UM1081 Lecture 17

Statistics is not intuitive

If data are normally distributed, then parametric tests should be used

Non-parametric tests are considered more powerful than parametric tests

Woohoo! My results are statistically significant! Now I've finally found something important!

What would the Bonferroni-adjusted p-value threshold be when there are four comparisons?

The need to correct for multiple comparisons is standard practice, but there are others who contend it

Specificity is defined as the probability that the test result will be negative when the disease is not present.

A Type I statistical error is failing to detect a statistically significant relationship when in fact one does exist

A bigger sample leads to a narrower confidence interval

How is standard error of the mean calculated?

By convention, a p-value above 0.05 is considered significant

Standard Error of the Mean (SEM) is a descriptive statistic

Which of the below is NOT a function of descriptive statistics?

My p-value is 0.04. What can you conclude?

The conventional p-value theshold of 0.05 is chosen due to mathematical rigour and a clear basis