Format
Live-Course with Lecture and Exercise alternating every other week

Dates
  • Time: Thursday 16:00 - 19:00.
  • Location: F 007.

Enrollment key
  • Please only enroll if you want to ACTIVELY participate; you will be automatically unenrolled after 1 month of inactivity. The enrollment key is: adv_26_iml
Contents
This course is an introduction to the concepts and methods of machine learning interpretability, and to their implementation in R and Python. It counts as the module "Advanced Machine Learning". The course focuses on model-agnostic interpretability methods for tabular data, and in parts is close to the course on our website. Course topics include:
  • General introduction to interpretable ML,
  • Inherently interpretable ML models,
  • Global and local feature effect methods,
  • Feature importance methods,
  • Shapley values,
  • Functional decompositions,
  • Regional feature effect methods, and
  • Local explanations, including counterfactual explanations.

Dates:

 Termin Ort Person
Lecture Tuesday, 10:15-11:45  Geschw.-Scholl-Pl. 1 (A) / A014 Olma/Starck
Lecture/Exercise  Wednesday, 12:15-13:45 Geschw.-Scholl-Pl. 1 (A) / A016  Olma/Starck

Password
  • The password for enrolment is: "mathstat26"

Lecture hours:

Enrolment Key: s26EcTheory

Kick-off meeting:
Friday, April 24, 10 am
Seminar Room #144, Ludwigstr. 33

Final presentations:
July 16&17

Time and Dates:  on mondays 12:15 - 13:45 

First meeting: monday, 27.04.2026

Room:   Geschw.-Scholl-Pl. 1 (M) - M 105





Overview: This course will discuss essential research techniques in statistics and data science, also preparing students for successfully participating in seminars and writing a thesis. The material presented focuses mainly on classical research techniques and a first understanding of research as a social system. 




The course is part of the Bachelor’s programmes in Statistics and Data Science (150 major or 60 ECTS minors: `Methoden und Techniken des wissenschaftlichen Arbeitens’,  P16.1, and  WP 12.1 / WP 13.1, respectively).  Bachelor's students from the "old POs" and Master’s students are most welcome as well. A certificate can be issued for active personal attendance.

Minor students and Bachelor's degree Erasmus students who will not attend a seminar can obtain 3 ECTS via an examination/small project at the end of the course.

Enrollment key: ResTech26

Format
Inverted classroom with 90 min live lecture recap + 90 min live exercise recap

Class
  • Time: Thursday 12:15 - 13:45 h.
  • Location: S 003.
Exercise
  • Time: Wednesday 10:15 - 11:45 h.
  • Location: S 006.

Enrollment key
  • The enrollment key is: "I2ML".


The course Analysis of high-dimensional biological data (formerly Statistische Methoden in Genomik und Proteomik / Statistical methods for biological high-throughput data) will cover important statistical methods and concepts for the analysis of high-dimensional biological high-throughput data. We will focus on bulk RNA-Seq, single-cell RNA-Seq, proteomic, metabolic, and especially microbiome data such as 16S rRNA and other amplicon data. 

Statistical topics include:

  • Generative statistical models for count data
  • Hypothesis testing for high-dimensional data
  • Differential abundance and expression analysis
  • High-Dimensional regression models for biological data
  • Graphical models for network inference
  • Deep learning models for high-throughput data

Schedule:

Date and TimePlacePersonBeginn
LectureThu, 14:00 - 16:00Prof.-Huber-Pl. 2 (V) Raum LEHRTURM-V002
C.L Müller16.04.2026
ExercisesMo, 10:00 - 12:00
(bi-weekly)
Geschw.-Scholl-Pl. 1 (A) Raum A 015L. Schwarzmeier


Enrollment Key: HighDimBio26

Enrollment Key: MDI2026

Schedule:

Time Lecturer Begin

Lecture

 Monday, 10:15 - 11:45
 Prof. Dr. Heumann
 13.04.2026
Lecture  Tuesday, 14:15 - 15:45  Prof. Dr. Heumann
 14.04.2026

