Biostats

Front 1

______ studies provide the most convincing evidence for any hypothesis as it is generally possible to control for factors that may affect the outcome.

Back 1

experimental

Front 2

the clinical trial is an example of what type of study?

Back 2

experimental

Front 3

cohort and case-control studies are examples of what type of study?

Back 3

observational

Front 4

_____ studies are those in which the investigator does nothing to affect the outcome, but simply observes what happens.

Back 4

observational

Front 5

epidemiological studies are examples of what type of study?

Back 5

observational

Front 6

what study type is typically used for studying the etiology of a rare disease?

Back 6

retrospective case-control

Front 7

______ studies are carried out at a single point in time

Back 7

cross-sectional

Front 8

identify the type of bias: "where a spurious association arises due to a failure to adjust fully for factors related to both the risk factor and outcome."

Back 8

confounding bias

Front 9

the ________ is the smallest group of 'individuals' which can be regarded as independent for the purposes of analysis, for example, an individual patient.

Back 9

experimental units

Front 10

replication and sample size are two factors that can be manipulated to decrease the impact of ______ on a study.

Back 10

variation

Front 11

most clinical trials are ______ trials, in which each patient receives one of the two or more treatments that are being compared.

Back 11

parallel

Front 12

in a clinical trial setting, the __________ design is an example of a within-individual comparison.

Back 12

cross-over

Front 13

cross-over designs can only be used when studying what kinds of treatments?

Back 13

treatments that temporarily alleviate symptoms rather than provide a cure. as well as the response time of treatment is not prolonged.

Front 14

in what phase of a clinical trial must you report all main aspects of the trial in any publication? (i.e. phase I, II or III?)

Back 14

phase III

Front 15

what is the difference between primary endpoints and secondary endpoints?

Back 15

primary - usually relates to treatment efficacy
secondary - usually relates to toxicity

Front 16

what biases do we avoid by randomizing patients between treatment groups in a clinical trial?

Back 16

allocation bias and confounding

Front 17

trials in which patients are randomized to receive either the new treatment or a control treatment are known as ___________ and are regarded as optimal.

Back 17

randomized controlled trials

Front 18

before any clinical trial is carried out, a written description of all aspects of the trial, known as the ________, should be prepared.

Back 18

protocol

Front 19

a _____ study takes a group of individuals and usually follows them forard in time, the aim being to study whether exposure to a particular actiological factor will affect the incidence of a disease outcome in the future.

Back 19

cohort

Front 20

if individuals leave a cohort study, and are not replaced, this is known as what type of cohort study?

on the other hand, if individuals drop out and are then replaced by new individuals, this is known as what type of cohort study?

Back 20

fixed

dynamic

Front 21

what type of study allows you to assess risk factor (i.e. relative risk) for a disease outcome?

Back 21

cohort study

Front 22

can cohort studies be prospective? retrospective? both?

Back 22

both, although the quality of retrospective/historical cohorts are often compromised by recall bias.

Front 23

what is the general formula for estimated relative risk?

Back 23

risk-exposed group divided by risk of unexposed group:

Front 24

the ______ indicates the increased (or decreased) risk of disease associated with exposure to the factor of interest.

Back 24

relative risk

Front 25

a relative risk greater than one indicates that the risk is _______ (greater/smaller) in the exposed group than in the unexposed group.

Back 25

greater

Front 26

what are some advantages of a cohort study? (total of 7 according to textbook)

Back 26

1. the time sequence of events can be assessed.
2. they can provide information on a wide range of outcomes.
3. it is possible to measure the incidence/risk of disease directly.
4. it is possible to collect very detailed information on exposure to a wide range of factors.
5. it is possible to study exposure to factors that are rare.
6. exposure can be measured at a number of time points, so that changes in exposure over time can be studied.
7. there is reduced recall and selection bias compared with case-control studies.

Front 27

the possibility of studying exposure to factors that are rare is an advantage of what type of study?

