Short Courses


Over the course of the year Stats Central teaches several short courses aimed at researchers across all disciplines. Offerings in 2019 include:

  • Introduction to R
  • Introductory Statistics for Researchers
  • Experimental Design
  • Introduction to Regression Modelling in R
  • Sample Size and Power Calculations (tentative)

Introduction to R

7 May, 2019

Course Overview

R is widely used and extremely powerful statistical software. This course assumes that you have never used R before. You will learn how to obtain and install R, which is open-source software, and RStudio, which is a versatile, user-friendly interface for using R.

This one-day introduction to R will cover some basic features of R and lay the groundwork for you to improve your R skills independently. The course is self-paced and focussed on developing practical skills.

Note: It is very useful to do this course before our introductory statistics course, Introductory Statistics for Researchers.

Course Outline

We will cover:
  • calculations in R - addition, subtraction, multiplication, division, exponentiation (raising something to a power)
  • variables - how to store values so you can easily reuse them
  • types of data - different types of data structures and how to store them (e.g. numbers, text and Boolean (TRUE or FALSE) values)
  • organising R code and data so you can easily reuse them at a later date (script files and working directories)
  • efficient ways to create patterns of numbers
  • logical operators useful for manipulating data (e.g. <, >, etc.)
  • handling "spreadsheets" in R (matrices and data frames)
  • adding comments to your code so people you share code with can easily follow it
  • using inbuilt R Help files and other help resources
Duration: 9.00am to 5.00pm
Location: UNSW Business School (E12), Level 1, Room 119, UNSW Kensington Campus

Requirement: You will need to bring your own laptop to the workshop.

UNSW students: $125
UNSW staff: $250
External Student: $450
External: $600
Course fee includes morning tea and lunch


Introductory Statistics for Researchers

8 - 9 May, 2019

Course Overview

In many disciplines, researchers wishing to publish are asked to provide a rigorous statistical analysis. Reviewers are often specific about what statistical measures they want included. "Why wasn't Fisher's Exact Test used?" "Was an appropriate sample size determined a priori?"
Statistical analyses require specialised software to perform calculations. In this course, we use the free statistical program R, although researchers may have another statistical package available to them.
How does one decide which statistical procedure is the most appropriate? What do all the pages of the printout mean?
This course is designed as an introduction to statistical design and analysis for researchers. There is emphasis on understanding the concepts of statistical procedures (with a minimum of mathematics, although some will be discussed) and on interpreting computer output. This course is designed to help you, the researcher. It is helpful if you have done an undergraduate statistics subject, although this course can serve as a first introduction or a refresher.
Instructions on how to obtain computer printouts will be provided with an emphasis on interpreting the computer printout (most packages produce similar printouts). There will be plenty of practical work throughout the course.
Do you need to have previous experience using the program R?
It would be very helpful if you have some basic knowledge of R. We recommend our one-day course, Introduction to R (see above), which runs just prior to this course. However, previous experience with statistical packages like SAS, SPSS or Stata and some basic programming skills are also helpful.
Please note that R and R Studio are free to use and are both available for Windows/Mac/Linx platforms. The links are provided below:
You can play around with the software before deciding on the course. Here is a really good website with some introductory notes for doing statistics in R.
Course Outline
Types of experiments, scales of measurement, which method to use.
In this course, the statistical software package used is R. We do not use or demonstrate SPSS.
Summarising and Graphing Data
Ways of presenting data (histograms, boxplots), measures of centre and spread, analysing tables, correlation, and confidence intervals.
Comparing Groups
Hypothesis testing concepts - power, significance, P-value. Comparing two groups (t-tests, Wilcoxon). Comparing many groups (with one treatment factor) - one-way ANOVA or Kruskal-Wallis - multiple comparison tests.
Finding Relationships
Correlation, predicting relationships (regression - simple).
Other topics covered
Non-Normal data - transformations and non-parametric tests. If time is available, we will briefly discuss sample size and power.
Duration: 2 days, 9.00am to 5.00pm daily
Location: UNSW Business School (E12), Level 1, Room 119, UNSW Kensington Campus
Bring your own laptop computer.
UNSW students: $200
UNSW staff: $400
External Student: $750
External: $1,000
Course fee includes morning tea and lunch


Experimental Design

30 May, 2019

This is a one-day short course which covers the essentials of experimental design. Topics covered include randomisation, controls, sample size, reducing variability and pilot studies. This course will also have a practical component using online tools and the software packages, Excel and G*Power.

