Mathematical Statistics Lecture 2021 Jun 2026

Parameters are treated as random variables with probability distributions. We update our "prior" knowledge with new data to obtain a "posterior" distribution. 6. Applications of Mathematical Statistics

n(X̄n−μ)dN(0,σ2)the square root of n end-root open paren cap X bar sub n minus mu close paren cap N open paren 0 comma sigma squared close paren

Lectures teach you standard algorithmic ways to construct estimators from data. Maximum Likelihood Estimation (MLE)

drawn from a probability space. The joint distribution of these random variables belongs to a parametrized family: mathematical statistics lecture

Estimation asks "What is $\theta$?" Hypothesis testing asks "Is $\theta$ equal to a specific value?"

Understanding the risks of "false alarms" versus "missing a real effect."

A foundational covers testing whether a claim is supported by evidence. Null (H₀) vs. Alternative ( Hacap H sub a ) Hypotheses: Setting up the scenario. Parameters are treated as random variables with probability

): The probability of correctly rejecting a false null hypothesis. -value Approach

: Evaluating whether a specific supposition about a population parameter is supported by experimental data. Likelihood Ratio

Should we add a section on vs. Frequentist Statistics? Share public link Null (H₀) vs

Understanding discrete (Binomial, Poisson) versus continuous (Normal, Exponential, Gamma) variables.

Bayesian statistics offers an alternative perspective to the frequentist paradigm. Instead of treating as a fixed, unknown constant, Bayesian inference treats as a random variable with its own probability distribution. Bayes' Theorem for Inferences

For students, listening to a derivation of the Cramér–Rao bound can feel like watching a magic trick from the third row. Here is how to move to the front row.