So, let’s revisit the crayon example. This time we’ll add more people to the survey. In statistical context we can also call this process as increasing the sample size. Anyways, let’s set the size as 10. So if I survey everyone about the number of crayons each one of you have, I’d end up with the following numerical data.
|Name||No. of crayons|
So let’s summarise all this data statistically. If you are not sure what these terms are, check out the Mindspace lesson on the measure of central tendencies.
- The range of the data set is from 0 to 40.
- Mean is 14.3.
- Median is 11.
- Mode is 20.
- Standard Deviation is 13.20.
Or in other words, we can assert that, in the given sample, the average number of crayons is 14.3, with 20 crayons being the most common number, and the spread of crayons across the sample is approximately 13.
Discrete numerical data¶
Numerical data can be absolute. In the above table, the number of crayons is a good example of discrete data. No matter how many crayons you have, the number you provide will always be a discrete number that can be counted.
Continuous numerical data¶
Now if I were to collect an additional information, like the height of a crayon, the data would be an abstract one. Or in other words, you can only describe the data within the range of the measuring ruler like 5 cm or 8 cm. But the value is continuous. It could be 4.9 cm or 4.91 cm or 4.92 cm, etc. It’s based on the instrument you measure.