How to Create a Covariance Matrix in R
Covariance Matrix in R, Covariance is a measure of the degree to which two variables are linearly associated. We can measure how changes in one variable are associated with another variable.
A covariance matrix indicates the covariance between different variables. It’s mainly used to understand how different variables are related.
This article describes how to create a covariance matrix in R.
Kendall’s Rank Correlation in R-Correlation Test »
How to Create a Covariance Matrix in R
Step 1: Load the data frame.
Let’s create a data frame that contains different parameter’s scores of 10 different products
data <- data.frame(Appearance = c(8, 8, 8, 9, 7, 9, 9, 7, 8, 9), Thickness = c(8, 8, 7, 7, 7, 8, 9, 8, 7, 9), Spredability= c(7, 9, 9, 9, 8, 8, 7, 8, 6, 7)) data
Appearance Thickness Spreadability 1 8 8 7 2 8 8 9 3 8 7 9 4 9 7 9 5 7 7 8 6 9 8 8 7 9 9 7 8 7 8 8 9 8 7 6 10 9 9 7
Step 2: Create the covariance matrix.
Now let’s create the covariance matrix using the cov() function:
Intraclass Correlation Coefficient in R-Quick Guide »
cov(data)
Appearance Thickness Spreadability Appearance 0.62222222 0.2666667 -0.06666667 Thickness 0.26666667 0.6222222 -0.26666667 Spreadability -0.06666667 -0.2666667 1.06666667
Step 3: Inference.
The values along the diagonals of the matrix are simply the variances of each product.
The variance of the appearance scores is 0.62
The variance of the thickness scores is 0.62
The variance of the spreadability scores is 1.06
How to Calculate Partial Correlation coefficient in R-Quick Guide
The other values in the matrix represent the covariances between the various products
The covariance between the appearance and thickness scores is 0.26
The covariance between the appearance and spreadability scores is -0.066
The covariance between the thickness and spreadability scores is –0.266
A positive number for covariance indicates that two variables tend to increase or decrease simultaneously.
For example, appearance and thickness have a positive covariance (0.26), which indicates that products that score high on appearance also tend to score high on thickness.
Point Biserial Correlation in R-Quick Guide »
A negative number for covariance indicates that as one variable increases, a second variable tends to decrease.
For example, appearance and spreadability have a negative covariance (-0.066), which indicates that product which scores high on appearance tend to score low on spreadability.
Note:-
Covariance can vary between -∞ and +∞
Covariance is affected by the changes in scale.
Covariance is zero indicates if one variable move and the other doesn’t.
PSC Mock Test » Online Platform for all Exams » PSC Mock Test
Subscribe to the Newsletter and COMMENT below!
[newsletter_form type=”minimal”]