Exercise course     
(Group 1)

 Wednesday, 08:15 - 09:45  Sapargali, Garces Arias 
 22.04.2026

Exercise course
(Group 2)

 Wednesday, 14:15 - 15:45  
 Sapargali, Garces Arias 
 22.04.2026
Tutorial
 Thursday, 08:15 - 09:45  Jai Lunkad  16.04.2026



Enrollment Key
  • The enrollment key is "stat_inf_s26"
Note: the course is creditable for "Mathematische Statistik, M.Sc. Mathematik WP5 (PO2021)".

Welcome to this introductory course on causality! This is where we gather all the material and organize the in-person sessions.

Dates [Summer Term 2026]


Lecture: Monday, 12h15 - 13h45
Lecture/Exercise (alternating): Tuesday, 08h30 - 10h00


If self-enrollment in this moodle course does not work automatically, you need to register via the backdoor ;)
--> Enrollment key: backdoor

Extreme Value Theory (EVT) studies the statistical behavior of rare and extreme events, which are central to risk assessment and appear frequently in risk management, finance, insurance, and environmental sciences. In this seminar, students read and present selected book chapters and research papers covering the basic principles of EVT, including limit theorems for extremes, block-maxima and peaks-over-threshold methods, tail index estimation, and extrapolation beyond the observed range. The seminar emphasizes core tools and techniques, diagnostic methods, model assumptions and limitations, and selected advanced models for dependent or multivariate extremes.

 There will be 2 block days for the presentations (during the semester).


Termine:

TerminOrtPersonBeginn
VorlesungDi, 08:30-10:00
Mi, 10:15-11:45
Schellingstr. 3 (S) - S 001
Schellingstr. 3 (S) - S 005
Thomas Nagler14.04.2026
 Tutorium Fr, 12:15-13:45 Schellingstr. 3 (S) - S 004 Eugen Gorich 16.04.2026
Übungsgruppe 1Mo, 16:15-17:45Geschw.-Scholl-Pl. 1 (B) - B 006Tobias Brock20.04.2026
Übungsgruppe 2Do, 12:15-13:45Geschw.-Scholl-Pl. 1 (B) - B 106Tobias Brock23.04.2026

    Einschreibeschlüssel
    • Der Einschreibeschlüssel lautet: "linalg2026"

    Einschreibeschlüssel: sample2026

    Der Schlüssel zum Einschreiben ist Stat2NFSoz26.

    The seminar will present and discuss current statistical analyses of the climate crisis, including climate change, extreme climatic events, and natural hazards. There will be four focal points. 

    1. Uncertainty Modeling in Climate Simulation

    2. Drought prediction (short, seasonal, long-term)

    3. Discussion of tipping points in climate change. The current scientific discussion and the uncertainty will be the issue

    4. Measurement of Biodiversity and relationship to climate change      

    Students are expected to engage intensively with the scientific literature, present the statistical methodology for the chosen topic, and/or replicate results from the literature. The Seminar meetings, presentations, and final report will be in English. We also recommend good skills in git and GitHub. It is possible to present your topics and, if suitable, to work on them in the seminar. The final results of the Seminar will be published as Chapters online in a Book.

    Key: CCstats26

    Enrolment key: RegCor26

    Format: In-person lectures and lab sessions

    Dates & Rooms:
    Wed 10-12  / Thu 14-16 @ E006 (Main Building)

    Grading: Oral exams at the end of the semester.


