a. can only be used in parametric data
b. it is a test of the null hypothesis

c. it is calculated at ± 1.96 times the standard
error of the mean

d. is useful when comparing data with another population

e. if zero difference lies within the 95% when comparing
two groups to a

treatment, it indicates the treatment
has no effect

2. Meta-analysis of randomized controlled trials:

a. should only include peer-reviewed studies
b. is usually performed if individual trials are too small
to give a reliable answers

c. should include trials in which patient selection is
not randomized

d. provides a more stable estimate of the effect of treatment
than individual trials

e. gives conclusion making further controlled trials unnecessary

3. The following are true about evidence-based medicine:

a. does not involve health economic assessment
b. is restricted to randomized placebo-controlled trials

c. is used to cut down waiting list

d. relies only on objective measurements of disease outcomes

e. combines clinical expertise and external evidence

4. The following are true about errors in clinical
trials:

a. type I error is wrongly rejecting the null
hypothesis
b. type II error is accepting the null hypothesis when
it is invalid

c. errors are more common when big samples are used

d. type I error is more likely to occur when multiple
t-test are used

e. type II error is reduced by the use of confidence interval.

5. The following are true about a normal (Gaussian
distribution):

a. the mean, median and mode coincide
b. 95% of observation lie between the mean 2 standard
deviation

c. 68% of observations lie between the mean 1 standard
deviation

d. the 95% confidence interval may be calculated as the
mean ±1.96 times

the standard error of the mean for
population >30

e. data from a normal distribution is suitable for parametric
tests without

prior transformation.