Statistics Phase 5 : Correlation Vs Causation


COVARIANCE
Covariance is a measure of the relationship between 2 or more random variables or how 2 random variables vary together. Its similar to variance, but where variance tells you how a single variable varies, covariance tells you how 2 variables vary together.
Positive covariance means as one variable increases the other one also increases. For example: lets’ take 2 variables height and weight. As heights increases weight also increases.
Negative covariance means as one decreases, the other one also decreases. For example, as salary decreases, the expenditure also decreases.
Measuring something in inches would be say 12 and converting the same into centimetres would be different only because of the unit change. So its hard to tell how strong the relationship is based on the actual magnitude of the covariance.

CORRELATION
On one hand, covariance indicates the direction of the linear relationship between the variables whereas correlation on the other hand, indicates both the strength and the direction of the linear relationship.
When correlation coefficient is 0, covariance is also 0.
For example: as the number of accident claims per month increase, the number of individuals asking for the claim decreases or as temperature increases, the demand for coolers increases.

ADVANTAGES OF CORRELATION OVER COVARIANCE
·         Covariance can take any number while correlation is limited; -1 to +1
·         Correlation is more useful for determining how strong the relationship is between 2 variables.
·         Correlation does not have units unlike covariance.
·         Correlation remains unaffected by the change in scale.
Due to all these reasons, correlation is preferred over covariance.



CORRELATION VS CAUSATION
A statistical measure (expressed as a number) that describes the size and direction of a relationship between two or more variables is correlation whereas while causation indicates that one event is the result of the occurrence of the other event; i.e. there is a causal relationship between the two events. This is also referred to as cause and effect.
The causation vs correlation example that is frequently used is that smoking is correlated with alcoholism, but doesn’t cause alcoholism. While smoking causes an increase in the risk of developing lung cancer.
When a person is exercising then the amount of calories burning goes up every minute. Former is causing latter to happen.



Follow us on LinkedIn : Actuary Sense
Follow me on LinkedIn: Kamal Sardana


credits: Simran Agrawal

Comments

  1. This comment has been removed by the author.

    ReplyDelete
  2. Your explanation related to negative covariance is wrong.
    If both the variables move in same direction it is positive covariance and in negative covariance both the variable move in opposite direct.
    Example for negative covariance is
    Price and demand
    If price increases demand decreases and vice versa.

    ReplyDelete

Post a Comment

Popular posts from this blog

Role of Generalised Linear Model in Non Life Pricing - Phase1

CFM vs UDD vs Balducci

Role of Generalised Linear Model in Non-Life Pricing - Phase 2