PSYCH 2220H Chapter Notes - Chapter 10: Normal Distribution, Confidence Interval, Null Hypothesis
Document Summary
Goal is to establish a distribution that specifies the null hypothesis for a within-groups design. Randomly chose three pairs of cards, replacing each pair of cards before randomly selecting the next. For each pair, calculate a difference score by subtracting the first weight from the second weight. Calculate the mean of the difference in weights for these three people. Repeat steps: the six steps of the paired-samples t test. Comparison distribution based on the null hypothesis that posits no mean difference, so mean of comparison distribution = Determine appropriate mean and standard error of the comparison distribution. Standard error is calculated exactly same as single-sample t test, except use the difference scores rather than scores of each condition. Degrees of freedom is the number of participants minus 1. Use means of difference scores instead of means of individual scores. Beyond hypothesis testing: calculating a confidence interval for a paired-samples t test.