    Einschreibeschlüssel: StoSta26

    Termine
    Vorlesung:

    Di  & Do 12-14 (A 140 HGB)

    Übungen:

    Mi 12-14 (M 114 HGB  - in english) 
    Mi 14 -16 (M 114 HGB - auf deutsch)
    Do 14-16 (M 105 HGB - in english)

    Klausur:

    Do 30.7. 9-12 (voraussichtlich)

    Organisation

    Veranstaltung    Termin                      Ort
    Vorlesung  
    Mo, 12.00 - 14.00
    Schellingstr. 3 - S 003
    Vorlesung
    Di, 10.00 - 12.00
    Schellingstr. 3 - S 001
    Übung
    Do, 08.00 - 10.00 
    HGB - E 216
    Übung
    Do, 14.00 - 16.00
    HGB - B 106
    Tutorium
    Di, 12.00 - 14.00  
    HGB - D 209

    Einschreibeschlüssel 

    LiMo_s26



    This seminar explores open topics in Human-AI collaboration in statistical and data science contexts, with a focus on design, evaluation and validation skills for implementing trustworthy workflows.

    Learning Objectives

    • Critically evaluate AI-assisted workflows in statistical and data science contexts, with a focus on integrating statistical and computational perspectives.
    • Identify limitations of standard accuracy-based evaluation metrics for complex, multi-step tasks.
    • Design, justify and/or evaluate AI-assisted data workflows involving non-linear, exploratory statistical tasks.
    • Conduct independent research and communicate findings in a scientific paper or research software prototype.
    • Give and receive structured feedback on research-in-progress.

    Schedule & Format

    Location TBC -- see Moodle announcements

    • Thursday, April 23, 12.30-2PM: Introductory lecture, discussion of pre-readings, form research directions and groups
    • Thursday, May 7, 12.30-2PM: Feedback on research directions, discussion of additional readings
    • Monday, Jun 22, 12-2PM: Progress presentations and feedback
    • [Tentative] Week of Jul 20: Final presentations
    • [TBCAug: Submission of final papers

    Language: English (papers and presentations)
    Recommended background: Introductory statistics, basic programming experience; familiarity with using LLMs and agentic workflows

    Enrollment Key: human-ai-collab




    This class will teach students advanced skills in R, building on the ”Einführung in die Statistische Software für NF” class. Participants will learn advanced workflows using statistical software, more complex functions, packages and applications. Examples and exercises are designed to be as close as possible to real-life scenarios and an additional focus is put on understanding the handled data. Class participants should have fundamental skills in R and have ideally
    completed the ”Einführung in die Statistische Software für NF” class (regularly taught in winter semesters).


    Enrollment key: STATPROG26

    Die statistische Analyse von Netzwerkdaten ist ein wachsendes Gebiet. Netzwerkdaten sind inhärent nicht i.i.d., denn die Verbindung zwischen zwei Akteuren hängt ab von den sonstigen Verbindungen im Netzwerk. Ein klassisches Beispiel sind soziale Netzwerke, an denen sich Eigenschaften wie „der Freund meines Freundes ist mein Freund“ beobachten lassen.

    Das Seminar führt ein in das Thema. Wir besprechen Datenstrukturen, graphische Darstellungen und statistische Modelle für Netzwerkdaten. Die Beispiele werden numerisch in R begleitet.

    Als Grundlage für das Seminar dient das Buch Network Analysis von Rawlings, Smith, Moody und MaFarland, jüngst erschienen bei Cambridge University Press

    https://www.cambridge.org/core/books/network-analysis/C9202FD5420BE99225FEED4B6214DBB7#fndtn-metrics

    Organisation: Wöchentliche Termine (Mai - Juni)

    Kick Off: 14. April

    Sprache: Die Vorträge können in deutscher und englischer Sprache gehalten werden. Die Betreuung erfolgt in deutscher und englischer Sprache. Die Literatur ist englischsprachig.

