# Analysing 2x2 Tables: Chi-Square Test and Beyond

• 5 hours
• 1 day
• 28 February 2019

## Overview

This one-day course aims to demystify the range of statistics that can be used to summarise the associations between two binary variables.

It'll move beyond standard chi-square tests to investigate other options that may yield more useful information.

This course is run by UCL's Centre for Applied Statistics Courses (CASC) - part of the UCL Great Ormond Street Institute of Child Health (ICH).

## Course content

When faced with exploring the relationship between two binary variables (e.g. comparing the percentage who test positive between two treatment groups, or between two subgroups such as males and females) it's common to display this as a 2x2 table and use a chi-square test to determine the statistical significance of any difference. Chi-square tests are commonly used to compare the percentage of individuals in two groups who share a trait.

However, there are many other statistics that may be applied to a 2x2 table to provide more useful information.

This course aims to help guide researchers through alternative analyses to decide on the most appropriate investigation of their data.

The following tests and concepts are covered in the course:

• Fishers exact testing
• Absolute risk reduction (ARR)
• Proportions tests
• Number needed to treat (NNT)
• Relative risk (RR)
• Attributable risk (AR)
• Odds ratio (OR)
• Kappa
• Sensitivity and specificity
• Positive and negative predictive values
• Likelihood ratios

For each statistic we consider the interpretation and appropriate usages.

## Who this course is for

The course is for non statisticians and is open to anyone who needs to understand or analyse 2x2 tables.

Knowledge of the very basics of statistics (such as means, standard deviation, confidence intervals, etc.) is beneficial.

## Learning outcomes

By the end of this course you should be able to:

• understand what a chi-square significance test actually shows
• understand the difference between chi-square and Fishers exact test, ARRs and NNT
• understand the relative measures (RR, AR and OR)
• know how to assess agreement for a 2x2 table
• understand diagnostic statistics and their application
• be better equipped to determine the best test to use for a 2x2 table

## Cost and concessions

The fees are as follows:

• External delegates (non UCL) - £125
• UCL staff, students, alumni - £62.50*
• ICH/GOSH staff and students - free

* valid UCL email address and/or UCL alumni number required upon registration

Prices include printed course materials, refreshments (and lunch for non-ICH  participants).

## Certificates

You can request a certificate of attendance for this course once you've completed it. Please send your request to ich.statscou@ucl.ac.uk

Include the following in your email:

• the name of the completed course for which you'd like a certificate
• how you'd like your name presented on the certificate (if the name/format differs from the details you gave during registration)

## Cancellations

Cancellations will be accepted up to five working days before the start of the course with a full refund, though as much notice as possible would be appreciated in order to re-allocate the place.

Places cancelled or changed after this point won't be eligible for a refund. Please send all cancellation requests directly to the course administrator

## Find out about other statistics courses

CASC's stats courses are for anyone requiring an understanding of research methodology and statistical analyses. The courses will allow non-statisticians to interpret published research and/or undertake their own research studies.

Find out more about CASC's full range of statistics courses, and the continuing statistics training scheme (book six one-day courses and get a seventh free.)

Course team

Angie, Director of the Centre for Applied Statistics Courses (CASC), has been involved in the provision of statistical training to medically based non-statisticians for 25 years. She has a first class Bachelor’s degree in Mathematics and a Master's degree in Applied Statistics from UCL, and a PhD Statistics in the development of likelihood based models for the construction of covariate-related centiles. She joined GOS ICH in 1990, began the development of CASC in 2008 and was ICH’s first teaching professor. She's an active member of local teaching committees, previously chaired an MSc examination board and is currently a member of the UCL Academic Board Education Committee.

Student review

“Thank you, as ever, for running another great course!”

“Excellent, very clear presentation with the right amount of exercises in between, very useful.”