# Chapter 10 Study Questions

- What is the difference between descriptive and inferential statistics? Which do we use to assess statistical significance in fMRI?
- What are Type I and Type II errors? Which is typically minimized in fMRI data analysis?
- What is an alpha value? Does it relate to Type I or Type II errors?
- What is a
*t*-test used for in statistical testing? How does this relate to the idea of “contrast”? - What is a correlation coefficient used for in statistical testing? How does this relate to the idea of a “model,” which is the second core concept of fMRI data analysis?
- What does a Fourier transform do to a time series of data? For what sorts of experimental designs might it be useful?
- Write the basic model for a regression analysis (using the general linear model).
- What are the four types of matrices used in an fMRI regression analysis?
- What is a nuisance regressor? List some common nuisance regressors included in an fMRI model.
- What does it mean to orthogonalize two regressors? Describe a situation in which an experimenter might use orthogonalization.
- What two approaches might an fMRI experimenter take when dealing with an independent variable that could take any of several levels?
- What does it mean to include a set of basis functions in a model?
- Why must fMRI researchers correct for multiple comparisons?
- What are the differences between controlling for the family-wise error rate and controlling for the false discovery rate? Which tends to involve a more stringent statistical threshold?
- What are the advantages and disadvantages of region-of-interest analysis?
- Why do fMRI analyses typically use a random-effects statistical model?
- What is a reverse inference? When is it justified, and when is it not justified?
- What is the difference between radiological and neurological conventions for displaying MRI data?
- Describe some of the common ways in which fMRI data are displayed.