Which of the following can be used to summarize the variability of a continuous outcome variable?

A. Mean

B. Median

C. Standard deviation

D. Standard error of mean

C. Standard deviation measures how widely measurements are scattered around the mean, while standard error of mean measures the accuracy of estimation of mean.

Which is true for a normal (Gaussian) distribution?

A. The graph normally has 2 peaks

B. When the data are distributed normally, the mean and median are very close and may be identical

C. It only applies to cross-sectional trials

D. The most frequently occurring value is on either end of the curve

B. A normal distribution is a bell-shaped curve (1 peak) where approximately 68% of the results fall within 1 standard deviation and about 95% within 2 standard deviations. Since the mean is the average number and the median is the value that half the population falls below, these numbers can be very close when values follow a normal distribution.

A study which is done in a very specific population that is not generalizable to the population that you treat, would be said have low:

A. Construct validity

B. Internal validity

C. External validity

D. Statistical validity

C. One major objective of trials is to have the results apply to those outside of the study population. When a trial has low external validity, the therapy is found to be best for the population studied only. Internal validity takes into account whether the trial was done properly and had valid findings.

The power of a test has the following qualities, EXCEPT:

A. It is equal to (1 − the probability of making a type II error)

B. It is the probability of correctly concluding that the treatments do in fact differ.

C. It is the probability of making a type I error.

D. It can be expressed as 1 − β.

C. The power of a study tells the investigator how good the study is at correctly identifying a difference ...

### Pop-up div Successfully Displayed

This div only appears when the trigger link is hovered over. Otherwise it is hidden from view.