Suppose observations are normally distrubuted with standard deviation 3, and we wish to carry out a two-sided test if the null hypothesis M=0. If M=0, the probability that a random sample of 9 observations is significant at the 5% level, by definition exactly 5%. Calculate the probability that a random sample of 9 observations from N( M , 3^2 ) is significant at the 5% level, for M=0.5, 1, 1.5, 2.

Any help would be great.