Two (2.5 really) ways to test the hypothesis: 1. With confidence intervals: is the hypothetical value inside the interval? 2. By computing a t value and comparing it to the critical t (or lookup t). 2.5 Finally, probably the best way is the compute the p value. In Excel, we can use the =TDIST(computed t, d.f., 2 tail) = 1.3%. This returns a significance level (alpha) for us. That means, with 98.7% confidence (1 - alpha) we can reject the null. The advantage is that we do not need to specify a confidence/significance, instead the significance is returned for us (i.e., the point at which we can reject the null) and we can decide whether it's enough
Questions about Hypothesis Testing
Want more info about Hypothesis Testing?
Get free advice from education experts and Noodle community members.