cells in a
certain volume, what kind of variable is that. It has all the properties of a ratio variable, except it must
be an integer. Is this a ratio variable or not? These questions just point out that the classification scheme
appears to be more complicated and comprehensive than it appears. So the more in depth statistics
becomes the more knowledge about what kind of data is important and how to collect so it is reliable to
what is being researched.
Levels of Measurement part 2 4