Credit points: 15
Statistical inference is used to describe procedures that draw conclusions from datasets arising from systems affected by random variation.This subject comprises components in estimation and testing hypotheses. Topics in the first component include method of moments and maximum likelihood, reduction by sufficiency and invariance, unbiasedness, consistency, efficiency and robustness. The second component examines size and power of tests, Neyman-Pearson lemma, optimality of tests, the likelihood ratio test and relationship to confidence interval estimation. This subject is co-taught with STM3SI. For STM4SI there is greater emphasis on research and inquiry with an expactation that students independently formulate proofs for extension questions related to the subject material.
SchoolSchool Engineering&Mathematical Sciences
Subject Co-ordinatorAndriy Olenko
Available to Study Abroad StudentsYes
Subject year levelYear Level 4 - UG/Hons/1st Yr PG
Prerequisites STA2MD or STM2PM
Incompatible subjects STA3SI, STA4SI, STM3SI
|Resource Type||Title||Resource Requirement||Author and Year||Publisher|
|Readings||Introduction to Probability and Mathematical Statistics||Recommended||Bain LJ, Engelhardt M 2000||2ND ED, DUXBURY.|
|Readings||Online learning materials (readings and examples)||Prescribed||2016||La Trobe University|
Graduate capabilities & intended learning outcomes
01. Research, model and solve problems when randomness is involved
- 8 assignments and weekly problem classes involve various modelling and problem solving questions. One question on each of four assignments provides little guidance and therefore requires students to research possible solutions.
02. Present clear, well structured proofs of important theoretical statistical model results. This includes detailed referencing to inportant statistical principles.
- Weekly problem classes involve theoretical derivations of results introduced in lectures. One question on each of four assignments provides little guidance and therefore requires students to research possible solutions to prove statistical results.
03. Compute/derive mathematical calculations to investigate numerical properties of statistical models
- 12 problem classes where students need to do this to solve complex problems. Modelled as worked examples in Lectures
04. Present clear, well structured explanations of numerical results. This includes appropriate use of statistical and mathematical vocabulary
- 8 assignments includes a 10% mark for each assignment relating to students written expression and clarity.
05. Independently formulate proofs for key theoretical results presented in the lectures.
- 8 assignments include 20% of marks relating to research and enquiry where questions may only be answered with correct referencing to resources.
Select to view your study options…
Melbourne, 2018, Semester 1, Day
Maximum enrolment sizeN/A
Subject Instance Co-ordinatorAndriy Olenko
Three 1.0 hours lecture per week on weekdays during the day from week 10 to week 22 and delivered via face-to-face.
One 1.0 hours practical per week on weekdays during the day from week 10 to week 22 and delivered via face-to-face.
|8 Assignments (approx. 200-250 words each)||30||01, 02, 03, 04|
|3-hour short answer Final Examination (approx. 3000 words)||70||01, 02, 03, 04, 05|