Data Analysis for Experimental Design is an intuitive introduction to experimental design in the social sciences. The emphasis is on single degree of freedom tests, which simplifies the statistical treatment because fewer assumptions are required and direct tests of research hypotheses are permitted.

More information about the book is available through the Guilford Press website.

You can download my lecture notes that include ANOVA, Regression and multivariate statistics as part of a year long graduate level course at the University of Michigan (course notes).