|
Teaching GuideTerm Faculty of Computer Science |
| Grao en Ciencia e Enxeñaría de Datos |
 Subjects |
| Statistical Analysis of Complex Data |
| Contents |
|
|
|
| Identifying Data | 2022/23 | |||||||||||||
| Subject | Statistical Analysis of Complex Data | Code | 614G02031 | |||||||||||
| Study programme |
|
|||||||||||||
| Descriptors | Cycle | Period | Year | Type | Credits | |||||||||
| Graduate | 1st four-month period |
Fourth | Optional | 6 | ||||||||||
|
||||||||||||||
| Topic | Sub-topic |
| Introduction to missing data | Challenges and problems with missing data Missing data mechanisms: missing at random (MAR) and missing completely at random (MCAR) The consequences of discarding missing data |
| Imputation methods | Mean imputation Single imputation methods Maximum likelihood multiple imputation under MAR Expectation{Maximization (EM) algorithm Multiple imputation methods under MAR |
| Introduction to functional data | Motivation and examples Functional data registration and smoothing Metrics and semimetrics for functional data Representing functional data: basis expansions |
| Functional data analysis | Estimation of mean and covariance operator On the concept of depth for functional data: functional anomaly detection Functional principal component analysis Functional linear models |
| Censored data | Missing data and censoring The consequences of discarding censored data Parametric estimation for censored data Nonparametric estimation for censored data: the Kaplan-Meier estimator Cox model: conditional survival |
| Biased data | Selection bias: length, time and size The consequences of disregarding bias Mean and variance estimation for biased data Likelihood principle for biased data Situations with unspecified bias function |
|
