There are many active research projects accessing and applying shared ADNI data. Use the search above to find specific research focuses on the active ADNI investigations. This information is requested annually as a requirement for data access.
| Principal Investigator | |
| Principal Investigator's Name: | Natasha Stewart |
| Institution: | University of Michigan |
| Department: | Statistics |
| Country: | |
| Proposed Analysis: | As a Ph.D. student in statistics, I am currently working on a project involving multi-task feature selection and post-selection inference. ANDI MRI/MMSE data is a commonly used benchmark in the multi-task feature selection literature, and I would like to test my methods on this data. I would apply a multi-task Lasso algorithm to select a set of features from the MRI data that are useful in modeling Mini Mental State Examination (MMSE) scores at various time points and proceed to infer about the parameters in the selected model using my proposed post-selection inference methodology. This is joint work with my advisors Drs. Elizaveta Levina and Snigdha Panigrahi. |
| Additional Investigators | |
| Investigator's Name: | Snigdha Panigrahi |
| Proposed Analysis: | We would like to apply our proposed algorithm for multi-task feature selection and post-selection inference to ANDI MRI/MMSE data. A randomized multi-task Lasso algorithm will be used to select a set of relevant features from the MRI data that are useful in modeling Mini Mental State Examination (MMSE) scores at various time points. From there, we will use our post-selection inference procedures to infer about the parameters in the selected model. |
