Statistics
Statistics are essential part of sciences but in a hands of less than mathematically savvy person a lot of harm can be done by applying methods that might or might not apply to the situation. This is a well known problem. Anyone wanting to work with statistics should really read the following articles.
Scientific method: Statistical errors
How scientists fool themselves – and how they can stop
Statisticians issue warning over misuse of P values
The problem with unadjusted multiple and sequential statistical testing
This is not to say that statistics are useless but just like with any tool a person working with statistics must understand when the tools can be employed and what the results actually mean.
Introduction to t-test
Introduction to the most commonly used parametric statistic test.
Introduction to Kolmogorov-Smirnov test
Introduction to the most commonly used non-parametric statistic test.
On standard deviation and standard error of the mean
Exploring the implications of standard deviation and standard error of mean
LMU talks on statistics
Talk 1
Standard error of the mean and standard deviation. Confidence intervals.
Talk 2
Normality
Talk 3
Statistical significance
Talk 4
Multiple comparisons
Talk 5
Non-parametric models
Talk 6
ANOVA
Talk 7
Post-hoc for ANOVA
Talk 8
Non-parametric ANOVA - Kruskal-Wallis
Talk 9
Bootstrapping