Prev: matlab back propogation neural network
Next: 2D Acoustic Taper Waveguide and Recursive convolution
From: uny gg on 11 May 2010 17:01
Hello

I have a basic statistic question.

I have two sets of dataset. I would like to test where the mean of the first group is significantly larger than the other group.

I am wondering whether there is direct test or not.

What I thought is that

1) do the t-test to compare the mean of these two group is significantly different or not.

2) if it is, compare the mean of those two group.

My question is that
is there any direct way to compare the first mean is significantly larger than the second without this two steps? for example. H0 : Mean(group1) > Mean(group2)

It will be really helpful.

THanks.
From: Rogelio on 11 May 2010 17:10
take a look to ANOVA

"uny gg" <illinois.ks(a)gmail.com> wrote in message <hscgij$ks4$1(a)fred.mathworks.com>...
> Hello
>
> I have a basic statistic question.
>
> I have two sets of dataset. I would like to test where the mean of the first group is significantly larger than the other group.
>
> I am wondering whether there is direct test or not.
>
> What I thought is that
>
> 1) do the t-test to compare the mean of these two group is significantly different or not.
>
> 2) if it is, compare the mean of those two group.
>
> My question is that
> is there any direct way to compare the first mean is significantly larger than the second without this two steps? for example. H0 : Mean(group1) > Mean(group2)
>
> It will be really helpful.
>
> THanks.
From: Peter Perkins on 12 May 2010 10:21
On 5/11/2010 5:01 PM, uny gg wrote:

> I have two sets of dataset. I would like to test where the mean of the
> first group is significantly larger than the other group.
>
> I am wondering whether there is direct test or not.

If you have the Statistics Toolbox,

>> help ttest2
TTEST2 Two-sample t-test with pooled or unpooled variance estimate.
[snip]
H = TTEST2(X,Y,ALPHA,TAIL) performs the test against the alternative
hypothesis specified by TAIL:
'both' -- "means are not equal" (two-tailed test)
'right' -- "mean of X is greater than mean of Y" (right-tailed
test)
'left' -- "mean of X is less than mean of Y" (left-tailed test)
TAIL must be a single string.

 | 
Pages: 1
Prev: matlab back propogation neural network
Next: 2D Acoustic Taper Waveguide and Recursive convolution