POPM 3240 Exam (Unit 3 (two-week unit)
Questions and Answers.
What are screening tests used for? - Answer A screening test is generally used as a population
approach on apparently healthy individuals to detect subclinical disease; it provides an early
indication of a pathological disease process or limited health/productivity outcome.
What are diagnostic tests used for? - Answer Diagnostic tests are used on sick individuals with
clinical disease to confirm, classify, inform treatment, or provide a prognosis for a particular
disease.
How to tell if a test has high validity - Answer high validity of the test is demonstrated when
the average of all the test results (half-way point of the curve) is near the true value
The notion of a "true value" is not an absolute number that is constant for every individual. The
value may vary due to biological factors such as age and gender. This is what we call biological
variability or the natural variation within an individual or population.
How to tell if a test has high reliability - Answer Reliability of a test can also be thought of as
the variation in the test results after it has been repeated numerous times or the deviation from
the average result (width of the curve)
High reliability is indicated by a narrow distribution of test results, instead of a wide range of
possibilities
What is a "gold standard" test - Answer In epidemiology, when a test has perfect validity we
refer to that test as the "gold standard". A gold standard test is one where all diagnoses are
correct and there are no misdiagnoses. Sadly, very few of these tests exist in the real world.
What are the 2 reasons we use 2x2 tables for - Answer 1) to evaluate the performance of a
diagnostic test(s) 2) to analyze the relationship between 2 variables such as a binary
health/disease outcome and a binary exposure
T or F: you should always put your outcome on top of the table - Answer True! ALWAYS put
your outcome (health or disease status) on top of the table (columns)
What to do when we don't already know the level of existing disease in a population - Answer
the background disease level is determined by an already existing test that is commonly in use.
This test is often referred to as the "reference" test or "gold standard" test if it has historically
been the test with the most accurate performance.
, T/F: You should put the test you are evaluating on the sides of the table (rows) - Answer True!
The second rule of thumb for 2x2 tables is to put the test you are evaluating on the sides of the
table (rows)
Cell A - Answer True positive
Cell B - Answer False positive
Cell C - Answer False negative
Cell D - Answer True negative
Causes of false positives - Answer False positives may be the result of a test cross-reacting
with a similar disease agent or biological marker, or due to a previous vaccination or infection,
or a test error.
Causes of false negatives - Answer False negatives may be the result of testing occurring too
early in the course of a disease, before a biological change has occurred.
These false negatives can also result from of the presence of test inhibiting substances in a
sample, an individual being immunocompromised resulting in an inability to produce enough of
the biological marker being tested (e.g., antibodies), the timing of biological cycles influencing
what is being measured (e.g., diurnal variation), or a test/technician error.
What are the 2 ways we measure validity - Answer Sensitivity and specificity
Sensitivity/Sn/fewer false negatives=^Sn - Answer Sensitivity (Sn) is the ability of the test to
identify correctly those who have the disease or outcome of interest.
Numerically, this is the proportion of the outcome positives (a+c) that test positive (a).
Sn = a / (a+c)
Since the Sn denominator includes c (false negatives), as Sn increases, the number of false
negatives decreases. Fewer false negatives means greater sensitivity, which in turn means that
we are more likely to detect disease if it is present.
Specificity/Sp/fewer false positives=^Sp - Answer Specificity (Sp) is the ability of the test to
identify correctly those who do not have the disease or outcome of interest.
Numerically, this is the proportion of the outcome negatives (b+d) that test negative (d).
Sp = d / (b+d)
Questions and Answers.
What are screening tests used for? - Answer A screening test is generally used as a population
approach on apparently healthy individuals to detect subclinical disease; it provides an early
indication of a pathological disease process or limited health/productivity outcome.
What are diagnostic tests used for? - Answer Diagnostic tests are used on sick individuals with
clinical disease to confirm, classify, inform treatment, or provide a prognosis for a particular
disease.
How to tell if a test has high validity - Answer high validity of the test is demonstrated when
the average of all the test results (half-way point of the curve) is near the true value
The notion of a "true value" is not an absolute number that is constant for every individual. The
value may vary due to biological factors such as age and gender. This is what we call biological
variability or the natural variation within an individual or population.
How to tell if a test has high reliability - Answer Reliability of a test can also be thought of as
the variation in the test results after it has been repeated numerous times or the deviation from
the average result (width of the curve)
High reliability is indicated by a narrow distribution of test results, instead of a wide range of
possibilities
What is a "gold standard" test - Answer In epidemiology, when a test has perfect validity we
refer to that test as the "gold standard". A gold standard test is one where all diagnoses are
correct and there are no misdiagnoses. Sadly, very few of these tests exist in the real world.
What are the 2 reasons we use 2x2 tables for - Answer 1) to evaluate the performance of a
diagnostic test(s) 2) to analyze the relationship between 2 variables such as a binary
health/disease outcome and a binary exposure
T or F: you should always put your outcome on top of the table - Answer True! ALWAYS put
your outcome (health or disease status) on top of the table (columns)
What to do when we don't already know the level of existing disease in a population - Answer
the background disease level is determined by an already existing test that is commonly in use.
This test is often referred to as the "reference" test or "gold standard" test if it has historically
been the test with the most accurate performance.
, T/F: You should put the test you are evaluating on the sides of the table (rows) - Answer True!
The second rule of thumb for 2x2 tables is to put the test you are evaluating on the sides of the
table (rows)
Cell A - Answer True positive
Cell B - Answer False positive
Cell C - Answer False negative
Cell D - Answer True negative
Causes of false positives - Answer False positives may be the result of a test cross-reacting
with a similar disease agent or biological marker, or due to a previous vaccination or infection,
or a test error.
Causes of false negatives - Answer False negatives may be the result of testing occurring too
early in the course of a disease, before a biological change has occurred.
These false negatives can also result from of the presence of test inhibiting substances in a
sample, an individual being immunocompromised resulting in an inability to produce enough of
the biological marker being tested (e.g., antibodies), the timing of biological cycles influencing
what is being measured (e.g., diurnal variation), or a test/technician error.
What are the 2 ways we measure validity - Answer Sensitivity and specificity
Sensitivity/Sn/fewer false negatives=^Sn - Answer Sensitivity (Sn) is the ability of the test to
identify correctly those who have the disease or outcome of interest.
Numerically, this is the proportion of the outcome positives (a+c) that test positive (a).
Sn = a / (a+c)
Since the Sn denominator includes c (false negatives), as Sn increases, the number of false
negatives decreases. Fewer false negatives means greater sensitivity, which in turn means that
we are more likely to detect disease if it is present.
Specificity/Sp/fewer false positives=^Sp - Answer Specificity (Sp) is the ability of the test to
identify correctly those who do not have the disease or outcome of interest.
Numerically, this is the proportion of the outcome negatives (b+d) that test negative (d).
Sp = d / (b+d)
