ODS EXAM PART 2 QUESTIONS & ANSWERS
1. Net survival: refers to the estimate of the survival probability; the probability of surviving cancer in the absence of
other causes of death. Both relative survival and cause-specific survival settings can be used to estimate net survival, the
survival that would be observed if the only possible underlying cause of death was the disease under study.
2. Observed survival: refers to the calculation of an estimate of the probability of surviving all causes of death for
a specified time interval for a cohort of cancer cases. Observed survival does not consider cause of death, it simply looks
at who is alive and who is not.
3. overall survival: represents the length of time from either the date of diagnosis or the start of treatment for a
disease, such as cancer, that patients diagnosed with the disease are still alive
4. ambiguous terminology: Apparently, Appears, Comparable with, Compatible with, Consistent with,
Favor(s), Malignant appearing, Most likely, Presumed, Probable, Suspected, Suspicious (for), Typical (of)
5. Aggregate data: refers to information about groups of patients (e.g., data can be stratified by age, sex,
primary site, etc.) that is combined without personal identifiers. It does not include names of specific patients,
physicians, or facilities
6. De-identified data: refers to information that represents individual persons without personal identifiers
7. Simulation modeling: refers to the process of creating and analyzing a digital prototype of a physical
model to predict its performance in the real world
8. Joinpoint model: refers to a statistical model characterizing cancer trends using statistical criteria to deter-
mine how many times and when the trends in incidence or mortality rates changed. The joinpoint results are given as
calendar-year ranges and the annual percent change (APC) in the rates over each period
9. Logistic regression model: refers to a statistical method that describes the association between a
categorical dependent variable and a set of independent (explanatory) variables; used when the dependent variable has
only two values (e.g., 0 and 1 or yes and no).
10. Predictive model: refers to a statistical process used to predict outcomes, usually for an event in the future, but
can be applied to any type of unknown event; may be broadly classified as either parametric or nonparametric
1/
15
, 11. End point: refers to the health consequence as a result of some exposure; usually an undesirable health event
(e.g., the occurrence of disease or death), but occasionally a beneficial event (e.g., the recovery from an illness or
healing of a wound).
12. Latency: refers to the interval from the start of a disease until it is clinically detected
13. Morbidity: refers to the state of being diseased or unhealthy; a complication or other ettect of disease, such as
impaired organ function resulting from a surgical procedure
14. Cause-specific survival: refers to the length of time from either the date of diagnosis or the start of
treatment for a disease, such as cancer, to the date of death from the disease. Patients who die from causes unrelated
2/
15
1. Net survival: refers to the estimate of the survival probability; the probability of surviving cancer in the absence of
other causes of death. Both relative survival and cause-specific survival settings can be used to estimate net survival, the
survival that would be observed if the only possible underlying cause of death was the disease under study.
2. Observed survival: refers to the calculation of an estimate of the probability of surviving all causes of death for
a specified time interval for a cohort of cancer cases. Observed survival does not consider cause of death, it simply looks
at who is alive and who is not.
3. overall survival: represents the length of time from either the date of diagnosis or the start of treatment for a
disease, such as cancer, that patients diagnosed with the disease are still alive
4. ambiguous terminology: Apparently, Appears, Comparable with, Compatible with, Consistent with,
Favor(s), Malignant appearing, Most likely, Presumed, Probable, Suspected, Suspicious (for), Typical (of)
5. Aggregate data: refers to information about groups of patients (e.g., data can be stratified by age, sex,
primary site, etc.) that is combined without personal identifiers. It does not include names of specific patients,
physicians, or facilities
6. De-identified data: refers to information that represents individual persons without personal identifiers
7. Simulation modeling: refers to the process of creating and analyzing a digital prototype of a physical
model to predict its performance in the real world
8. Joinpoint model: refers to a statistical model characterizing cancer trends using statistical criteria to deter-
mine how many times and when the trends in incidence or mortality rates changed. The joinpoint results are given as
calendar-year ranges and the annual percent change (APC) in the rates over each period
9. Logistic regression model: refers to a statistical method that describes the association between a
categorical dependent variable and a set of independent (explanatory) variables; used when the dependent variable has
only two values (e.g., 0 and 1 or yes and no).
10. Predictive model: refers to a statistical process used to predict outcomes, usually for an event in the future, but
can be applied to any type of unknown event; may be broadly classified as either parametric or nonparametric
1/
15
, 11. End point: refers to the health consequence as a result of some exposure; usually an undesirable health event
(e.g., the occurrence of disease or death), but occasionally a beneficial event (e.g., the recovery from an illness or
healing of a wound).
12. Latency: refers to the interval from the start of a disease until it is clinically detected
13. Morbidity: refers to the state of being diseased or unhealthy; a complication or other ettect of disease, such as
impaired organ function resulting from a surgical procedure
14. Cause-specific survival: refers to the length of time from either the date of diagnosis or the start of
treatment for a disease, such as cancer, to the date of death from the disease. Patients who die from causes unrelated
2/
15
