Alpha is the (two-tailed) type I error, rho is the correlation between the two variables with mean the difference in variable means and sd the (common) sd for each variable.
[COPY AND PASTE INTO R AND THEN ADJUST INPUTS AS DESIRED]
alpha <- 0.05 mean <- 2 sd <- 4 rho <- 0.5 n <- 45
[COPY AND PASTE THE BELOW INTO R]
pow <- 1 - pt(abs(qt(alpha/2, 2*n-2)), 2*n-2, mdiff/sqrt((2*sd*sd)/n*(1-rho))) print(pow)