You don’t always get a nice, neat, Normal Distribution to do analysis with. In those cases you must use non-parametric tests.

- http://www.micquality.com/6sigma101/glossary/nonparametric_tests.htm (List of non-parametric tests)

Mann-Whitney

- http://www.isixsigma.com/tools-templates/hypothesis-testing/making-sense-mann-whitney-test-median-comparison/ (Similar to 2 sample T test)

Kruskal-Wallis

- http://udel.edu/~mcdonald/statkruskalwallis.html (Similar to Anova)

Mood’s Median

Friedman

- http://www.statisticslectures.com/topics/friedman/ (Uses Chi squared table for critical value)

1 Sample Sign

1 Sample Wilcoxon

One and Two Sample Proportion

- http://www.cliffsnotes.com/math/statistics/univariate-inferential-tests/test-for-a-single-population-proportion (Z test for a single population proportion)
- http://www.cliffsnotes.com/math/statistics/univariate-inferential-tests/test-for-comparing-two-proportions (Z test for a comparing two proportions)

Chi-Squared (Contingency Tables)

http://math.hws.edu/javamath/ryan/ChiSquare.html

a. Including Tests of Equal Variance, Normality Testing and Sample Size calculation,performing tests and interpreting results.

http://en.wikipedia.org/wiki/Levene’s_test (Levene’s test of equal variances)