How to get marginal effects for a logit model

[dbyroo1]

I am currently using EViews 7 and want to get the marginal effects for the logit output I have. I've seen another post which says that you have to go to Proc then forcast but if I do that I just get a graph. If possible can someone give me a step to step guide. This is my first time using the program and I am very new to econometrics. If it's relevant I have 7 coefficients (including the intercept) which I need the marginal effects for.

Thanks

[EViews Glenn]

Do a forum search for "marginal effects in probit". There's a number of dicussions.

[dbyroo1]

I've worked out how to do it now. I would really appreciate it if anyone could tell me how to perform a Hausman-Wu test for endogeneity. Again using eviews7. The manual gives instructions for how to perform one with standard OLS but the same options aren't available to click on when a logit regression is run.
Thanks

[EViews Gareth]

It isn't available for logit estimation.

[bensamen]

binary y c x1 x2 x3 x4 x5 x6 x7 x8 x9
vector beta=@coefs
vector(10) a
a(1) =1
a(2) = @mean(x1)
a(3) = @mean(x2)
a(4) = @mean(x3)
a(5) = @mean(x4)
a(6) = @mean(x5)
a(7) = @mean(x6)
a(8) = @mean(x7)
a(9) = @mean(x8)
a(10) = @mean(x9)
matrix xbar =@transpose(a)
vector ihat=xbar*beta
vector phat=@clogistic(ihat)
vector(1) ddx
ddx(1) =1
vector pl=phat(1,1)
vector marginal=beta*pl*(ddx-pl)