Differences between revisions 2 and 10 (spanning 8 versions)
Revision 2 as of 2008-12-02 16:42:33
Size: 2625
Editor: crash
Comment:
Revision 10 as of 2008-12-05 20:07:26
Size: 1695
Editor: crash
Comment:
Deletions are marked like this. Additions are marked like this.
Line 1: Line 1:
Two Groups (One Factor/Two Levels), One Covariates [[FsgdExamples|Back to FSGD Examples]]
Line 3: Line 3:
This models the input as two lines. If DODS, then each line has its
own intercept and slope. If DOSS, then each line has its
own intercept but they share a slope.
~+'''One Group, One Covariate'''+~
Line 7: Line 5:
FSGD File: example3.fsgd This models the input as a single line (ie, an intercept and a slope).
factor (eg, Age). Because there is only one group, this will be the
same for both DODS and DOSS.

<<TableOfContents>>

= FSGD File (g1v1.fsgd) =
Line 11: Line 15:
Class Group1
Class Group2
Class Main
Line 14: Line 17:
Input subject1 Group1 30
Input subject2 Group2 40
Input subject1 Main 30
Input subject2 Main 40
Line 18: Line 21:
Nclasses = 2<<BR>>
Nvariables = 1<<BR>>
Nclasses = 1 <<BR>>
Nvariables = 1 <<BR>>
Line 21: Line 24:
--------------------------------------------------------------------------------------
DODS
Regressors: <<BR>>
Nregressors = Nclasses*(Nvariables+1) = 2*(1+1) = 4 <<BR>>
Regressor1: ones for subjects in Group 1, 0 otherwise. Codes intercept/mean for Group 1 <<BR>>
Regressor2: ones for subjects in Group 2, 0 otherwise. Codes intercept/mean for Group 2 <<BR>>
Regressor3: age for subjects in Group 1, 0 otherwise. Codes age slope for Group 1 <<BR>>
Regressor4: age for subjects in Group 2, 0 otherwise. Codes age slope for Group 2 <<BR>>
= Regressors =
Line 30: Line 26:
Contrasts: Nregressors = Nclasses*(Nvariables+1) = 1*(1+1) = 2 <<BR>>
Regressor1: All ones. Codes intercept/mean for Main <<BR>>
Regressor2: age for each subject. Codes age slope for Group 1 <<BR>>
Line 32: Line 30:
Contrast1: ------------
Null Hypothesis: is there a difference between the group intercepts?
= Contrasts =
Line 35: Line 32:
Contrast File: g1-g2.intercept.mtx
--------------- cut here --------------
1 -1 0 0
--------------- cut here --------------
The number of columns in each contrast matrix must be the same as the
number of regressors (Nregressors). If there is only one row in the
contrast matrix, then the result will be a t-test and will have a
sign. Reversing the signs in the contrast matrix will only change the
sign of the output, not its magnitude. If there is more than one row,
the result will be an F-test and will be unsigned.
Line 40: Line 39:
Since this is a t-test, the output will be signed, with Group1>Group2
being positive (red/yellow). Reversing the sign will only change the
sign of the output, not its magnitude.
== Contrast 1 (intercept.mtx) ==
Null Hypothesis: is the intercept equal to 0?
Line 44: Line 42:
Contrast2: ------------ {{{
1 0
}}}
Line 46: Line 46:
Null Hypothesis: is there a difference between the group slopes? Note:
this is an interaction between group and age. Note: not possible to
test with DOSS
This is a t-test with the intercept>0 being positive (red/yellow).
Line 50: Line 48:
Contrast File: g1-g2.slope.mtx
--------------- cut here --------------
0 0 1 -1
--------------- cut here --------------
== Contrast 2 (slope.mtx) ==
Line 55: Line 50:
Since this is a t-test, the output will be signed, with Group1>Group2
being positive (red/yellow). Reversing the sign will only change the
sign of the output, not its magnitude.
Null Hypothesis: is the slope equal to 0?
Line 59: Line 52:
Contrast3: ------------
Null Hypothesis: does Group1 differ from Group2 in intercept or slope?
{{{
0 1
}}}
Line 62: Line 56:
Contrast File: g1-vs-g2.mtx
--------------- cut here --------------
1 -1 0 0
0 0 1 -1
--------------- cut here --------------
Note: this is an F-test (and hence unsigned).
This is a t-test with the slope>0 being positive (red/yellow).
Line 69: Line 58:
Contrast4: ------------
Null Hypothesis: does mean of group intercepts differ from 0?
= mri_glmfit command =
Line 72: Line 60:
Contrast File: g1g2.intercept.mtx
--------------- cut here --------------
0.5 0.5 0 0
--------------- cut here --------------
This is an example invocation of mri_glmfit. Depending upon your
application, you may have other options as well.
Line 77: Line 63:
Contrast5: ------------
Null Hypothesis: does mean of group slopes differ from 0?

Contrast File: g1g2.intercept.mtx
--------------- cut here --------------
0 0 0.5 0.5
--------------- cut here --------------
{{{
mri_glmfit \
  --glmdir g1v1 \
  --y y.mgh \
  --fsgd g1v1.fsgd \
  --C intercept.mtx \
  --C slope.mtx
}}}

Back to FSGD Examples

One Group, One Covariate

This models the input as a single line (ie, an intercept and a slope). factor (eg, Age). Because there is only one group, this will be the same for both DODS and DOSS.

FSGD File (g1v1.fsgd)

GroupDescriptorFile 1
Title OSGM
Class Main
Variable Age
Input subject1 Main 30
Input subject2 Main 40

Nclasses = 1
Nvariables = 1

Regressors

Nregressors = Nclasses*(Nvariables+1) = 1*(1+1) = 2
Regressor1: All ones. Codes intercept/mean for Main
Regressor2: age for each subject. Codes age slope for Group 1

Contrasts

The number of columns in each contrast matrix must be the same as the number of regressors (Nregressors). If there is only one row in the contrast matrix, then the result will be a t-test and will have a sign. Reversing the signs in the contrast matrix will only change the sign of the output, not its magnitude. If there is more than one row, the result will be an F-test and will be unsigned.

Contrast 1 (intercept.mtx)

Null Hypothesis: is the intercept equal to 0?

1 0

This is a t-test with the intercept>0 being positive (red/yellow).

Contrast 2 (slope.mtx)

Null Hypothesis: is the slope equal to 0?

0 1

This is a t-test with the slope>0 being positive (red/yellow).

mri_glmfit command

This is an example invocation of mri_glmfit. Depending upon your application, you may have other options as well.

mri_glmfit \
  --glmdir g1v1 \
  --y y.mgh \
  --fsgd g1v1.fsgd \
  --C intercept.mtx \
  --C slope.mtx

Fsgdf1G1V (last edited 2010-09-20 15:10:27 by MartinReuter)