Chapter 3 Flashcards

1
Q

Good data collection

A

A realistic and sound plan is needed to develop a study that is a good representation of the population

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

Three steps in designing a study

A
  1. Identify population of interest 2. Compile list of subjects 3. Decide sampling design
How well did you know this?
1
Not at all
2
3
4
5
Perfectly
3
Q

Note on identifying population of interest

A

Have to have the population match the study’s question

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

Sampling Units

A

Subjects of interest

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

Sampling Frame

A

List of subjects to sample from

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

Sample Design

A

Method of drawing samples from the sample frame

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

What makes a good Sampling Design?

A

Resulting sample is a good representative of the population and reflects characteristics of the population

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

Three types of Sample Designs

A
  1. Simple Random 2. Cluster 3. Stratified
How well did you know this?
1
Not at all
2
3
4
5
Perfectly
9
Q

Simple Random Sampling

A

Sample guided by equal chance, given a population of n subjects, each possible sample of that size (n) has the same chance of being selected

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

Fraternity example

A

Two of five officers set to go on trip, picked randomly from a hat. Possible samples of officers are C(5,2) = 10. Chance of selecting any one of samples is 1/10 and each officer appears 4/10 samples, each has a 4/10 = 2/5 chance of selection

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

Random Number Tables (Generators)

A

Number assigned to subjects in frame; random numbers of same length as above generated; subjects with numbers generated selected and process stopped when sample size is reached

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

Cluster Sampling

A

Population divided into large number of clusters and simple random sample of pre-specified number of clusters selected

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

Cluster Random Sample

A

All samples in the clusters chosen during the cluster sampling

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

Stratified Sampling

A

Population divided into separate groups (strata) and a simple random sample is selected from each

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

What you need for Stratified Sampling

A

Access to sampling frame and strata into which each subject belongs

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

Margin of Error

A

Potential error range in estimations

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

Sampling Fraction

A

Ratio of sample size n to population size N (n/N)

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
18
Q

What if n/N is less than or equal to 0.05?

A

Margin of error is given by:

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
19
Q

What if n/N is greater than or equal to 0.05?

A

We use finite population correction:

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
20
Q

True proportion

A

Between the observed proportion ± margin of error

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
21
Q

Bias

A

Responses from sample tend to favor parts of population and aren’t representative of the whole

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
22
Q

Three types of Biases

A
  1. Sampling 2. Non-response 3. Response
How well did you know this?
1
Not at all
2
3
4
5
Perfectly
23
Q

Sampling Bias

A

Results from flaw in sampling method, especially if sample is non-random

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
24
Q

Under-Coverage

A

Sampling frame that lacks representation from parts of the population

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
25
Non-Response Bias
Results when some sampled subjects cannot or refuse to participate; even those willing to may only do so since they have strong views on the subject
26
Response Bias
Results from actual responses, may be due to the way the question is asked or if people believe their responses are socially acceptable
27
Convenience Sample
Easily obtainable samples such as stopping people on the street
28
Problem with Convenience Sampling
May result in serious biases
29
Volunteer Sample
Subjects volunteer to be in survey
30
Problem with Volunteer Sampling
Inherent biases; one segment may be more likely to volunteer due to their strong opinions
31
Simple Random Sample vs. Non-Random or Convenience Sample
Former less likely to be affected by the biases
32
Statistical Association
Change in one variable is companied with the change of the other
33
Response Variable
Dependent variable, outcome that depends on the independent variable
34
Explanatory Variable
Independent variable or covariate, which may explain or be related to the outcome
35
Statistical Association and causal relationships
Does not necessarily provide this between the response and explanatory variable
36
Lurking Variables
Also called confounders; associated with both the response and explanatory variable giving misleading impressions about their relationship
37
Lurking Variable in the cell phone use - eye cancer - computer use example
Computer use
38
Experimental Study
Researchers assign subjects to experimental conditions (treatments) based on explanatory variables and then get outcomes on response variable
39
Treatments
Experimental condition groups based on levels of one explanatory variable or a combination
40
Observational Study
Researches do NOT assign subjects but simply observe response and explanatory variables possessed by subjects
41
Advantage of Experiments w/ causal relationships
Experiments can establish causal relationships because they control over lurking variables by allocating subjects to different treatments
42
Disadvantage of Experiments
Not easy and often unrealistic to do; subjecting humans to potentially unethical treatments may cause concern
43
Advantages of Observational Studies
Preferred especially medical field where results can be gathered without treatments or when researchers aren't interested in assessing causality
44
Experimental Units
Subjects in sample
45
Factors
Categorical explanatory variables in experiment
46
Levels
Categories of factors
47
Placebo
Secondary no-go treatment against which effectiveness of primary treatment is tested
48
Placebo Effect
Better responses if people are given a placebo rather than nothing
49
Control Group
Group who receives placebo or new treatment against old
50
Randomization
Randomly assigning experimental units into treatment groups
51
Three Goals of Randomization
1. Balance treatment groups 2. Eliminate effect of lurking variables 3. Reduce bias
52
Double-Blinded
Neither subjects nor data collectors know about treatment assignment
53
Nine Components of Experiment
1. Response Variable 2. Explanatory Variable (Factor/Covariate) 3. Levels 4. Confounders (Lurking Variables) 5. Experimental Units 6. Levels 7. Treatments 8. Control Group 9. Randomization
54
Cross-Sectional Study
Sample survey takes a snapshot or cross-section of population at a given point in time
55
Retrospective Study
Observational study in which researcher looks for outcome first and then looks at covariate/explanatory variable later
56
Cases
Group who has a particular disease or trait to be observed
57
Controls
Group without the disease or trait
58
Case-Control Study
Retrospective study involving cases and controls
59
Estimating population percentages from Case-Control Study
Can't do it since the cases and controls are often randomly decided
60
Prospective Study
Group of subjects (cohorts) followed over time and the outcome is noted
61
Systematic Sampling
1/m of a group of n are sampled (say 1/5 of every incoming person into a concert)
62
Z-Score Reminder
63
What to do in cases of Bias
New sample design/plan to remove bias
64
Determining if a causal relationship is legitimate
Groups need to be randomized and experiments are preferred to observations since they can control for confounders