Validity and Reliability Assessments-Epidemiology – Flashcards
Unlock all answers in this set
Unlock answersquestion
What are the three indices of central tendency?
answer
1. mode 2. median 3. mean
question
the most frequently occurring observation
answer
mode
question
the measurement level below which half the observations fall, the 50th percentile
answer
median
question
the sum of the observed measurements divided by the number of observations
answer
mean
question
ability to distinguish between who has a disease and who does not
answer
validity
question
What are two ways to measures validity?
answer
1. specificity 2. sensitivity
question
ability of the test to determine correctly those who have the disease
answer
sensitivity
question
ability of the test to determine correctly those who do not have the disease
answer
specificity
question
true positive/true positive + false negative
answer
sensitivity
question
true negative/true negative + false positive
answer
specificity
question
the degree to which the study accurately answers the question it is intended to answer
answer
internal validity (study)
question
What are threats to internal validity?
answer
1. selection bias 2. information bias 3. uncontrolled confounding 4. small study sample
question
the extent to which we can generalize the results of a study to a broader population beyond the study population
answer
external validity (generalizability)
question
What is the threats to external validity?
answer
1. small study sample 2. improper selection of sample
question
the degree to which a test actually measures what it is designed to measure
answer
measurement validity (variable)
question
What are the threats to measurement validity?
answer
1. observer bias 2. instrument bias
question
restrict the study population to individuals who are comparable in other respects for the outcome under study
answer
increasing validity
question
restrict the study population to individuals whom complete and accurate information can be obtained
answer
increasing validity
question
provides information about the proportion of people who have the disease and those who do not have the disease
answer
predictive value
question
found by dividing the number of true positives by the total number who tested positive (true positives + false positives)
answer
positive predictive value
question
found by dividing the number of true negatives by the total number who tested negative (true negatives + false negatives)
answer
negative predictive value
question
What are the factors that affect the predictive value?
answer
1. prevalence of disease 2. specificity of the test
question
the degree to which a measurement procedure can be reproduced
answer
reliability
question
What are the threats to reliability?
answer
1. differences in observations 2. differences in instruments of measurements 3. instability of the attribute being measured
question
What affects reliability?
answer
1. intrasubject variation 2. intraobserver variation 3. interobserver variation
question
variation within individual subjects
answer
intrasubject variation
question
intrinsic biologic variability in the study subjects due to such things as fluctuations in mood or circadian rhythms
answer
intrasubject variation
question
variation in the reading of test results by the same reader
answer
intraobserver variation
question
variability in measurement that is due to the observer and includes such things as choice of words in an interview.
answer
intraobserver variation
question
variation between those reading the test results
answer
interobserver variation
question
variation between observers
answer
interobserver variation
question
What is used to evaluate interobserver variation?
answer
1. Percent agreement 2. Kappa Statistic
question
total agreed observations/total observations x 100
answer
percent agreement
question
quantifies the agreement that exceeds that which would be expected by chance alone
answer
kappa statistic
question
What are ways to increase reliability?
answer
1. standardizing the study procedures 2. standardizing the measurement methods 3. using the most up to date equipment 4. using similar testing conditions 5. repeat testing of samples
