SOC202H1 Lecture Notes - Lecture 6: Null Hypothesis, Central Limit Theorem, Sampling Distribution
Document Summary
More common than 1-sample hypothesis tests are situations where we want to compare two or more populations. Step 1: the two samples must be selected independently: independent random sampling. Step 2: null hypothesis statement will say that the two populations are not different. Step 3: sampling distribution refers to difference between the sample statistics- determine the critical value value is ux1-x2 (x= x bar) --. > represents the difference between two samples. Step 4: in computing the test statistic, z(obtained) or t(obtained), the basic form of the standard error. Step 5: same as before: if the test statistic, z(obtained) or t(obtained), falls intot he critical region, as marked by z(critical) or t(critical), reject the ho. Another application of the hypothesis test procedure is to compare two or more samples with sample data drawn randomly from those populations. Today we will focus on comparing two samples; next week we will extend the analysis to consider three or more samples.