Exam 1 - Research Designs & Methods Flashcards

1
Q

Validity

A

The accuracy of results

Extent to which an instrument measures what it is intended to measure

(If it isn’t accurate, it isn’t valid)

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
2
Q

Internal validity

A

Degree to which study outcomes can be explained by the differences in the assigned intervention

To strengthen: add a control group

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
3
Q

External validity

A

Extent to which the results of a study can be generalized to other settings

(Is it valid outside the study?)

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
4
Q

Causality

A

The outcome is the result of the treatment

(Think cause and effect)

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
5
Q

Analytical studies

A

Provide casual interpretation of an existing phenomenon

Used to test a hypothesis

(Casual anal)

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
5
Q

Descriptive studies

A

Describes a phenomenon

Describes/summarizes info about diseases/events without making any casual inferences

Casual inferences = who, what, when, where, why

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
6
Q

Prospective studies

A

Data is collected after the study as individuals are followed

Time and cost intensive

Researchers determine variables

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
7
Q

Interventional/experimental studies

A

Researcher controls the treatment

Usually involved randomization

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
7
Q

Retrospective studies

A

Researchers go backward in time to determine relationship between cause and outcome that has already occurred

Require minimal resources; researchers have NO control over variables

(Retro = past)

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
8
Q

Quasi-experimental studies

A

Experimental designs WITHOUT randomization

Kind of like observational studies

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
9
Q

What is the gold standard in evaluating the safety and efficacy of an intervention

A

Randomized controlled trials

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
10
Q

2 essential elements of RCTs

A

Randomization of participants to interventional and control groups

Prospective - patients in study group are followed after the intervention to evaluate changes in clinical outcome

(Random and prospective)

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
10
Q

Do RCTs increase or decrease internal validity

A

Increase

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
11
Q

What is the key element of observational designs

A

Non-randomization of the independent variable

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
11
Q

Observational designs

A

Researcher observes the relationship between independent (intervention/exposure) and dependent (outcome/disease) variables in a natural setting

(Observing variables)

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
12
Q

Types of observational studies

A

Case report
Cross sectional
Case control
Cohort studies

(4 Cs or Really Sad Cassie Studies)

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
13
Q

Case report

A

Study of a single case of a new disease/manifestation

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
14
Q

Cross-sectional

A

The exposure and outcome are measured at the same point in time

(The exposure and the outcome cross)

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
15
Q

Case control

A

Involve comparison of exposure status among individuals w/ disease or outcome of interest (cases) and those without (controls)

(To compare, you have to control the case)

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
16
Q

Cohort studies

A

Followed exposed and unexposed groups over a period of time until the development of the outcome of interest (RR)

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
17
Q

Research methodology

A

Focuses on data collection and measurement techniques

(Collection and techniques are methods)

18
Q

Primary methods (research methodology)

A

Collect data specifically for the research question under consideration

Ex. Surveys and observations

19
Q

Pros/cons of primary methods (research methodology)

A

PROS: researcher can collect data to fit needs of study

CONS: resource intensive (cost and time)

(Takes more time and money to have something personalized)

20
Q

Pros/cons of secondary methods (research methodology)

A

PROS: easier to conduct and less costly

CONS: may not include certain variables needed for the purposes of the study and may be difficult to interpret

(You save time and money if you don’t order something personalized, but it may not be exactly what you want)

21
Q

Secondary methods (research methodology)

A

Use of data that was collected for a different purpose

Ex. Medical charts and medical claims

22
Q

Reliability

A

Consistency and reproducibility of results

23
Q

RCTs are in which phase of the drug development process

A

Phase III

23
Q

Bias

A

Systematic errors that can occur during the implementation of a study

23
Q

What can be done to reduce selection bias

A

Randomization

24
Q

Investigator bias

A

Errors in the the:

  • study design
  • implementation
  • analysis by the investigator
24
Q

Simple randomization

A

Use of a random number generator to allocate participants to study groups

(Random number generator sounds like the easiest [simplest] option)

24
Q

Hawthorne effect

A

Subjects modify their behavior because of the fact they’re being studied or observed

(Hawthorne was a man, and men be changing their behavior like this)

24
Q

Selection bias

A

Preferential enrollment of specific patients into one treatment group over another

25
Q

Randomization

A

Assigned patients to a treatment or control group by chance

25
Q

Block randomization

A

Ensures treatment groups have an equal number of patients by dividing into “blocks”

26
Q

Stratified randomization

A

Ensures certain baseline characteristics are equal between groups of a study

27
Q

Group/cluster randomization

A

Subjects in the same cluster would be randomized and receive the same treatment

28
Q

Blinding

A

People involved in the trial are unaware of what treatment the patients are receiving

(Blind to their treatment)

29
Q

Double blind

A

Two sets of individuals are unaware of what the patients are receiving

(Double = two sets)

30
Q

Single blind

A

Only one set of individuals is unaware of what the patients are receiving

(Single = one set)

31
Q

Sample size

A

Number of participants to be enrolled in each treatment group in a study

32
Q

Effect size (sample size)

A

Statistical elimination of the magnitude of effect due to treatment or the association between 2+ variables that is likely to occur

(How big is the effect)

32
Q

Power (sample size)

A

Measures the capacity to detect a difference in the study groups if a true difference exists (a larger study group indicates greater power)

(Think power difference)

33
Q

Clinical research protocol

A

Standardized document that provides instructions to the investigators on all aspects of carrying out the study

(Think of it as the instruction manual)

34
Q

Inclusion criteria

A

The specific characteristics that the investigator is most interested in studying

(You’re only included if the researcher is interested in you)

35
Q

Exclusion criteria

A

The factors that would confound or impair the ability to interpret the study results or eliminate patients that should not be receiving the intervention

36
Q

Relative risk

A

Ratio between the rate of the outcome in the treatment and control groups

36
Q

Placebo

A

Consists of an inert substance (ex. Lactose powder) that is identical in appearance (shape, form, taste, color) to the active treatment

37
Q

Relative risk difference

A

How far away the relative risk is from the “no difference mark” of 1

38
Q

Number needed to treat

A

The number of patients that must receive the treatment in order for one patient to experience a desired outcome

(Number needed for treatment to work in one person. Like 1 in X)

39
Q

Number needed to harm

A

The number of patients that must receive the treatment in order for one patient to experience an adverse outcome (should be high to be considered a safe medication)_

(Think out of # people, only one was harmed. Ex. You have a 1 in 1 million chance)