Lecture

Elements of Statistics: Probability, Distributions, and Estimation

Graph Chat

Chat with Graph Search

Ask any question about EPFL courses, lectures, exercises, research, news, etc. or try the example questions below.

DISCLAIMER: The Graph Chatbot is not programmed to provide explicit or categorical answers to your questions. Rather, it transforms your questions into API requests that are distributed across the various IT services officially administered by EPFL. Its purpose is solely to collect and recommend relevant references to content that you can explore to help you answer your questions.

In course

MICRO-428: Metrology

The course deals with the concept of measuring in different domains, particularly in the electrical, optical, and microscale domains. The course will end with a perspective on quantum measurements, which could trigger the ultimate revolution in metrology. ...

Description

This lecture covers the fundamental concepts of statistics, focusing on probability theory, various distributions such as uniform, Gaussian, binomial, Poisson, and exponential, and estimation theory. Topics include moments, covariance, correlation, the Law of Large Numbers, and the Central Limit Theorem. The instructor discusses the accuracy, precision, and resolution of measurements, error analysis, and the importance of ergodicity in random processes.

This video is available exclusively on Mediaspace for a restricted audience. Please log in to MediaSpace to access it if you have the necessary permissions.

Watch on Mediaspace

Instructors (3)

Georg Fantner

Claudio Bruschini

Claudio Bruschini holds an MSc in high energy physics from the University of Genova and a PhD in Applied Sciences from the Vrije Universiteit Brussel (VUB). He started his career with INFN (Italy, 1993), in the WA92 CERN collaboration (particle physics), and then moved to CERN as a Fellow in the European GP-MIMD2 project, attached to the NA48 collaboration (particle physics, parallel programming, 1994-1995). He then started his close collaboration with EPFL, first in the DeTeC (Demining Technology Center) project (sensors for landmine detection/humanitarian demining, 1996-1997). After DeTeC's end, he started the first of a series of fruitful collaborations with the Vrije Universiteit Brussel (VUB) on humanitarian demining related R&D (1998). This was followed by the EUDEM survey project (The European Union in Humanitarian Demining, 1998), the EUDEM2 three year EC sponsored support measure (www.eudem.info, 2001-2004), and the DELVE support action (www.delve.vub.ac.be, 2007). In parallel he started working within the EPFL's AQUA group (Advanced Quantum Architectures, Edoardo Charbon), on topics as diverse as ultrasonic sensors for in-air application, optical 3D and high speed 2D sensing, sensor networks, or tracking/motion capture systems, in particular for the preparation of research projects. This culminated in the European MEGAFRAME (www.megaframe.eu, FP6, 2006-2010, SPAD arrays and related in-pixel time stamping electronics in deep submicron CMOS technology) and SPADnet (www.spadnet.eu, FP7, 2010-2014, networked SPAD arrays for Positron Emission Tomography) projects, coordinated by EPFL-AQUA. As from 2009 he also worked with Dario Floreano on the management of the CURVACE Curved Artificial Compound Eyes FP7 project (www.curvace.org), coordinated by EPFL-LIS. He was also active with CHUV (Lausanne University Hospital) within EndoTOFPET-US (endoscopic PET) as well as on a CTI project devoted to the development of a new hand-held standalone tool for tracer-guided medical procedures. In 2014 he had also the pleasure of joining the EPFL ICLAB of Christian Enz during its ramp-up phase, collaborating on device related topics (SNF GigaRadMOST) and biomedical R&D (NanoTera WiseSkin). Claudio is now fully with EPFL’s Advanced Quantum Architecture (AQUA). He has also been active as independent scientific consultant, under the label CBR Scientific Consulting, on the preparation of (European) R&D project proposals and the execution of individual studies, and worked in 2006 for a local start-up as operations manager and R&D advisor.... but this is another story. An unauthorized early biography is available at http://lami.epfl.ch/team/claudiob/...

Official source

Ontological neighbourhood

Statistics

Statistical inference: Mathematical statistics

Data analysis: Regression analysis

Related concepts (32)

Maximum likelihood estimation

In statistics, maximum likelihood estimation (MLE) is a method of estimating the parameters of an assumed probability distribution, given some observed data. This is achieved by maximizing a likelihood function so that, under the assumed statistical model, the observed data is most probable. The point in the parameter space that maximizes the likelihood function is called the maximum likelihood estimate. The logic of maximum likelihood is both intuitive and flexible, and as such the method has become a dominant means of statistical inference.

Linear least squares

Linear least squares (LLS) is the least squares approximation of linear functions to data. It is a set of formulations for solving statistical problems involved in linear regression, including variants for ordinary (unweighted), weighted, and generalized (correlated) residuals. Numerical methods for linear least squares include inverting the matrix of the normal equations and orthogonal decomposition methods. The three main linear least squares formulations are: Ordinary least squares (OLS) is the most common estimator.

Gauss–Markov theorem

In statistics, the Gauss–Markov theorem (or simply Gauss theorem for some authors) states that the ordinary least squares (OLS) estimator has the lowest sampling variance within the class of linear unbiased estimators, if the errors in the linear regression model are uncorrelated, have equal variances and expectation value of zero. The errors do not need to be normal, nor do they need to be independent and identically distributed (only uncorrelated with mean zero and homoscedastic with finite variance).

Least squares

The method of least squares is a standard approach in regression analysis to approximate the solution of overdetermined systems (sets of equations in which there are more equations than unknowns) by minimizing the sum of the squares of the residuals (a residual being the difference between an observed value and the fitted value provided by a model) made in the results of each individual equation. The most important application is in data fitting.

Stable distribution

In probability theory, a distribution is said to be stable if a linear combination of two independent random variables with this distribution has the same distribution, up to location and scale parameters. A random variable is said to be stable if its distribution is stable. The stable distribution family is also sometimes referred to as the Lévy alpha-stable distribution, after Paul Lévy, the first mathematician to have studied it. Of the four parameters defining the family, most attention has been focused on the stability parameter, (see panel).

Related lectures (64)

Elements of Statistics: Probability and Random Variables

Introduces key concepts in probability and random variables, covering statistics, distributions, and covariance.

Elements of Statistics: Estimation & Distributions

Covers fundamental statistics concepts, including estimation theory, distributions, and the law of large numbers, with practical examples.

Probability and Statistics

Covers probability, statistics, independence, covariance, correlation, and random variables.

Central Limit Theorem: Properties and Applications

Explores the Central Limit Theorem, covariance, correlation, joint random variables, quantiles, and the law of large numbers.

Dependence and Correlation