    Einschreibeschlüssel: adjacency26



    LECTURE: Wednesday 12:00 - 14:00 c.t. (Prof.Huber-Platz W201, Raumfinder)

    EXERCISE: Thursday 16:00 - 18:00 c.t. (Schellingstr. 03 S003, Raumfinder)

    Format: inverted classroom with 90-minute lecture session + 90-minute exercise session.
    Language: English

    Self-enroll key: sl_summer_26

    Block Course - March16th - 26th 2026

    Entropy  is defined as a measurable physical property that is most commonly associated with a state of disorder, randomness, or uncertainty. It is strongly connected with  probability distributions  and the principle of  maximum entropy  can be very useful in statistical inference, in particular in Bayes statistics. In this course, we will introduce the concept of entropy in the context of information theory as well as apply the concepts to real data sets.

    Syllabus

    1. Introduction and Preview
    2. Entropy, Relative Entropy, and Mutual Information
    3. Asymptotic Equipartition Property
    4. Entropy Rates of a Stochastic Process
    5. Differential Entropy
    6. Information theory and statistics

    Schedule:   The course will be held online in English.

    Information Theory and Entropy for Master Statistics and Data Science, Master Data Science, Master Statistics, Master Biostatistics, Master Statistics WiSo.

    Enrollment key: entropy_2026

    Instructors:

    Time:

    • Lecture: Every Monday 16:00 - 18:00 (c.t.)  -> Room: Geschw.-Scholl-Pl. 1 - M 010
    • Labs: Every Thursday 10:00 - 12:00 (c.t.) -> Room: Geschw.-Scholl-Pl. 1 - A 125

    Start:

    • Note: Due to labor day (public holiday), 
      • the first lab session will be on May 8
      • the first lecture session will be on May 5

    Enrollment Key:

    • Singularity

    Termine

    • Wiederholungsübungen: 
      • Do 10-12
      • Fr 10-12

    Einschreibeschlüssel

    • Der Einschreibeschlüssel lautet "stats26wdh"


    This course will provide a comprehensive introduction to univariate time series analysis, covering key concepts such as stochastic processes, trend modeling, and linear filters. We will also model and forecast time series using both ARIMA and GARCH processes, focusing on estimation techniques and practical applications. 

    Enrollment Key (Einschreibeschlüssel): UTSA_2026

    Person: Dr. Cornelia Oberhauser

    SAS Course as a 5-day block course during the semester break

    Dates:

    Day

    Time
    Room
    Mon 09.03.2026 Lecture 9:15 - approx. 12:15
    online via Zoom

    Exercise
    13:15 - 17:00
    online via Zoom
    Tue 10.03.2026 Lecture
    9:15 - approx. 12:15 online via Zoom
    Exercise
    13:15 - 17:00 online via Zoom
    Thu 12.03.2026 Lecture
    9:15 - approx. 12:15 online via Zoom
    Exercise
    13:15 - 17:00 online via Zoom
    Mon 16.03.2026 Lecture
    9:15 - approx. 12:15 online via Zoom
    Exercise
    13:15 - 17:00 online via Zoom
    Tue 17.03.2026 Lecture
    9:15 - approx. 12:15 online via Zoom
    Exercise
    13:15 - 17:00 online via Zoom

    Enrolment key

    • The enrolment key is: ‘saskurs2026’

    Guest key

    • The guest key is: ‘saskurs2026’

    Schedule:

    Day & TimeRoom  
    LectureTuesday, 14:15-16:45  Geschw.-Scholl-Pl. 1 - A 016
    Exercise Friday, 12:15-13:45Geschw.-Scholl-Pl. 1 - A 016

      Enrolment key
      • The enrolment key is: "DAS26"


      Der Kurs zur Einführung in die statistische Datenanalyse wird vom Statistischen Beratungslabor der LMU (StaBLab) angeboten. Ziel der Kurse ist es, den Teilnehmerinnen und Teilnehmern grundlegende statistische Kenntnisse zu vermitteln und sie dazu zu befähigen, diese eigenständig in ihren Projekten anzuwenden. Die Veranstaltungen zeichnen sich durch einen starken Praxisbezug aus und basieren auf den vielfältigen Erfahrungen aus der statistischen Beratung am StaBLab.