Course Overview

  • Research questions: How to ask well-defined research questions
  • Populations: How to infer properties of populations from samples
  • Manipulative experiments: Sampling design to infer causal relationships
  • Randomisation: How to collect independent samples for valid inference
  • Control: Importance of comparing to a control group, properties of good controls
  • Sample size: Determining how much data to collect to answer the research question
  • Reducing variability: How blocking and stratification can reduce variability and improve power
  • Pilot study: How pilot studies can save time and money

Practical Component

  • How to randomise – Random allocation of subjects to treatments and random sampling in space
  • Simple power analysis – How much data do we need to answer the question of interest?
  • We will use free online tools and the software packages, Excel and G*Power

Duration: 9.00am to 5.00pm

Location: UNSW Business School (E12), Level 1, Room 115, UNSW Kensington Campus

Requirement: You will need to bring your own laptop to the workshop.

UNSW students: $125
UNSW staff: $250
External Student: $450
External: $600
Course fee includes morning tea and lunch


Sample Size and Power Calculations

7 November, 2018

Power calculations and sample size determination are essential parts of planning a scientific study. In this one-day course we will introduce the basic principles of precision-based and power-based sample size calculations. We will demonstrate how to perform sample size calculations for various outcome types in single-sample studies and for comparing groups, as well as discussing related issues such as multiple comparisons. This course will highlight some useful R packages and provide the tools for running basic simulations in R.

Course outline:

  • Introduction and motivation

  • Basic principles of power and sample size calculations

  • Single-sample studies

  • Comparing groups: normally-distributed outcomes

  • Comparing groups: other outcome types

  • Complex power calculations via simulation

  • Other issues

Course fees include morning and afternoon teas and lunches.

Duration: 9.00am to 5.00pm
Location: Law Theatre G23, UNSW Law Building (F8)
Bring your own laptop computer.

Introduction to Regression Modelling in R

18-20 June, 2018

The core outcome from this course is to recognise that most statistical methods you use can be understood under a single framework, as special cases of (generalised) linear models. Learning statistical methods in a systematic way, instead of as a "cookbook" of different methods, enables you to take a systematic approach to key steps in analysis (like assumption checking) and to extend your skills to handle more complex situations you might encounter in the future (random factors, multivariate analysis, choosing between a set of competing models).

This three-day short course is aimed at applied researchers with prior experience using R and familiar with introductory statistics tools - you should know about the t-test, linear regression, analysis of variance and know something about orthogonal and nested designs.  If you have not used R before, we strongly recommend you learn basic features of R and how to use the RStudio interface to R before this course.  If you need to revise introductory statistics material, you should attend the Introductory Statistics for Researchers course in September 2018 and then take this regression course later, as the material in the Introductory Statistics for Researchers course is taken as assumed knowledge for this regression course.

An outline of topics included in this regression course is below (click the "+" on the right).

Course fees include morning and afternoon teas and lunches on all days.

You will need to bring your own laptop! We will sort out internet access for you.

Course outline

Linear regression
Simple linear regression, including assumptions, influential observations and inference
Equivalence of two-sample t-test and linear regression

Linear models with multiple predictor variables
Multiple regression
Analysis of variance (ANOVA), including multiple comparisons
More linear models
Paired and blocked designs
Factorial experiments
Interactions in regression
Model selection
Information criteria (AIC, BIC)
Penalised estimation (LASSO)

Mixed effects models
Random effects
Linear mixed effects models
Inference for mixed models, including likelihood ratio tests, parametric bootstrap, hypothesis tests, confidence intervals
Correlated random effects
Wiggly models
Spline smoothers, including diagnostics and interactions
Generalised linear models (GLMs)
Examples of GLMs
Fitting GLMs and checking assumptions, including mean-variance relationship
Extensions - offsets, zero-inflated models