Presentation is loading. Please wait.

Presentation is loading. Please wait.

RFX in SPM5 Floris de Lange

Similar presentations


Presentation on theme: "RFX in SPM5 Floris de Lange"— Presentation transcript:

1 RFX in SPM5 Floris de Lange

2 RFX Options

3 Compare 2 conditions Conditions are MI LH (press left foot) and MI RH (press right foot); 8 subjects; threshold used is p 20 (arbitrary) Methods used: One-sample T-test on difference images MI LH>MI RH Paired-samples T-test on MI LH and MI RH Measurements assumed independent Measurements assumed dependent Two-samples T-test on MI LH and MI RH Multiple regression analysis on MI LH and MI RH Full factorial Flexible factorial

4 The gold standard: one-sample T-test

5 Paired T-test: dependence/indepence Independent: error covariance matrix = identity matrix (check SPM.xVi.V!) Dependent: error covariance matrix will be estimated (check SPM.xVi.V!)

6 Paired-samples T-test dep.: same

7 Paired-samples T-test indep.: same Dependence/inde pendence doesn’t make a difference here, because there’s only one sample to estimate covariance from

8 = identical Multiple regression analysis: same

9 Two-samples T test indep: worse Degrees of freedom ↑ Variance term ↑

10 Two-samples T test dep: better the correlation between the variance of the subjects in the first group and those in the second group is estimated this reduces the error term

11 Two-samples T test: dep vs indep Dependent measuresIndependent measures

12 Two-samples T test: con images Dependent measuresIndependent measures =

13 Two-samples T test: ResMS images Dependent measuresIndependent measures < Error terms is reduced for dependent measures by modelling the dependencies

14 Full factorial dep. = 2-sample T dep

15 Full factorial indep. = 2-sample T indep

16 Flex factorial dep. = 2-sample T dep

17 Flex factorial indep = 2-sample T indep

18 Summary There are two types of models: Models that specify the subject factor (e.g., one-sample, paired-samples, MRA if you specify the factor yourself) Models that estimate the subject factor (e.g., two-samples T- test, full factorial, flexible factorial; measurements are dependent) If you don’t specify the subject factor, but also don’t estimate the error covariance, you are likely to shoot yourself in the foot because the errors will be assumed to be independent, and simply added, leading to much higher estimates of the error term

19 Is it valid to use 2-sample T test dep? It can be statistically beneficial to specify the model as a “between- subjects” model without modelling subject, but instead estimating the subject-induced regularities by specifying that measures may be dependent SPM5 manual suggests to do analyses this way But is it valid? Aren’t df’s inflated? SPM5 manual


Download ppt "RFX in SPM5 Floris de Lange"

Similar presentations


Ads by Google