Generalized linear models: fitting and evidence
Specify grouped-binomial and Poisson responses, derive vector fitting steps, distinguish finite existence from bounded computation, and audit conditional uncertainty and frozen checks.
Open any lesson. Completion records participation; automatic practice checks and human judgment of written arguments are separate. This unit retains its own versioned requirements.
Readiness and preparation
Loading saved mathematics work…
GLM specification, computation and evidence
The mixed assessment has separate response history and review criteria; it does not change lesson participation records.
Lesson sequence
Each linked lesson opens on its own page. Expand its details here when you want to check the objectives before choosing.
Response families and link scales
Lesson details and objectives
Response families and link scales. Derive, calculate and qualify a fitted response model.
- Connect response support, design and a conditional probability model.
- Show intermediate calculations and prove the relevant general statement.
- Report numerical and inferential limitations separately.
6 practice tasks.
Score, information and IRLS
Lesson details and objectives
Score, information and IRLS. Derive, calculate and qualify a fitted response model.
- Connect response support, design and a conditional probability model.
- Show intermediate calculations and prove the relevant general statement.
- Report numerical and inferential limitations separately.
6 practice tasks.
Bounded fitting and finite existence
Lesson details and objectives
Bounded fitting and finite existence. Derive, calculate and qualify a fitted response model.
- Connect response support, design and a conditional probability model.
- Show intermediate calculations and prove the relevant general statement.
- Report numerical and inferential limitations separately.
6 practice tasks.
GLM uncertainty and model checks
Lesson details and objectives
GLM uncertainty and model checks. Derive, calculate and qualify a fitted response model.
- Connect response support, design and a conditional probability model.
- Show intermediate calculations and prove the relevant general statement.
- Report numerical and inferential limitations separately.
6 practice tasks.