All the theory you need for ANOVA is contained in these three videos on Khan Academy totaling about 30 minutes of your time. Once you’ve watched and thought about these three videos, you’ll be ready to learn how easy it is to calculate complete ANOVAs using Excel with the basic, free Data Analysis Add-in. (I’ve listed those videos later in this document.) Khan Academy’ series on ANOVA:
- https://www.khanacademy.org/math/probability/statistics-inferential/anova/v/anova-1—calculating-sst–total-sum-of-squares
- https://www.khanacademy.org/math/probability/statistics-inferential/anova/v/anova-2—calculating-ssw-and-ssb–total-sum-of-squares-within-and-between–avi
- https://www.khanacademy.org/math/probability/statistics-inferential/anova/v/anova-3–hypothesis-test-with-f-statistic
Performing a t-test in Excel on experimental data (6 min) Dory Video: http://www.youtube.com/watch?v=X14z9r8FUKY This is a useful video because it does show how to install the Data Analysis add-in (Tool pack) to Excel and then use it to run a t-test on data. As you may know, we usually have to run post-hoc tests (t-tests) after a basic ANOVA, if it is significant, because the ANOVA just tells us if at least one of the means compared is different from one of the other means. So we’ll see this t-test again in the next video.
Simple one-way ANOVA using Excel by Dory Video in which he first gives an explanation of what the output means. This is an example of comparing three independent variables (with unequal number of data points) to determine if there is a difference in at least one of the means. He shows a quick post hoc using a modified Boniferoni. Good to watch. Dr James E Clark: http://www.youtube.com/watch?v=tPGPV_XPw-o