One of the concepts of research we're investigating this week is the idea of a type I (type one) and type II (type two) error. A type I error is when we reject a true null hypothesis. A type II error is when we fail to reject a null hypothesis. If researchers are trying to see if a new medicine helps to treat a disease, they have two hypotheses; the null hypothesis is that the medicine has an equal or less effect on the patient as the standard medication. The alternative hypothesis is that the medicine helps more than the standard medicine. A type I error in this situation would be if the researchers concluded that the new medicine is more effective when, in fact, it is not. A type II error in this situation would be if the researchers decide that the new medicine isn't better then the standard medicine when, in fact, it's actually better. There's different reasons why researchers might make this mistake. They might have a biased sample, their medical testing instruments might be incorrect, etc. In general, a researcher must balance the chances between a type I and a type II error. If you lower the chances of a type I error, you increase the chances of a type II error.

The following article is a relatively brief investigation into the relationship between sunlight and prostate cancer:

https://drive.google.com/file/d/1NN99EGn_LUDgZvTf169N2d84qRyBAkHu/view

The null hypothesis is that increased sunlight/solar radiation does not impact prostate cancer mortality. The alternative hypothesis is that increased sunlight/solar radiation reduces prostate cancer mortality.

Which is more serious in this study - a type I or a type II error? Why? Which is more likely for these researchers - a type I or a type II error? Why?