The number of tests m was set at
m= 64, 512 and 4096, with the fraction of the true null hypotheses (m0/m)
at 0%, 25%, 50%, 75% and 100%. The p-values were generated in the following
way. With Z1, . . . ,Zm+1 distributed independently and identically as
N(0, 1), we first let Yi = sqrt(ρ)*Zm+1 + sqrt(1 −ρ)Zi + μi, i = 1, . . . ,m, and then
defined the corresponding p-values as pi = 1−(Yi) , i = 1, . . . ,m, where 
is the cdf of N(0, 1). The values of μi were either 0 or an equal proportion of
1, 2, 3 and 4; the values of ρ were 0, 0.2, 0.5 and 0.8. The simulation results
are based on 5000 replications.,
上面是我从文章里粘贴过来的的，我想问各位高手，上面这个问题如何用MATLAB编程求p值；
是单边假设检验，谢谢了！！