Old Timer Says, \"Why, in My Day,

¶ … old timer says, "Why, in my day, kids were much more respectful and didn't cause as much trouble as they do nowadays!" It may seem like a statement that is impossible to test. In fact, one of the reasons that "in my day" type statements may be so popular is because they are difficult to test, and, therefore, difficult to disprove. However, this statement is actually relatively easy to test. While one cannot retroactively test to see if kids were really more respectful, it is fairly easy to test whether kids got in as much trouble in the past as they do at the present time. First one needs to pick a variable that stands in for a measurement of how much trouble kids actually cause. It is important to pick this variable carefully, so that the test is valid. Test validity refers to "the degree in which our test or other measuring device is truly measuring what we intended it to measure" (AllPsych, 2003). This can be done by using variables that are known to correlate with the item being tested (Shuttleworth, 2008). One variable that is known to measure how frequently a kid gets in trouble, at least in the school setting, is detention. Therefore, to test the old timer's statement, one could come up with the following hypothesis: Kids going to high school in the 1958-1959 school year were given detention less frequently than kids attending high school in the 2011-2012 school year. The number of detentions would be related to the number of times students got into trouble at the school.

The hypothesis could be tested by selecting a high school and comparing the number of detentions it gave out in the 1958-1959 school year with the number of detentions in the 2011-2012 school year. However, one would need to carefully select the high school to ensure that the same things were being measured. The high school would have to give detentions for the same things now as it did in the past, have the same socio-economic composition, and have the same ethnic and cultural composition to ensure that it was a change in times, not a change in other demographic factors, which led to a change in number of detentions.

Part B

Generally, "a p-value of .05 or less rejects the null hypothesis "at the 5% level" that is, the statistical assumptions used imply that only 5% of the time would the supposed statistical process produce a finding this extreme if the null hypothesis were true" (Beggs, 2013). Therefore, there is 95% certainty that the results are the due to the variables being tested and not to some external influence. For most cases, particularly for social science research, this confidence level is adequate. However, it may not be acceptable in all cases.

For example, you would want a lower p-value in cases where the results need to be certain. "If you were testing a new medical product or a new drug, you would choose a much smaller P. value (perhaps as small as .0001). That's because you would want to be as sure as possible that any difference you see between groups is attributed to the new product or drug and not to chance" (Rempher & Urquico, 2007). This is especially true if the tested drug, device, or procedure has negative side-effects or consequences. For example, migraine sufferers experience tremendous pain. A drug that is known to cause liver damage might be approved to alleviate migraines, but only with a low p-value.