R squared conceptual question with respect to number of observations.

46 Views Asked by At

The following statement is true. However, I have difficulties to understand why. I would appreciate if someone could explain it conceptually or perhaps with or without reference to any formula.

In a simple linear regression model (ie an intercept and one regressor) with $n=10$ observations the slope coefficient will be significant at the $5%$ level provided that the R squared is at least $0.384/(1-0.384)$.