Back 27

cohort study

Front 28

what are some disadvantages of cohort studies? (total of 5 according to textbook)

Back 28

1. in general, cohort studies follow individuals for long periods of time, and are therefore costly to perform.
2. where the outcome of interest is rare, a very large sample size is needed.
3. as follow-up increases, there is often increased loss of patients as they migrate or leave the study, leading to biased results.
4. as a consequence of the long time-scale, it is often difficult to maintain consistency of measurements and outcomes over time. furthermore, individuals may modify their behavior after an initial interview.
5. it is possible that disease outcomes and their probabilities, or the etiology of disease itself, may change over time.

Front 29

in general, _______ studies follow individuals for long periods of time, and are therefore costly to perform.

Back 29

cohort

Front 30

in contrast to randomized controlled trials, which often include a highly selective sample of individuals who are willing to participate in the trial, ___________ often include all patients with the condition at the hospitals in the study.

Back 30

clinical cohorts

Front 31

a ______ study compares the characteristics of a group of patients with a particular disease outcome to a group of individuals without a disease outcome, to see whether any factors occurred more or less frequently in the group with the disease outcome than the group without the disease outcome.

Back 31

case-control

Front 32

do case-control studies provide information on the prevalence or incidence of disease?

Back 32

no. but they may give clues as to which factors elevate or reduce the risk of disease.

Front 33

what is the difference between incident cases and prevalent cases in a case-control study?

Back 33

incident cases - patients who are recruited at the time of diagnosis

prevalent cases - patients who were already diagnosed before entering the study.

Front 34

in what type of study is an odds-ratio calculated?

Back 34

case-control study

Front 35

when a disease is rare, the _________ is an estimate of the relative risk.

Back 35

odds ratio

Front 36

what are advantages of case-control studies? (total of 4 in textbook)

Back 36

1. quick, cheap, easy to perform
2. suitable for rare diseases
3. wide range of risk factors can be investigated.
4. there is no loss to follow-up

Front 37

what are disadvantages of case-control studies? (total of 3 in textbook).

Back 37

1. recall bias
2. if onset of disease preceeded exposure to the risk factor, causation cannot be inferred.
3. case-control studies are not suitable when exposures to the risk factor are rare.

Front 38

an odds ratio of .39 means that the odds of disease is lesser or greater in the exposed group than in the unexposed group?

Back 38

odds of disease is lesser in the exposed group than in the unexposed group.

Front 39

what are two types of categorical/qualitative data?

Back 39

nominal and ordinal

Front 40

what are two types of numerical (quantitative) data

Back 40

discrete and continuous

Front 41

percentages, ratios, rates and scores are all examples of what type of data?

Back 41

derived data

Front 42

social security numbers are an example of what type of measurement?

a. nominal
b. ordinal
c. interval
d. ratio

Back 42

a. nominal

Front 43

consumer product rankings are an example of what type of measurement?

a. nominal
b. ordinal
c. interval
d. ratio

Back 43

b. ordinal

Front 44

temperature using the fahrenheit or celsius measurement systems is a classic example of what type of measurement?

a. nominal
b. ordinal
c. interval
d. ratio

Back 44

c. interval

Front 45

salaries measured in dollars is an example of what type of measurement?

a. nominal
b. ordinal
c. interval
d. ratio

Back 45

d. ratio

Front 46

_________ is defined as the similarity of results provided by independent but comparable measures of the same object.

a. validity
b. deviation
c. error
d. reliability

Back 46

d. reliability

Front 47

generally speaking, _____ addresses the question: "Are we measuring what we think we are measuring?"

Back 47

validity

Front 48

_______ validity refers to the degree to which a variable accurately reflects the phenomenon it purports to measure.

a. statistical conclusion
b. construct
c. internal
d. external

Back 48

b. construct

Front 49

selection bias can pose a threat to what type of validity?

a. statistical conclusion validity
b. construct validity
c. internal validity
d. external validity

Back 49

c. internal validity

Front 50

generally speaking, a lack of ______ validity represents an interaction between study variables and/or subjects and the environment.

a. statistical conclusion
b. construct
c. internal
d. external

Back 50

d. external

Front 51

what is one key way to increase external validity?

