Ordinal and Nominal Data: What is the Difference?

In summary: SW VandeCarr!In summary, nominal data is qualitative and can be based on quantitative measurements, ordinal data is quantitative and qualitative data, and discrete data is qualitative and can only be based on discrete observations.
  • #1
zmike
139
0
I am having trouble distinguishing ordinal and nominal data, I know that ordinal is when there is some order but when you have to decide the type of data it is for something like "are you currently taking this medication?" it is very confusing as it seems like binary nominal to me but there is some order as taking medication is better than not taking med.

help?

thanks
 
Physics news on Phys.org
  • #2
zmike said:
I am having trouble distinguishing ordinal and nominal data, I know that ordinal is when there is some order but when you have to decide the type of data it is for something like "are you currently taking this medication?" it is very confusing as it seems like binary nominal to me but there is some order as taking medication is better than not taking med.

help?

thanks

Reducing nominal data to 0,1 coding is usual and IMO, the best way to handle these data. There is an order in that 1>0 and the computer accepts it as such. You end up with a lot variables as when you are coding for occupation, geographic location, medications, but these variables can be conveniently split out and summarized as subgroup variables. So for medicines we can have NSAIDs, anti-hypertensives, etc. I knew many statisticians who preferred to use 0,1 indicator variables for grouped ordinal data as well (such as age).

I don't think you should impose some kind of order on nominal data that is not natural unless the there is some good specific reason for doing so.
 
Last edited:
  • #3
Is it possible to change continuous data to discrete data?

Will data have to be infinitely continuous to be considered continuous? If I were to break continuous data down into intervals would it be considered discrete?

eg. volume of A
1) 1-10 mL
2) 10-20 mL


Thanks
 
  • #4
zmike said:
Is it possible to change continuous data to discrete data?

Thanks

The variable can be continuous, but usually your data consists of individuals. So yes, the variable "volume" can be made discrete as you have shown. However you must not have overlapping or skipped values; so 0ml -<10ml; 10ml - <20ml; etc.
 
Last edited:
  • #5
thanks but would I classify the type of data I would get from that question as ordinal? since discrete means integers only.
 
  • #6
zmike said:
thanks but would I classify the type of data I would get from that question as ordinal? since discrete means integers only.

The data are ordinal. The variable "volume" is continuous. The fact that it's categorized or grouped for analysis doesn't change that. You are grouping individual (discrete) observations (usually) according to convenient ordered categories. The categories must be mutually exclusive and free of gaps, respecting the fact that the variable is continuous.
 
  • #7
thanks SW VandeCarr!

do we classify the type of data based on what we would get from the questions we ask or the type of variable we're looking at? because in this case the variable volume is continuous but our options 1) and 2) lose the level of detail we would get from continuous data but the magnitudes of the numbers are still important? and ordinal data is qualitative so that label wouldn't really fit?

would it be correct to say that despite ordinal is qualitative data, they can technically be based on quantitative measurements?
 
  • #8
zmike said:
thanks SW VandeCarr!

would it be correct to say that despite ordinal is qualitative data, they can technically be based on quantitative measurements?

It seems you don't understand a lot of basic concepts. Data consists of observations. Generally these are simply discrete quantities or qualities. If they are quantitative they are ordinal. If they are qualitative they are nominal. I already addressed nominal data in my previous posts.

If ordinal, they may be in terms of continuous variables. If you are dealing with discrete observations of a continuous variable you cannot be more precise then the observations allow. Whether you choose to enter each value directly or create ordered categorical sets is a matter of preference and the requirements of analysis. If you actually have a continuous record, as in many engineering applications, there are special ways to input these kinds of data with right kind of software.
 
Last edited:

1. What is the difference between ordinal and nominal data?

Ordinal data is a type of categorical data that has a natural order or ranking, while nominal data is a type of categorical data that does not have a natural order or ranking.

2. What are some examples of ordinal data?

Examples of ordinal data include ratings such as "strongly agree", "agree", "neutral", "disagree", and "strongly disagree", as well as grades such as A, B, C, D, and F.

3. How can ordinal data be represented visually?

Ordinal data can be represented visually using bar charts, histograms, and box plots. These types of graphs are useful for showing the distribution of data and any patterns or trends in the data.

4. What are some common statistical tests for analyzing ordinal data?

Some common statistical tests for analyzing ordinal data include the Mann-Whitney U test, Wilcoxon signed-rank test, and Kruskal-Wallis test. These tests are non-parametric, meaning they do not assume a normal distribution of the data.

5. Can ordinal data be converted to numerical data?

Yes, ordinal data can be converted to numerical data by assigning numerical values to each category. However, it is important to note that the numerical values do not hold the same meaning as in numerical data, and the data should still be treated as ordinal when analyzing it.

Similar threads

  • Set Theory, Logic, Probability, Statistics
Replies
3
Views
1K
  • Set Theory, Logic, Probability, Statistics
Replies
27
Views
3K
  • Set Theory, Logic, Probability, Statistics
Replies
18
Views
2K
  • Set Theory, Logic, Probability, Statistics
Replies
28
Views
5K
  • Special and General Relativity
Replies
16
Views
1K
Replies
8
Views
549
  • Set Theory, Logic, Probability, Statistics
Replies
20
Views
1K
  • Set Theory, Logic, Probability, Statistics
Replies
7
Views
2K
  • Set Theory, Logic, Probability, Statistics
Replies
11
Views
14K
  • Set Theory, Logic, Probability, Statistics
Replies
4
Views
774
Back
Top