Lecture 01a

ANU - RSFAS

Semester 1, 2015

1 / 20

What is Statistics?

Statistics is the Science of Data or Data Science

2 / 20

Our Increasingly Quantitative World

The world is becoming quantitative. More and more professions, from the everyday to the exotic, depend on data and numerical reasoning.

Data are not just numbers, but numbers that carry information about a specific setting and need to be interpreted in that setting. With this growth in the use of data comes a growing demand for the services of statisticians, who are experts in

Producing trustworthy data,

Analyzing data to make their meaning clear, and

Drawing practical conclusions from data.

-The American Statistical Association.

3 / 20

Business

Economics, Engineering,

Marketing,

Computer Science

Health &

Medicine

Genetics, Clinical Trials,

Epidemiology,

Pharmacology

Areas where

STATISTICS

are used

Physical

Sciences

Astronomy,

Chemistry, Physics

Environment

Agriculture,

Ecology, Forestry,

Animal Populations

Government

Census, Law,

National Defense

4 / 20

“I keep saying the sexy job in the next ten years will be statisticians. People think I’m joking, but who would’ve guessed that computer engineers would’ve been the sexy job of the 1990s?”

-Hal Varian, The McKinsey Quarterly, January 2009

Nate Silver (data journalism) - http://www.fivethirtyeight.com

Andrew Gelman (academic blog) - http://andrewgelman.com

5 / 20

John Tukey (1915 - 2000)

“The best thing about being a statistician is that you get to play in everyone’s backyard.” — J. Tukey

– coined the terms ‘bit’ and ‘software’.

6 / 20

Backyards that I Play In

Assessing uncertainty in weather predication → Atmospheric Science.

Developing a ‘Health’ index for streams → Environmental Science.

Statistical models for game theoretic data → Political Science,

Economics.

Statistical models for network data → Sociology, Political Science,

Economics, Biology.

Statistical models for relating gene marker data to genetic line data to phenotype data → Biology.

7 / 20

Course Description

This course introduces students to the theory underlying the development and assessment of statistical techniques in the areas of: point estimation interval estimation hypothesis testing

8 / 20

Statistical Inference - the course and the notes are broken into the following three sections}

Point estimation

Frequentist (maximum likelihood, method of moments, . . .)

Bayesian

Non-Parametric (frequentist)

Interval estimation

Frequentist

Bayesian

Non-Parametric (frequentist)

Hypothesis testing

Frequentist

Bayesian

Non-Parametric (frequentist)

9 / 20

Format

Lectures in CBE Bld LT 2

Monday 10:00 - 11:00

Tuesday 1:00 - 2:00

Wednesday 2:00 - 3:00

Tutorial (starting in the second week)

Friday

STAT3013 10:00 - 11:00 (CBE Bld TR3)

STAT8027 1:00 - 2:00 (CBE Bld TR4)

10 / 20

Texts I

Prescribed Texts

G. Casella and R. Berger

Statistical Inference (second edition)

Brooks/Cole Cengage Learning

Recommended Reading

1. P. Garthwaite, I. Jolliffe and B. Jones

Statistical Inference (second edition)

Oxford University Press

2. G. Givens and J. Hoeting

Computational Statistics (second edition)

Wiley

11 / 20

Texts II

3. J. Kadane

Principles of Uncertainty http://uncertainty.stat.cmu.edu/wp-content/uploads/2011/ 05/principles-of-uncertainty.pdf

CRC Press

4. G. Parmigiani and L. Inoue

Decision Theory: Principles and Approaches

Wiley

12 / 20

Texts for Revision

D. Wackerly, W. Mendenhall, and R. Scheaffer Mathematical Statistics with Applications (seventh edition)

Duxbury, Thomson, Brooks/Cole (WMS).

R. Adams and C. Essex

Calculus: A Complete Course (eigth edition)

Pearson

13 / 20

Assesments

Final Examination (60% or 80%)

Mid-Semester Examination (20% or 0%) (redeemable in favour of the

Final)

Group Presentation/Project (15%)

Weekly Tutorial Solutions (5%)

14 / 20

Tutorials

Before each tutorial you should submit your answers to the tutorial questions online via Wattle.

These will be graded weekly for