Upgrade to remove ads
Only $35.99/year

Validity and Sampling

Terms in this set (62)

Reliability
reproducibility consistency
Validity
accuracy, correctness
We need what in order to have confidence in our measurements?
Both reliability and validity
Measurement validity
extent to which an instrument measures what it is intended to measure
Can the test?
Discriminate among individuals? Evaluate change in magnitude or quality from one time to another? Predict an outcome?
Reliability is a prerequisite for ?
validity
A test cannot be valid
if it is unreliable
A test can be reliable
but not valid
Reliability=
consistency of a measurement. Does not require measurement to be "correct"
Validity=
alignment of measurement with a targeted construct.. Can we make inferences based on these value/findings?
Both are not inherent to an instrument
but must be evaluated within the context of test's intended use and a specific population
Validity and reliability is evaluated on a what?
on a continuum
Types of evidence for validity
content validity, criterion-related validity, construct validity
Face validity
an instrument appears to test what is intended to test. Ex: ROM, strength, balance
Face validity is
a judgment by the users of a test after the test is developed . Judgement made by those who use the instrument
Content validity evolves
out of the process of planning and constructing a test. Judgment is made by content experts, theoretical context and multi-item composition
Content Validity requirements 1
Items must represent the full cope of the construct being studied
Content Validity requirements 2
Number of items are proportionate to the importance of that concept. Example: topics on exam 1 are proportionate to the amount of time spent on topic in class
Content Validity requirements 3
No irrelevant items
Content Validity
Do measurements adequately represent concept. Typically used in questionnaire development
Content validity measured how?
Measured by expert panel review in planning/construction of instrument
Criterion-Related Validity
can the outcomes of the instrument be substituted for an established gold standard?
Criterion-Related validity
Highest and most objective form of validity
Criterion-related validity measured?
Correlation coefficients, sensitivity/specificity analyses
Concurrent validity
measurements between tests taken at approximately same time
Predictive validity
Establishes that the outcome of the target test can be used to predict a future criterion score or outcome. Example: do results of test predict success with certain intervention?
Construct validity
reflects the ability of an instrument to measure the theoretical dimensions of a construct. How well a tool measures an abstract concept/construct
Construct validity methods
Known-groups method, Convergence and divergence, factor analysis
Known group methods
Do test results differ between 2 groups (known to be different)? EX; is new pain score different between acutely injured and people 2 months after injury
Convergent Validity
Does test validity results correlate with other similar tests EX; pain and disability
Divergent validity
Low correlation with different tests? EX; new pain score and height
Validity of an instrument
putting together a "case" for validity. Use the highest form available. Each kind adds a piece of evidence support
Population
Persons, objects, or events that meet a specific set of criteria
target population
the larger population to which results of a study will be generalized to
Accessible population
the actual population of subjects available to be chosen for a study )a subset of the target population)
Sample
A subgroup of the population of interest (accessible population) which allows the results of research to be "generalized" to the population
Example: Study of Its attitudes about dry needling following hamstring injury
Target pop: Its practicing in USA ; Accessible pop: active members of Ortho section of APTA ; Sample: Ortho section members of APTA chosen at random who answer a survey
Inclusion Criteria
the primary traits of the target and accessible populations that will make someone eligible to be a participant
Exclusion criteria
factors that would preclude someone from being a subject. Traits/circumstances that preclude one who meets the inclusion criteria from participating in study
Exclusion criteria are NOT
the inverse of inclusion criteria. EX: Inclusion criterion: Males Exclusion criterion: Not males
Recruitment
Plan for subject recruitment from the accessible population. Not everyone in accessible population will meet the selection criteria or agree to participate
CONSORT flow diagram
reporting clinical trails
Sampling bias
Extent that sample systematically misrepresents population. Can be conscious/unconscious
Sampling error
Extend that sample randomly misrepresents population
Estimations of sampling error
are key to all inferential statistics
The difference between
sample averages (called statistics) and population averages (called parameters)
Probability samples
random selection. sample is "considered" representative or population. Can estimate sampling error
Non-probabilty samples
non-random samples, generalization is difficult. Cannot estimate sampling error
Probability sampling
simple random sampling, systematic sampling, stratified random sampling, cluster sampling
Simple random sampling
random sampling
Systematic sampling
selected every 10th person
Stratified random sampling
specify number from each category. Study for depression as a risk factor for dementia
Cluster sampling
Multilayer/stage
Cluster example whale watching tours
12 tours in a day, randomly select 5 and survey everyone on that tour
Stratified example whale watching tours
Take all customers from that day, stratify them by age and randomly sample
Nonprobabilty sampling
Convenience Sampling, Quota sampling, purposive sampling
Convenience sampling
most common form. subjects chosen on basis of availability
Consecutive sampling
recruit all folks to meet inclusion/exclusion criteria. Essentially the entire accessible population within a short period of time
Quota sampling
like stratified, but not random
Purposive sampling
subjects hand-picked by specific criteria
random sampling
how you get them
random assignment
what you do to them after you get them
Recommended textbook explanations

Psychology: Principles in Practice

1st EditionSpencer A. Rathus
1,024 explanations

Myers' Psychology for AP

2nd EditionDavid G Myers
900 explanations

A Concise Introduction To Logic (Mindtap Course List)

13th EditionLori Watson, Patrick J. Hurley
1,960 explanations

Myers' Psychology for AP

1st EditionDavid G Myers
313 explanations