EBM

Question 1

Systematic revue

Answer 1

overview of particular clinical research question

Question 2

Meta-analysis (3 points)

Answer 2

Uses statistical method to summarise studies, often included in a systematic review, produces single quantitative result

Question 3

Single quantitative result

Answer 3

pooled treatment result / overall effect estimate

Question 4

Forest plot

Answer 4

graphical result of meta-analysis

Question 5

Point effect estimate (forest plot)

Answer 5

vertical midpoint of each square, mean treatment effect for that study

Question 6

forest plot vertical line

Answer 6

line of no effect

Question 7

horizontal line (each) on forest plot

Answer 7

confidence interval

Question 8

if horizontal line (confidence interval) crosses vertical line (line of no effect) then..

Answer 8

No significant difference between two treatments

Question 9

width of diamond at bottom of forest plot

Answer 9

certainty of overall affect estimate - 95% confidence interval

Question 10

confidence interval

Answer 10

range of values within which the true mean of whole population is expected to lie

Question 11

95% confidence interval

Answer 11

95% confident that true mean lies somewhere between two limits of interval

Question 12

larger sample sizes lead to CIs which are

Answer 12

narrower

Question 13

less variability leads to CIs which are

Answer 13

narrower

Question 14

a larger confidence level results in CIs which are

Answer 14

broader

Question 15

outcome variable

Answer 15

dependent variable

Question 16

outcome variable of meta analysis

Answer 16

often odds ratio (NOT ALWAYS)

Question 17

in a meta analysis where the mean difference is zero

Answer 17

no difference between groups

Question 18

negative mean difference in meta analysis

Answer 18

favours treatment

Question 19

positive mean difference in meta analysis

Answer 19

favours control (treatment harmful compared to no treatment)

Question 20

relative frequency

Answer 20

percentage of total number in sample

Question 21

categorical variable

Answer 21

non-numerical

Question 22

numerical variable

Answer 22

numerical value, measurable quantity. Continuous or discrete

Question 23

continuous numerical variable

Answer 23

measurement on continuous scale e.g. height

Question 24

discrete numerical variable

Answer 24

numbers of events, limited number of possible values e.g. pregnancies, heart attacks

Question 25

3 graphical representations of categorical variables

Answer 25

frequency distributions, pie charts, bar charts

Question 26

4 graphical representations of numerical variables

Answer 26

frequency distributions, histograms, frequency polygons, quantiles

Question 27

measures of central tendency (3)

Answer 27

mean, median, mode

Question 28

measures of spread of data (3)

Answer 28

range, interquartile range, standard deviation

Question 29

purpose of shapiro-wilk test

Answer 29

determining normality (or otherwise) of distribution

Question 30

purpose of t-test

Answer 30

determine whether 2 means differ reliably

Question 31

correlation and linear regression purpose

Answer 31

testing for relationship between 2 variables

Question 32

null hypothesis of hypothesis testing

Answer 32

no effect

Question 33

p < 0.05 hypothesis testing

Answer 33

reject null hypothesis - statistically significant result

Question 34

shapiro wilk null hypothesis

Answer 34

sample from normally distributed population

Question 35

shapiro wilk p <0.05

Answer 35

reject null hypothesis - statistically significant result, sample unlikely to be from normal distribution

Question 36

3 types of t test

Answer 36

one sample t test, unpaired t test, paired t test

Question 37

t test null hypothesis

Answer 37

no difference between 2 means

Question 38

t test p <0.05

Answer 38

reject null hypothesis- statistically significant result, reliable difference between 2 means

Question 39

pearson's r between which two values

Answer 39

-1 and +1

Question 40

r = 0 (approx)

Answer 40

no relationship between variables

Question 41

pearson's r p < 0.05

Answer 41

reject null hypothesis - statistically significant result, reliable relationship between two variables

Question 42

pearson's r null hypothesis

Answer 42

no relationship between two variables

Question 43

what is p value

Answer 43

probability of observing the results of a trial if the null hypothesis is true

Question 44

shapiro wilk test statistic

Answer 44

W

Question 45

one sample t test used to

Answer 45

compare sample mean with population mean

Question 46

unpaired t test used to

Answer 46

test whether there is difference between 2 independent groups - comparing same measure in 2 different groups

Question 47

paired t test used to

Answer 47

compare dependent samples of groups e.g. one subject at two times

Question 48

t test test statistic

Answer 48

t

Question 49

pearson's r is a

Answer 49

correlation coefficient

Question 50

cochrane review =

Answer 50

systematic reviews of primary research in human health care and health policy. highest standard of evidence-based heath care