The coefficient of determination is the formal name for R squared, the statistic that measures what share of the variation in a dependent variable is explained by the independent variable or variables in a regression model. It ranges from 0 to 1, or 0% to 100%.
Use in cost accounting
Management accountants meet the coefficient of determination when estimating cost behavior with regression analysis. Suppose a plant regresses its monthly maintenance cost on machine hours and obtains an R squared of 0.81. That means 81% of the month-to-month variation in maintenance cost is associated with changes in machine hours, and 19% is due to other factors or random noise. A high value supports using machine hours as the cost driver for budgeting and for allocating overhead.
With one independent variable, the coefficient of determination equals the square of the coefficient of correlation. A correlation of 0.9 therefore gives an R squared of 0.81. Squaring removes the sign, so R squared shows how strong the relationship is but not whether the variables move in the same or opposite directions.
A high R squared does not prove that one variable causes the other, and it says nothing about whether the relationship holds outside the range of data used. Accountants therefore check it alongside a scatter plot and common sense about what actually drives the cost, and many prefer it to the cruder high-low method, which uses only two observations.