Mathematical Statistics Lecture [exclusive] -

Standard curricula for this subject, such as those found at MIT OpenCourseWare and the LSE , typically follow a structured progression: Mathematical Statistics (2024): Lecture 1

is the probability measure. This structure ensures that probabilities are mathematically consistent. Random Variables and Transformations A random variable

Mathematical statistics is often abstract, dealing with measure theory and asymptotics. However, its utility is concrete. Without it:

Problem: The professor fills three boards with algebra, erases the first one, and you are still on line 2. Solution: Stop copying. Take a photo with your phone. Listen to the narrative of the proof. Focus on the "why" of each major step (e.g., "Now we use integration by parts to simplify the expected value"). You can copy the algebra from the textbook later. mathematical statistics lecture

Where the Fisher Information from a single observation is defined as:

The population parameters are known. You predict the behavior of a sample.

The professor defines p-value as ( P(T \geq t_obs | H_0) ), but the homework asks for a two-tailed p-value for an asymmetric distribution. The fix: Remember the strict definition: The smallest ( \alpha ) for which you would reject ( H_0 ). If the distribution is asymmetric, you must double the smaller tail, or use the likelihood ratio principle. Standard curricula for this subject, such as those

is the , representing updated beliefs.

We assume the data comes from a specific probability distribution family (e.g., Normal, Binomial, Poisson) that is completely defined by a finite set of parameters.

Probability theory is the foundation of mathematical statistics. It provides a measure of the chance or likelihood of an event happening. However, its utility is concrete

There are often many unbiased estimators for the same parameter. We prefer the one with the smallest variance.

The default assumption (e.g., "The new drug has no effect"). Alternative Hypothesis ( Hacap H sub a ): The claim we are trying to prove.

Point estimation involves choosing a single best value to represent an unknown population parameter

and use Student’s t-distribution instead of the standard normal distribution. 5. Hypothesis Testing and Neyman-Pearson Framework

A simpler alternative. Equate sample moments (like the sample mean) to theoretical population moments and solve for the parameters. 6. Data Reduction: Sufficiency and Completeness