Causal and selective inference in complex statistical models
Abstract/Contents
- Abstract
- During the past decades, advances in technology have led to a rapid growth of data in many fields. This abundance of data brings great opportunities as well as great challenges to data analysis: Datasets often measure hundreds of thousands of variables with complex dependence structures, which results in difficulties for statistical inference. For example, in a social network, each individual's behavior can be significantly influenced by the behavior of many others in complicated ways. Thus one cannot assume independence when analyzing the data. Similarly, in genetics, a trait could be associated with a large number of genetic variants, the relationship among which cannot be efficiently summarized by simple models. In both examples and many other real-world problems, datasets have dependence structures that standard statistical methods have difficulty dealing with. It is thus of interest to develop tools to conduct statistical inference under such complex dependence structures. This dissertation contributes to the toolbox of causal and selective inference in complex statistical models. One topic of interest is to develop methods to answer various causal questions in situations where individual subjects are interdependent. Chapter 2 and 3 develop statistical theory and methodology for treatment effect estimation under interference. Another interesting topic is to identify important dependency structures among many seemingly promising ones from a dataset. In settings where a specific variable is of scientific interest and many explanatory variables are potentially related to that variable, the goal is to build tools to select with confidence which of the variables are important for explaining the variable of interest. Chapter 4 and 5 tackle the problem of variable selection with false discovery rate control.
Description
| Type of resource | text |
|---|---|
| Form | electronic resource; remote; computer; online resource |
| Extent | 1 online resource. |
| Place | California |
| Place | [Stanford, California] |
| Publisher | [Stanford University] |
| Copyright date | 2022; ©2022 |
| Publication date | 2022; 2022 |
| Issuance | monographic |
| Language | English |
Creators/Contributors
| Author | Li, Shuangning |
|---|---|
| Degree supervisor | Candès, Emmanuel J. (Emmanuel Jean) |
| Degree supervisor | Wager, Stefan |
| Thesis advisor | Candès, Emmanuel J. (Emmanuel Jean) |
| Thesis advisor | Wager, Stefan |
| Thesis advisor | Hastie, Trevor |
| Degree committee member | Hastie, Trevor |
| Associated with | Stanford University, Department of Statistics |
Subjects
| Genre | Theses |
|---|---|
| Genre | Text |
Bibliographic information
| Statement of responsibility | Shuangning Li. |
|---|---|
| Note | Submitted to the Department of Statistics. |
| Thesis | Thesis Ph.D. Stanford University 2022. |
| Location | https://purl.stanford.edu/mf380ny0830 |
Access conditions
- Copyright
- © 2022 by Shuangning Li
- License
- This work is licensed under a Creative Commons Attribution Non Commercial 3.0 Unported license (CC BY-NC).
Also listed in
Loading usage metrics...