Back 51

make cooperation in a study as convenient as possible

Front 52

randomized controlled trials usually lack what type of validity?

Back 52

external validity

Front 53

bar/column chart and pie charts are often used to display what type of data?

Back 53

categorical or some discrete numerical data

Front 54

frequency distributions are used to represent how many different variables?

Back 54

just one variable

Front 55

if you want to display data from a study that has two variables which are both either numerical or ordinal, how would you graphically illustrated the data?

Back 55

using a scatter diagram

Front 56

the median is similar to the mean if the data are symmetrical. is the median less than or greater than the mean if the data are skewed to the right?

Back 56

median is less than the mean whan data are skewed to the right.

Front 57

if n = 30 in an ordered set, which value will represent the median?

a. 14
b. 15
c. 16
d. 15.5

Back 57

c. 16

(n/2+1) = 15 + 1 = 16

Front 58

what is one main disadvantage of the mean?

Back 58

distorted by outliers

Front 59

a geometric mean is only appropriate if the log transformation produces a _________ distribution

Back 59

symmetrical

Front 60

the 50th percentile is also known as what?

Back 60

the median

Front 61

the interquartile range contains the central __% of the observations in an ordered set.

the interdecile range contains the central __%

the reference interval/reference range/normal range contains the central ___%

Back 61

50%

80%

95%

Front 62

what are disadvantages of using the range as a measure of spread? (total of 3 in the textbook)

Back 62

1) uses only two observations
2) distorted by outliers
3) tends to increase with increasing sample size

Front 63

what type of measure of spread is appropriate for skewed data?

a. range
b. ranges based on percentiles
c. variance
d. standard deviation

Back 63

b. ranges based on percentiles

Front 64

the ______ distribution is particularly useful for analyzing categorical data.

a. normal
b. t
c. chi-squared
d. f
e. lognormal

Back 64

c. chi-squared

Front 65

the ______ distribution is particularly useful for comparing two variances, and more than two means using the analysis of variance (ANOVA).

a. normal
b. t
c. chi-squared
d. f
e. lognormal

Back 65

d. f

Front 66

the _____ distribution is particularly useful for calculating confidence intervals for and testing hypotheses about one or two means.

a. normal
b. t
c. chi-squared
d. f
e. lognormal

Back 66

b. t

Front 67

the _____ distribution is used when our data is highly skewed to the right. this produces an empirical distribution that is nearly normal.

Back 67

lognormal

Front 68

many variables in medicine follow what type of distribution?

Back 68

a lognormal distribution (a.k.a a distribution that is highly skewed to the right)

Front 69

we can use the properties of the binomial distribution when making inferences about _______.

Back 69

proportions

Front 70

the mean in a binomial distribution is n (sample size) multiplied by pi (the true probability of success for each individual included in the sample).

what is the equation for variance in the binominal distribution?

Back 70

n*pi(1-pi)

Front 71

the poisson distribution becomes more symmetrical as the _____ increases.

Back 71

mean (which in this case refers to the average rate, mu)

Front 72

we often apply the square root transformation if y is the count of a rare event occurring in time or space, i.e. it is a ______ variable.

Back 72

Poisson (the poisson random variable is the count of the number of events that occur independently and randomly in time or space at some average rate, mu).

Front 73

the ______ transformation is more effective at stabilizing variance than the log transformation if the variance increases very markedly with increasing values of y.

Back 73

reciprocal (z = 1/y)

Front 74

what kind of transformation would we use if our observations are skewed to the left?

Back 74

the square transformation (z = y^2). it achieves the reverse of the log transformation, so if y is skewed to the left, the distribution of z=y^2 is often approximately normal.

Front 75

the ________ transformation linearizes a sigmoid curve.

a. logarithmic
b. square root
c. reciprocal
d. square
e. logit (logistic)

Back 75

e. logit (logistic).

(this is the transformation we apply most often to each proprotion, p, in a set of proportions.