      Der Kurs teilt sich auf in einen Grundkurs und einen Aufbaukurs. Der Grundkurs vermittelt Grundlagen aus Theorie (Kurzeinführung in die Statistik) und Praxis (Vertiefung der Theorie, Umgang mit der statistischen Software R). Der Aufbaukurs widmet sich schwerpunktmäßig der Regression und der fortgeschrittenen Gestaltung von Graphiken in R sowie der Diskussion praktischer Fragestellungen (gerne auch anhand von Projekten der Kursteilnehmer). Die Bearbeitung der Praxisaufgaben findet am eigenen Laptop statt, da PC-Arbeitsplätze nicht gestellt werden können. Für den Grundkurs sind drei Blöcke und für den Aufbaukurs zwei Blöcke mit je zwei dreistündigen Einheiten geplant.

      Zielgruppe:
      Studierende, Promovierende und wissenschaftliche Mitarbeiter an der LMU, die sich in ihrer Abschluss- bzw. Forschungsarbeit mit quantitativen Analysen beschäftigen werden und geringe bzw. keine statistischen Kenntnisse haben, oder grundsätzlich Interesse haben, die freie Statistiksoftware R zu erlernen. Insbesondere ist es empfehlenswert, den Grundkurs vorbereitend zu einer Beratung beim StaBLab zu besuchen.

      Master course 

      • Master Statistics & Data Science – WP44 Advanced Statistical Modelling
      • ESG Data Science – Elective
      • Master Statistik (mit WiSo), Biostatistik – Ausgewählte Gebiete... oder Schätzen und Testen II (mit Zusatzleistung)

      Enrolment Key: Thomas

      Date and time

      Tuesday, 12-14        Geschw.-Scholl-Pl. 1 - M 109
      Friday, 10-12        Geschw.-Scholl-Pl. 1 ­- E 216

      Content: 

      Bayesian methods have seen increasing use within statistics in the last couple of years. In Bayesian frameworks, prior knowledge can be integrated as prior distribution. These also allows to regularise parameters in large p>>n models via priors, up to the point where the prior becomes part of the statistical model itself.

      In this course, advanced Bayesian models will be discussed. These include several types of latent models, in particular latent Gaussian fields, applied for example to time series and spatial data, mixed effect models and other structured regression models. The course will also cover different type of algorithms to assess the posterior, based on Monte Carlo methods and on approximation. Further topics include Bayesian model and variable selection and Bayesian classification.

      Requirements

      Students should be familiar with basics of Bayesian statistics.

      Recommended: 

      • Statistical inference
      • Statistical modelling

      Learning outcomes:

      After successfully completing the course, students will be able 

      • to understand Bayesian models 
      • to apply Bayesian modelling for appropriate data
      • to interpret the results of Bayesian models 
      • to implement Bayesian models in standard software

      Statistik II für Statistiker: Wahrscheinlichkeitstheoretische Grundlagen der Statistik


      TerminHörsaalDozent
      VorlesungMo 10-12
      Volker Schmid
      Do 9–12
      Übung Gruppe 1Mo 14–16
      Daniel Schlichting
      Übung Gruppe 2Mi 12–14
      TutoriumDi 18-20
      Michael Kobl

      Einschreibeschlüssel: Radon-Nikodym


      Schedule

      • Lecture: 
        • Wednesday, 12-14 c.t.
        • Location: Oettingenstraße 67, 151 (Raumfinder)
      • Tutorial: 
        • Tuesday, 16 - 18 c.t.

        Enrollment key

        • Enrollment key: <think>


        Termine

        • Vorlesung: Dienstag, 16 - 18 c.t.
        • Übungen (Statistik II): 
          Mittwoch, 12 - 14 c.t. & 14 - 16 c.t.
        • Übung (Statistik I):
          Montag, 10 - 12 c.t.

        Einschreibeschlüssel

        • Der Einschreibeschlüssel lautet "2026wiwistat".