Data Analytics Training

Data analytics for businesses and organisations (2 days)

This course is aimed at developing the capability of an organisation (e.g. a Business Intelligence team) to understand data, analytical methods, interpretation and presentation to a wide range of audiences. It is based on taking a more analytical and critical approach to key data series and performance indicators, ensuring that the maximum value is extracted from the data for the benefit of the business. While the standard version of the course is 2 days in length, the duration and content of the course can be tailored to meet your organisation's specific needs.

Course summary

  • Introduction
  • Data analysis overview
  • Descriptive statistics
  • Explanatory data analysis
  • Identifying outliers
  • Key performance indicators
  • Relationships between variables
  • Building models
  • Data inference
  • Data presentation: Building the ‘stories’
  • Pulling together the right skills (optional module)

Approach

The course is practically orientated with a mix of:

  • Key material on data analytics
  • ‘Real-world’ examples
  • Practical demonstrations
  • Individual and group exercises, with 'hands-on' experience
  • Group discussions incorporating experiences from your own organisation
 
 
 

Course content

Relationships between Variables

  • Using Excel to create pivot charts and tables for bivariate analysis
  • Generating pivot tables and charts
  • Bivariate methods: cross-tabulations, scatterplots, pivot charts and tables
  • Correlation types and examples
  • Causality vs correlation
  • Examples of using and interpreting pivot charts
  • Measuring correlation
  • Creating a correlation matrix and scatter plots (using Microsoft Excel)

Building models

  • Example of scenario modelling
  • Regression modelling: an introduction
  • Example: building a regression model for rent arrears
  • Building a model – initial thinking

Data inference

  • Confidence intervals (including sample sizes and significance levels)
  • Generating a confidence interval for a sample mean
  • Introduction to statistical significance tests

Statistical significance testing (optional module)

Testing for statistical significance, including:

  • t-tests (comparing the means of different samples, significance of correlation measures)
  • chi-squared tests (significance of differences within cross-tabulations)

Data presentation: Building the ‘stories’

  • The challenges of quantitative data presentation revisited
  •  Selecting the stories
  • Identifying audience characteristics
  • Making sure that the insight is used
  • Monitoring performance and changes
  • Reviewing examples of reports, scorecards and dashboards to draw out best practice for different audiences

Pulling together the right skills (optional module)

  • Identifying the right skills sets to deliver effective analytics
  • Individual and team skills assessment, with:
    • an assessment of analytics skills at the start of the course, and
    • a review at the end of the course

Introduction

  • Key questions
  • The Challenges of quantitative data presentation

Data Analysis Overview

  • Systematic and intuitive approaches
  • Data issues – limitations and overheads

Descriptive Statistics

  • Univariate statistics: mean, median and mode; quartiles; dispersion and standard deviation; normal distribution; skewness and modality
  • Generating descriptive statistics (using Microsoft Excel)

Exploratory Data Analysis

  • Using exploratory data analysis, focusing on graphical tools such as box and whisker, histogram, bar chart, line chart
  • Comparing the advantages and disadvantages of different graphical tools
  • Interpreting charts, e.g. box and whisker
  • Creating some useful charts, including histograms and box and whisker charts (using Microsoft Excel)
  • Further examples of displaying variability

Identifying Outliers

  • Processes to identify outlier performance
  • Run charts
  • Introduction to statistical process control: control charts and funnel plots
  • Building rules to identify the most important issues (outliers and changes)
  • Discussing useful business rules for alerts

Key performance indicators (KPIs)

  • Overview of relevant KPIs
  • Discussion of usefulness and usability

Relationships between Variables

  • Using Excel to create pivot charts and tables for bivariate analysis
  • Generating pivot tables and charts
  • Bivariate methods: cross-tabulations, scatterplots, pivot charts and tables
  • Correlation types and examples
  • Causality vs correlation
  • Examples of using and interpreting pivot charts
  • Measuring correlation
  • Creating a correlation matrix and scatter plots (using Microsoft Excel)