In a weight loss study, it's important to ensure that the weight of participants is balanced across conditions; if it's not, it will be impossible to tell whether the IV caused whatever difference between the groups might be found or whether it was caused by the groups having different average weights at the start. In other words, initial weight is a likely confound in an experiment designed to study weight loss. To ensure the groups are balanced in terms of participants' initial weight, researchers are likely to find two participants who weigh about the same amount and assign one to each group. They do the same thing with all participants, finding pairs of participants who are close in weight and then randomly putting one member of each pair in each group. What would be the appropriate statistical test to conduct to compare the amount of weight loss in these two groups 1. dependent/related/paired-samples t test 2. single-sample t test 3. independent-samples t test 4. z test