Of the ten statements on statistical tests below, four are true. Which are true?

- The largest Cohen's d value possible is 1.96

- The independent sample t test usually ends up with a larger effect size than a repeated measures t

- As t increases, Cohen's d necessarily increases

- An obtained z value of 2.50 is always more statistically powerful than an obained z value of 2.25

- An obtained t value of 2.50 is always more statistically powerful than an obtained t value of 2.25

- t tests are used when populations are no longer expected to be normally distributed

- You can have very high power with a very small effect size

- When controlling for sample size, a z test always has more statistical power than a t test

- Outlier are important to remove because they can increase the risk of a Type I or Type II error

- Homogeneity of variance is important because you can only choose one variance in the denominator for a t test. So both variances should be roughly equal so that whichever one you choose doesn't change the results that much