I have a quadratic linear regression of the form:

y = B0 + B1x^2

I need to do a hypothesis test that the marginal effect of an additional unit of x at a specific level of x is greater than 100.

I know that the marginal effect of x at any point is given by 2*B1*x. However, the regression output provides the standard errors for B1, not 2*B1*x.

To calculate the new standard error, do I simply multiply the standard errors by (2*x)^2?


Basic properties of variance include $\text{Var}(kY) = k^2 \text{Var}(Y)$.

So $\text{Var}(2x_0Y) = (2x_0)^2 \text{Var}(Y)$.

Consequently, multiplying by $2x_0$ (for some given constant $x_0$ multiplies both mean and standard error by $2x_0$.

| cite | improve this answer | |

Your Answer

By clicking “Post Your Answer”, you agree to our terms of service, privacy policy and cookie policy

Not the answer you're looking for? Browse other questions tagged or ask your own question.