In many practical scenarios, we might come across the situation where observations are available on two or more variables like heights and weights of the person ,expenditure on advertisement and sales revenue, tweet likes and popularity index of person etc.
A natural question arises in mind that is there any connection between popularity of person and number of likes on the tweet.
When two variables are related to each other in such a way that change in the value of one variable affects the value of another, variables are said to be correlated like expenditure on advertisement can increase the sales revenue so they are correlated.
There are two types of correlation :
Positive Correlation – Correlation between two variables is said to be positive if increase or decrease in value of one variable causes increase or decrease in the value of another variable respectively.
Example:
If there is increase in rainfall, crops yield will also increase.
Sales revenue may increase if there is more expenditure on advertisements.
Negative Correlation– Correlation between two variables is said to be negative if increase in the value of one variable decreases the value of another variable and vice versa.
Example: Literacy and poverty in a country. As literacy rate increases, poverty rate falls down.
Scatter Plot
Scatter plot is a statistical diagram that determine the positive and negative correlation.
Scatter diagram gives an idea about the existence of correlation between two variable.
If the values of dependent variable Y are plotted against corresponding values of the independent variable X in the XY plane, such diagram of dots is called scatter diagram or dot diagram.
It is to be noted that scatter diagram is not suitable for large number of observations.
Below are scatter plots showing different types of correlation.
- Positive Correlation
- Negative Correlation
If dots of scatter diagram don’t show any trend, there is no correlation between the variables as shown below.
Coefficient of Correlation
Coefficient of correlation measures the intensity or degree of linear relationship between two variables. It was given by Karl Pearson and it is denoted by r.
Correlation between variables x and y is given as
r = Corr(x,y)
= \frac{Cov(x,y)}{\sqrt{V(x)}\sqrt{V(y)}}where
Cov(x,y) is the covariance between x and y and is given as
Cov(x,y)= \frac{\sum(x-\hat{x})(y-\hat{y})}{n}V(x) is the variance of x given as:
V(x) = \frac{\sum(x-\hat{x})^2}{n}V(y) is the variance of y given as:
V(x) = \frac{\sum(y-\hat{y})^2}{n}Putting above values in equation (1), we can get correlation formula as
r= \frac{\sum(x-\hat{x})(y-\hat{y})/n}{(\sqrt{\sum(x-\hat{x})^2}/n)(\sqrt{\sum(y-\hat{y})^2}/n)}Correlation coefficient lies between -1 and +1
If X and Y are two independent variables then correlation coefficient (r) between X and Y is zero.
Corr(x,y)=0
Below table gives meaning of different values of correlation.
r | Correlation is |
+1 | Perfect Positive Correlation |
-1 | Perfect Negative Correlation |
0 | No Correlation |
0 to .25 | Weak Positive Correlation |
.75 to .1 | Strong Positive Correlation |
-.25 to 0 | Weak Negative Correlation |
-.75 to -1 | Strong Negative Correlation |
Coefficient of Determination
It is a measure which is used in statistical model analysis to assess how well a model explains and predicts future outcomes.
The coefficient of determination is the measure of variation in the dependent variable that is explained by the regression function.It is square of correlation of coefficient and denoted by r^{2}.The Coefficient of Determination
If coefficient of determination is 0, dependent variable can not be predicted from the independent variable, whereas the value of r^{2} =1 indicates that the dependent variable can be predicted from the independent variable without error.
If r^{2} is .75, it implies that 75% of the variations in dependent variable (Y) can be explained by the independent variable.
Correlation Ratio
If variables are not linearly related and show some curvilinear relationship then correlation coefficient is not a suitable measure to show the extent of relationship. We use Correlation Ratio in this type of cases. Please refer below link for details of correlation ratio.
Well, we look forward to meet you in next article.
18 Comments
먹튀인포 · June 18, 2019 at 12:23 am
Peculiar article, totally wht I wanted to find.
admin · June 25, 2019 at 11:42 am
Thanks a ton to share your feedback. It means a lot for us.
Free Stuff · July 8, 2019 at 11:12 am
Thanks for discussing your ideas. Another thing is that students have an alternative between federal student loan as well as a private education loan where it is easier to select student loan online debt consolidation than with the federal student loan.
Stacey · July 12, 2019 at 6:53 am
Using With and By; R in Action. … function to test a single correlation coefficient . … Try this interactive course on correlations and regressions in R .
Nolan · July 23, 2019 at 4:54 pm
Linear Correlation . … The points are close to the linear trend line. Correlation r = 0.9; … Perfect negative association. Correlation r = -1.
Joe · August 1, 2019 at 3:52 pm
Correlation and Regression coefficients. As we have seen in the previous pages, the variables xand ycan be linearly related. The correlation coefficient is a measure …
Joe · August 5, 2019 at 5:30 am
Let’s take a look at some examples so we can get some practice interpreting the coefficient of determination r 2 and the correlation coefficient r.
admin · August 6, 2019 at 5:22 pm
Sure, will definitely consider on it.Thanks for the feedback.
Hairstyles · August 19, 2019 at 10:30 pm
I needed to write you this very little observation to help thank you very much yet again for all the awesome information you’ve shared here. It is simply tremendously open-handed of you to give easily just what many of us could possibly have distributed as an e book to end up making some bucks for themselves, precisely now that you could have tried it in case you decided. Those ideas as well worked like the great way to comprehend someone else have similar zeal much like my personal own to find out much more with reference to this problem. Certainly there are several more pleasant instances in the future for individuals who scan through your site.
GuQin · September 23, 2019 at 11:07 am
Hiya, I’m really glad I have found this information. Today bloggers publish only about gossips and net and this is really annoying. A good site with interesting content, that is what I need. Thanks for keeping this site, I’ll be visiting it. Do you do newsletters? Can’t find it.
plenty of fish dating site · November 12, 2019 at 3:13 pm
When someone writes an piece of writing he/she maintains the thought of a user in his/her brain that
how a user can know it. Therefore that’s why this post is amazing.
Thanks!
coconut oil there · November 15, 2019 at 5:01 pm
I blog quite often and I really appreciate your information. This article has truly peaked my interest.
I am going to book mark your blog and keep checking for new
information about once per week. I opted in for your RSS feed too.
http://tinyurl.com · November 21, 2019 at 2:24 am
Hi, yes this paragraph is genuinely good and I have learned lot of things from it
about blogging. thanks.
토토사이트 · January 30, 2020 at 4:59 am
paragraph is genuinely good and I have learned lot of things from it
about blogging. thanks.
카지노사이트 · January 30, 2020 at 5:00 am
inely good and I have learned lot of things from it
about blogging. thanks.
파워볼 · March 9, 2020 at 2:49 pm
I think this is one of the most significant information for me. And i’m glad reading your article. But should remark on some general things, The web site style is perfect, the articles is really great.
토토사이트 · March 17, 2020 at 9:50 am
you have done a great job i hope you will do much batter in the future
ปั้มไลค์ · May 21, 2020 at 5:02 pm
Like!! I blog quite often and I genuinely thank you for your information. The article has truly peaked my interest.