How to use this tool?
First of all, select from the upper dropdown examples, or find out between what kinds of things you want to examine correlation.
It can be the weight and height of people, or temperate and number of ice creams sold, or the age and performance of an employee, and so on. Anything.
Write the first value of each datapairs in column X and the second value into column Y.
Obviously, you need to have the same number of lines in each input textarea.
You can also fill in the denomination of each lines in the first input textarea, but this is not compulsory.
After entering the datapairs, a diagram immediatelly appears where you can visually check how the values move together
and you can also see the strength of the correlation numerically from 0% to 100%. The sureness of the result is also shown.
How does it work?
A complex algorithm calculates the ρ Spearman and Pearson correlation coefficient and the statistical significance related to it.
But we don't want to bore you with math behind it, just use it. You don't need university-level math in order to use a tool that is based on that.
What does correlation and its strength mean?
If you know two numerical data about one kind of thing, and you have information about several pieces of this kind of things,
then you can examine if there is a relationship between the two values. If you draw a diagram with the two values (on axes x and y),
then the stronger the correlation, the more unequivocally can be seen on the diagram if the two values move together, i.e
if the first value of the datapair is bigger then the second value of the same datapair is usually bigger too.
Why you can't be absolutely sure?
Because the experienced correlation between X and Y columns may come from the work of coincidence.
Your data comes from an experiment or observation that is not exactly repeatable, they are not accurate, there is a fluke in them.
If you would measure again, you would get different values. This distribution causes that you can be sure about the relationship between the things only if you have several data and if the correlation is strong.
The more data you have and the more strong the relationship between values, the bigger the certainty.
Think about it: If you have a small 12 rows chart, in which you have the seasons and their average temperatures and the number of computers sold in that season,
then if there is a weak correlation between the values, this may be the work of coincidence, so you cannot say it with complete certainty
that computer sales are in connection with the temperature. However if you have 365 lines of datapairs about the temperature of each days
and the number of ice creams sold then - because of the many data and strong correlation - it is already sure that there is a relationship.
What does the certainty percentage show?
The above certainty value shows you as a percentage
how much you can be sure about the fact that there is a correlation between the two kind of values, i.e. they move together on the diagram.
Nevertheless it does not tell you anything about the strength of the correlation.
If you are 100% sure that there is a correlation, it means only that a correlation exists, but it cannot be told how strong it is,
because you can conclude it only from the data of the experiment or observation.
What does low sureness mean?
It means that from these numbers it cannot be known whether there is a correlation between the two values or not.
So it does not mean that
there is no correlation and the relationship experienced is only the work of coincidence
but it means you cannot be sure, whether it is the work of coincidence or a real connection exists.
The certainty is said to be low under 95%, so you can't be sure about the result. Generally, 95% or bigger sureness is required.
If you reach 99% or better, then you can be sure already. (But there is 1% chance, that the difference happened because of a very rare coincidence.)
What does high sureness mean?
It means that it is sure that there is a correlation between the values.
Usually above 95% or 99% certainty level is considered to be high.
It's important that despite of the certainty being high, it only means that there is a relationship between the two values,
but the strength of the connection between the two datapairs may be minimal or negligible.
This is why you must also check the experienced strength of the correlation.
How to increase the certainty?
You need more data. If you continue your experiment or observation with a larger number of events, you will get better certainty,
even if the strength of the correlation doesn't change.