What does Statistics for the Terrified cover?

Statistics for the Terrified covers all the techniques required by undergraduate students and many researchers in a user-friendly, commonsense, non-mathematical and highly interactive way.

Each chapter of the tutorial begins with an outline of its aims and objectives, and finishes with a summary of the key points covered. Click on the links below for screenshots.

Before you begin

• The trouble with Statistics
• How this tutorial will help you
• What is Statistics?
• The art of detective work

Probability

• Aims and objectives
• Probability
• Probability notation
• Getting a feel for conditional probability – Screenshot
• Joanna Watson: a conditional probability scenario
• Conditional probability as areas
• Conditional probability: the calculations
• Conditional probability
• Bayes theorem helps untangle confused logic
• Summary

Basic numerical data description

• Aims and objectives
• Data types
• Average values – the mean, median introduced – Screenshot
• The effect of outliers on the mean and median
• The advantages and disadvantages of the mean and median
• Range and variance
• Variance and Standard deviation
• What is the coefficient of variation?
• Summary

Graphical data description

• Aims and objectives
• Frequency charts and histograms – Screenshot
• Histograms and distributions
• Introducing the normal curve
• The normal curve shows relative likelihood – Screenshot
• How sd affects normal curve shape
• Normal distribution and calculating probabilities: datagame – Screenshot
• Dealing with data that isn’t normally distributed
• Summary

Standard error and confidence intervals

• Aims and objectives
• Introduction to standard error
• Standard error measures the accuracy of estimates – Screenshot
• Standard error decreases as standard deviation increases
• Accuracy increases as standard error decreases
• How this looks with normal curves
• How to calculate standard error in theory
• How to calculate standard error in practice
• Isn’t it cheating to use estimates in the calculation?
• Standard error and standard deviation are not the same! Recap
• Confidence intervals are based on standard error
• A 95% CI contains the population mean 95% of the time – Screenshot
• Summary

What does p<0.05 really mean?

• Aims and objectives – Screenshot
• What is hypothesis testing?
• Posing the hypothesis
• Introducing the null hypothesis
• Random sampling
• What do you take into account? – Screenshot
• The steps involved in hypothesis testing
• The relationship between the test statistic and p values
• The story so far…
• How difficult is it to reject the null hypothesis?
• The relationship between power and type II errors
• Power worsens as the alternative gets closer
• Making significance tests more powerful
• Summary

How to choose a test

• Aims and objectives
• The essentials
• For simple but essential concepts
• For simple but essential concepts
• Data patterns – Screenshot
• Appropriate tests
• Questions to ask – Screenshot
• The test quiz
• Summary

Testing for differences between groups

• Aims and objectives
• Overview – tests for differences between group means – Screenshot
• Two-sample t test overview
• Two-sample t test exploration
• Two-sample t test datagame
• Analysis of variance (ANOVA) overview
• Oneway ANOVA: exploration and datagame – Screenshot
• What is twoway analysis of variance?
• Twoway ANOVA: interpretation and datagame
• Non-parametric methods: ranking
• Mann-Whitney test – datagame and explore
• Kruskal-Wallis test – datagame and explore
• Summary

Analysing repeated measures

• Aims and objectives
• What are repeated measures?
• Collapse the data
• Before/after tests – Screenshot
• The paired t test
• The paired t test datagame – Screenshot
• Wilcoxon signed rank test overview
• Wilcoxon signed rank test datagame
• Why area under a curve?
• Datagame the areas
• Dealing with repeated measures: Recap
• Data patterns
• Tripping over the truth
• Time series: smoothing – moving averages
• Time series: exponential smoothing
• Summary

Analysing 2×2 classification tables

• Aims and objectives
• What are classification tables?
• Overview of the use and meaning of classification tables
• Calculating risk is straightforward
• Absolute risk and relative risk
• Testing: introducing the chi-square statistic
• Interpretation of discrepancies and relative risk – Screenshot
• The chi-square test, sample size and Fisher’s exact test
• The chi-square test datagame
• Summary – Screenshot

Fitting lines to data

• Aims and objectives
• The basics of regression: correlation
• The basics of regression: what is it good for?
• The basics of regression: describing the line
• Exploring linear regression
• Regression: datagame – Screenshot
• The pulling power of outliers
• Regression parameters and their standard errors
• Hypothesis testing a linefit
• Hypothesis testing challenges
• Summary

Uncovering hidden influences

• Aims and objectives
• A little knowledge is a dangerous thing 1 – Screenshot
• A little knowledge is a dangerous thing 2
• Analysis of covariance: uncovering influence by linefitting 1
• Analysis of covariance: uncovering influence by linefitting 2
• Twoway analysis of variance: reducing bias and variance 1
• Twoway analysis of variance: reducing bias and variance 2
• Twoway analysis of variance: reducing bias and variance 3
• Matching and the removal of bias
• Summary