Hi, I'm deciding on which test to use to calculate the sample size in g*power. I'm confused about the cell value requirement of the chi-square test of independence. It says that each cell must be at least 5. If it has less than that Fisher's exact test must be used. My study is a 4x8 test of independence. I don't have the data yet so I don't know what the distributions will be like. Each cell might have more than 5 or may even have 0. However, Fisher's exact should only have 2 options (which mine have 4 and 8). So I'm really confused about which test to use. Thanks in advance!