Zurück
| Semester | Herbstsemester 2022 |
| Angebotsmuster | unregelmässig |
| Dozierende |
Tracy Glass (tracy.glass@unibas.ch)
Giusi Moffa (giusi.moffa@unibas.ch, BeurteilerIn) |
| Inhalt | Formulation of causal questions, definition of causal effects in the potential outcome framework and causal identifiability assumptions. Reasoning about causality with directed acyclic graphs, an effective tool to describe the causal assumptions underlying a study, identify valid covariate adjustment sets and uncover potential pitfalls in study design and analysis, especially related to confounding and collider bias. Implementation with R of the most common analytical methods to control for confounding and estimate causal contrasts/effects for point exposures from observational data, including stratification, outcome regression, propensity score matching and inverse probability weighting. Methods for causal inference in longitudinal settings with time-varying exposures and time-varying confounding. |
| Lernziele | The focus of the course is on the practical software implementation of statistical analyses for causal inference. The course is intended to help students develop their ability to: - formulate causal questions and define causal estimands addressing a specific research question. - use DAGs to describe causal assumptions and guide the choice of suitable statistical analysis strategies. - understand the assumptions underlying the estimation of causal contrasts/effects of interest. - choose appropriate methods to estimate causal contrasts/effects from real data, and implement them using the `R` statistical software. |
| Bemerkungen | Assistant: Enrico Giudice |
| Teilnahmebedingungen | Prior knowledge in statistics, especially statistical inference and regression modelling, with some experience in implementing statistical analyses, preferably with R/RStudio which we will use for all practical examples. Students should have access to a laptop with R/Rstudio installed. |
| Unterrichtssprache | Englisch |
| Einsatz digitaler Medien | kein spezifischer Einsatz |
| HörerInnen willkommen |
| Intervall | Wochentag | Zeit | Raum |
|---|---|---|---|
| Block | Siehe Einzeltermine | ||
| Datum | Zeit | Raum |
|---|---|---|
| Montag 12.09.2022 | 09.15-13.00 Uhr | Spiegelgasse 5, Seminarraum 05.002 |
| Dienstag 13.09.2022 | 09.15-13.00 Uhr | Spiegelgasse 5, Seminarraum 05.002 |
| Mittwoch 14.09.2022 | 09.15-13.00 Uhr | Spiegelgasse 5, Seminarraum 05.002 |
| Donnerstag 15.09.2022 | 09.15-13.00 Uhr | Spiegelgasse 5, Seminarraum 05.002 |
| Module |
Modul: Advances in Epidemiology, Statistics and Global & Public Health (Masterstudium: Epidemiologie) Modul: Angewandte Mathematik (Bachelorstudium: Mathematik) Modul: Applications and Related Topics (Bachelorstudium: Computer Science) Modul: Applications and Related Topics (Bachelor Studienfach: Computer Science) Modul: Electives in Data Science (Masterstudium: Data Science) Modul: Vertiefung Mathematik (Bachelorstudium: Computational Sciences (Studienbeginn vor 01.08.2023)) |
| Leistungsüberprüfung | Lehrveranst.-begleitend |
| An-/Abmeldung zur Leistungsüberprüfung | Anm.: Belegen Lehrveranstaltung; Abm.: stornieren |
| Wiederholungsprüfung | keine Wiederholungsprüfung |
| Skala | Pass / Fail |
| Wiederholtes Belegen | beliebig wiederholbar |
| Zuständige Fakultät | Philosophisch-Naturwissenschaftliche Fakultät, studiendekanat-philnat@unibas.ch |
| Anbietende Organisationseinheit | Fachbereich Mathematik |