Choose a link to write about. Comment what you think about the link and what you learned. For example: \"So far, from what I understand of hypothesis testing it is more or less like taking an educated guess then working backwards through process of elimination to get what is most likely the right answer. If I understand correctly, this is building onto confidence intervals. Is the goal of hypotheses testing (by way of two "guessed" means) to decrease the size of the of the confidence interval? By comparing two possible means, with the same standard deviation, and a little bit of trial and error, I can see how we can assume with confidence (more than confidence intervals anyway) that the mean we "backward calculate" is correct. Is that close to what we are going for? I found this explanation helpful http://blog.minitab.com/blog/adventures-in-statistics/understanding-hypothesis-tests%3A-whywe-need-to-use-hypothesis-tests-in-statistics\" : Animated power It might be easier to think of these errors in relation to medical tests. "A type 1 error is where the person doesn't have the disease, but the test says they do (false positive). A type 2 error is where the person has the disease but the test doesn't pick it up (false negative)." (from Khanacademy site). Here's a fictitious example a student of mine posted: Fictitious Example of Ho and Ha Keep in mind that hypothesis testing always follows the same steps: 1. Specify the null and alternative hypothesis (one tailed is more powerful if there is a reasonable justification for using it). The null always includes =. The alternative is either not equal to (for two tailed tests) or < or > (for one tailed tests). 2. Specify alpha. 3. Run the statistical test (t, chi-square, F, whatever is appropriate for your research question and your data). 4. Calculate the p-value (probability of getting that value by chance). 5. Compare the p-value to your alpha and make your decision. I like to see decisions made in statistical terms (jargon?) and also in terms my grandmother would understand. This is what I consider to be the foundation of inferential statistics. And here is an article from the NY Times (where else since I was born and raised in Brooklyn) Hypothesis Testing in real life Once again, Hypothesis testing for beginners Obviously, reliability is crucial when running any hypothesis test. Here's a starter for you, if you're interested in providing an opinion. Reliability in the news Which t-test or ANOVA Here's an example of t-test used in real life Real life t-test