Brainscape's Knowledge GenomeTM

Browse over 1 million classes created by top students, professors, publishers, and experts.


See full index

N547 final > Sampling > Flashcards

Sampling Flashcards

1
Q

sampling

A

selecting a group of people, events, behaviors, or other elements with which to conduct a study

the way it is chosen determines how it can be generalized

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

inclusion/eligibility criteria

A

characteristics that define the population you want to sample

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

exclusion criteria

A

characteristics that would contaminate sample (ie make sample less representative of people to whom you want to generalize)

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

representative sample

A

one whose key characteristics closely approximate those of population

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

sampling error

A

difference between sample statistic and true population parameter

any sample’s mean is expected to be slightly different from population mean

larger the sampling error, less representative sample is of target population

larger the sample, more representative sample is of target population

decreases power

occurs b/c of random/systematic variation

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

random variation

A

expected, normal difference from mean in individual values

values randomly scattered around mean

as sample size inc, sample mean more likely to have value similar to that of population mean

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

systematic variation/bias

A

all values in sample may tend to be higher/lower than population mean

occurs when sample is not representative

risk factors: nonrandom samples, exclusion criteria, high refusal rates/attrition

issues with generalizability

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

random selection

A

everyone in accessible population has equal chance of being selected

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

random assignment

A

sample is randomly assigned to tx/control group

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

sampling frame

A

list of all members in accessible population asked to participate

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

sampling plan

A

strategies for obtaining sample

  • probability/random
  • nonprobability/nonrandom
How well did you know this?
1
Not at all
2
3
4
5
Perfectly
12
Q

probability sampling methods

A
  • reduce sampling error
  • leaves selection to chance
  • inc study validity
  • less opportunity for systematic bias but is possible for it to occur by chance
How well did you know this?
1
Not at all
2
3
4
5
Perfectly
13
Q

simple random sampling

A
  • most basic
  • elements selected at random from sampling frame
  • each member of population has equal chance of being included
How well did you know this?
1
Not at all
2
3
4
5
Perfectly
14
Q

stratified random sampling

A
  • researcher wants to include certain population variables so that none is unrepresented
  • disproportionate/proportionate sampling
How well did you know this?
1
Not at all
2
3
4
5
Perfectly
15
Q

cluster sampling

A
  • samples according to natural clusters
  • applied when population is heterogeneous
  • used when simple random sample would be prohibitive OR when elements of population cannot easily be IDed
  • provides a means for obtaining larger sample at lower cost
  1. randomly choose groups from population
  2. randomly choose subjects from groups
How well did you know this?
1
Not at all
2
3
4
5
Perfectly
16
Q

systematic sampling

A
  • when ordered list of all members of pop is available

- select every kth individual on list, using starting point selected randomly

17
Q

nonprobability sampling methods

A

not every element of population need have an equal opportunity to be included

more likely to be nonrepresentative of population

18
Q

convenience sampling

A

“accidental sampling” - right place, right time

  • may or may not represent target pop
  • inexpensive/accessible/less time than other approaches
  • considered weak (biases)
  • many quantitative/some qualitative research
19
Q

quota sampling

A
  • convenience sampling with set proportions from certain groups (like stratified random sampling but not random)
  • used to assure representation
  • many quantitative/some qualitative
20
Q

purposive sampling

A
  • certain elements purposefully selected
  • aka purposeful/judgmental/selective sampling
  • conscious selection of persons most likely to provide useful info
  • commonly used in qualitative research - provides understanding of specific topic
  • less common in quantitative
21
Q

network/snowball sampling

A

used to obtain subjects difficult to ID or connect with in other ways

takes adv of social networks

bias: participants are not independent… but they have expertise to provide essential info for study purposes

more common in qualitative, may be used in quantitative

22
Q

power

A

capacity of study to detect differences/relationships that actually exist in population

23
Q

power analysis

A

power (usu set at 0.8/80%)
level of significance (usu 0.05)
effect size
sample size

24
Q

factors that affect power

A 
effect size
type of study
# of variables
sensitivity of measurement methods
data analysis techniques
25
Q

effect size

A
  • extent ton which a phenomenon is present in population
  • as ES dec, power dec
  • to demonstrate small ES, larger sample req
  • to demonstrate large ES, can get by with smaller sample
  • ES varies according to population
26
Q

types of study/sample size

A
  • descriptive case study: small
  • other descriptive/correlational: often large
  • quasi-/experimental: small - often enough to meet power analysis needs
27
Q

of variables

A
  • as # of variables inc, needed sample size may also inc
  • variables highly correlated with dependent v: effect size inc, sample size can be dec
  • variables inc in data analysis must be carefully selected
28
Q

measurement sensitivity

A

concept of precision

stronger the measurement method, smaller the sample that’s needed
(measurement methods has validity, reliability, and measure at interval/ratio level)

29
Q

data analysis techniques

A
  • differ by test
  • parametric tests more sensitive than non-parametric, when used appropriately
  • for t-test and ANOVA, power inc w/ equal group sizes; for unequal groups, total sample size must be larger
  • chi-sq test: weakest!
30
Q

sample size in qualitative research

A
  • no explicit/formal criteria
  • determined by design/scope of study
  • decisions to stop sampling guided by data saturation
  • data quality can affect sample size

N547 final (7 decks)

Brainscape helps you reach your goals faster, through stronger study habits.
© 2024 Bold Learning Solutions. Terms and Conditions