Meaning of R Squared
- It is a statistical measurement that is used to indicate the proportion of the variance for a dependent variable from the independent variable in a regression model.
- A regression model is the statistical method used in finance and other disciplines to determine the strength and character of the relationship between two variables – one dependent and the other independent.
- Whereas correlation in a regression model explains the strength of the relationship between an independent and dependent variable, R-squared explains to what extent the variance of one variable affects the variance of the second variable.
- It is popularly termed as a coefficient of determination.
Calculation of R Squared
It is calculated as follows – R2 =1− (Unexplained Variation/ Total Variation) The steps involved to arrive at these figures are – The observations or data points of dependent and independent variables must be taken to find the line of best fit. This line of best fit can be arrived at with the help of a regression model. On calculating the predicted values, the actual values must be subtracted and the results must be squared. This yields a list of errors squared, which is summed and this equals the unexplained variance. In order to arrive at the total variance, one must subtract the average actual value from each of the actual values. The results must then be squared and added. Then the first sum of errors (explained variance) must be divided by the total variance sum to arrive at R squared.
More about R Squared
- In the world of finance, it is represented as a percentage of a fund or security's movements in line with a benchmark index i.e. to say an R Squared of 100% implies that the movement of the securities is completely in the same direction/ movement as the index.
- Funds with low R Squared (70% or less) proves that the security does not conform with the movements of the index.
- A higher R-squared value will inevitably direct toward a more useful beta figure.
