Ch. 2 - Study Designs

Question 1

Types of Study Designs

Answer 1

Observational and randomized studies

Question 2

Observational Study

Answer 2

observe a phenomenon

also called descriptive or associational studies, nonrandomized, historical studies

used to alert the medical community to a specific issue

Question 3

Randomized Study

Answer 3

intervene and measure a response, test specific hypotheses or evaluate the effect of an intervention

also called analytic or experimental studies

Question 4

Bias

Answer 4

systematic error that introduces uncertainty in estimates of effect or association

Question 5

Blinding/Double Blinding - also masking

Answer 5

Participant is unaware of their treatment status; double = both participant and researcher are unaware

Question 6

Clinical Trial

Answer 6

randomized trial involving humans

Question 7

cohort

Answer 7

group of participants that usually share some common characteristics and who are monitored or followed over time

Question 8

Concurrent

Answer 8

at the same time, i.e. optimally comparison treatments are evaluated in parallel

Question 9

Confounding

Answer 9

complex relationships among that can distort relationships between risk factors and outcomes

Question 10

Cross-sectional

Answer 10

at a specific, single point in time

Question 11

Incidence

Answer 11

the rate of development of new cases of a disease over a period of time

Question 12

Intention-to-treat

Answer 12

analytic strategy whereby participants are analyzed in the treatment group they were assigned regardless of whether they followed the study procedures completely

Question 13

Matching

Answer 13

process of organizing comparison groups by similar characteristics

Question 14

Per protocol

Answer 14

analytic strategy whereby only participants who adhered to the study protocol are analyzed

Question 15

Placebo

Answer 15

inert substance desgiend to look, feel, and taste like the active or experimental treatment

Question 16

Prevelance

Answer 16

proportion of individuals with the condition at a single point in time

Question 17

Prognostic factor

Answer 17

characteristic that is strongly associated with an outcome such that it could be used to reasonably predict whether a person is likely to develop a disease or not

Question 18

Prospective

Answer 18

study in which information is collected looking forward in time

Question 19

Protocol

Answer 19

step-by-step plan for a study that details every aspect of the study design and data collection plan

Question 20

Quasi-experimental design

Answer 20

study in which subjects are not randomly assigned to treatments

Question 21

Randomization

Answer 21

process by which participants are assigned to receive different treatments (usually based on a probability scheme)

Question 22

Retrospective

Answer 22

study in which information is collected looking backward in time

Question 23

Stratification

Answer 23

process whereby participants are partitioned or separated into mutually exclusive or non-overlapping groups

Question 24

Case Report

Answer 24

very detailed report of the specific features of a particular participant or case

Question 25

Case Series

Answer 25

systematic review of the interesting and common features of a small collection or series of cases

important - historically are used to identify new diseases

has no control or comparison group

easy to conduct but can be criticized because of their unplanned, uncontrolled nature and the fact that they are not designed to answer a specific research question

often used to generate hypotheses to be answered later

Question 26

Cross-Sectional Survey

Answer 26

study conducted at a single point in time - used to study prevalence of a disease or risk factors, a present practice, or an opinion

study is non-randomized and has a group of participants that are identified at a particular point in time and information is collected at that point in time

inferences are limited to the time and population from which the sample is drawn

also unable to assess temporal relationships

non-response also an issue

Question 27

Prospective Cohort Study

Answer 27

group of individuals who meet inclusion/exclusion criteria at the beginning of the study

cohort followed and associations are made between risk-factors and disease

cohort could be from general population or a special exposure cohort

allows researchers to assess temporal relationships - possible to estimate the incidence of disease

difficulties arise if the outcome of interest is rare or has a long latency period (could mean loss of patient follow-up)

confounding can be an issue - complex relationships between variables must be reconciled via statistical analyses

Question 28

Retrospective cohort study

Answer 28

exposure or risk factor ascertained retrospectively

often mounted on data gathered from medical records where risk factors and outcomes have already happened and have been documented

Question 29

Case-Control Study

Answer 29

used in epidemiological research - research question is whether there is an association between a particular risk factor/exposure and an outcome

useful when outcome of interest is rare or has a long latency period - outcome has already happened AND participants are identified on the basis of their outcome status

select a set of cases (those with outcome) and controls (those without outcome - similar in every way except the outcome)

explicit definition must be established before any participants are selected or data collected

RETROSPECTIVE study

researcher collecting exposure data should be blind as to whether each participant is a control or a case

challenges rest in bias
Misclassification bias, selection bias, recall bias

can’t establish temporal relationship and can’t estimate incidence

Question 30

Nested Case-Control Study

Answer 30

usually designed from a cohort study

used to assess new biomarkers or to evaluate expensive tests or technologies

Question 31

Randomized Controlled Trial

Answer 31

key feature is the randomization of test subjects into one of several comparison or treatment groups

randomization allows each group to differ only in the treatment given - reduces confounding and bias

each group gets a different treatment - one drug vs another, and if ethically feasible, one might be a placebo

active controlled trial - standard of care given against new drug

data collected prospectively and treatments should be evaluated concurrently

Trials should include multiple testing sites - multi-center trial - promotes generalizability

should be double blind

inferences from study are limited to the population from which the sample was drawn

Question 32

Crossover Trial

Answer 32

clinical trial where each participant gets two or more treatments sequentially

wash out period - time during which the effect of lack of effect of each treatment or lack of treatment is allowed to wash out before the application of the next treatment

Random or fixed assignment scheme
- random - randomly assigned to treatment or control
- fixed - all participants are assigned the same treatment sequence
must assume that order doesn’t affect outcome

each subject acts as their own control

wash out period must be long enough to nullify effects of first treatment but short enough to allow subjects to stay engaged

Question 33

Study Design

Answer 33

methodology used to collect the information to address the research question