calculated variable: A variable whose value is not coded in the database, but is calculated by SEER*Stat based on standard variables in the database and session-specific settings. For example, Age at Prevalence Date is a calculated variable because the age at prevalence is not coded in the database. This value is calculated based on the selected prevalence date and either date of birth (if available) or age and date at diagnosis.
conditional survival: Conditional survival is the likelihood for an individual, given having already survived for a certain duration or number of intervals after diagnosis of cancer, to continue to survive for some specified survival duration after that point.
confidence interval: An estimated range of values which is likely to include an unknown population parameter. The 95% (p-value = .05) and 99% (p-value = .01) confidence intervals are the most commonly used.
grouping: A group of values for a variable, with an associated label. Groupings are essentially formatting statements that allow you to label individual or groups of values.
index record: The record which causes a subject to be included in an analysis.
lost cases: A case is considered lost if it became lost to follow-up prior to a specific date. In prevalence, this is the prevalence date. In survival, the case is lost if it became lost to follow-up during an interval.
MDI: SEER*Stat is a Multiple Document Interface (MDI) application. MDI applications allow you to work with more than one document at a time. Examples of MDI applications include Microsoft Word and Excel, and WordPerfect. The fact that SEER*Stat is an MDI application means that you can have any number and combination of session and matrix windows open at the same time.
overlapping groupings: Two or more groupings in a variable that contain at least one common value. For example, the year range groupings "1980 - 1990" and "1990 - 2000" both include the value "1990".
person time at risk: For a particular subject, person time at risk is the time in years between entry into an analysis and exit from an analysis. This is the time during which a subject is at risk of having an event (whether second cancer, death, etc.) as defined by the analysis. Total person time at risk for a given subcategory is calculated by adding the person time at risk counted in that subcategory for each subject in the analysis.
sequence number: Every record has a sequence number variable that indicates its chronological position, relative to the person's other cancers. A sequence number of 0 indicates that the record is the person's only cancer. Any larger sequence number indicates the record's position among two or more cancers. For example, a sequence number of 3 represents the third of at least three cancers that the individual had. Sometimes a person's first record in the database has a sequence number of 2 or greater. This indicates that the person had one or more cancers prior to the time when their cancer history began to be collected by the database. It is known that they had cancer previously, but the details of the cancer are not known, and so no record exists for it in the database.
special interval: A special interval is a survival interval that starts at the time of diagnosis. Special intervals always start at time 0, and thus are not conditional on having survived for any duration, whereas conditional survival intervals always start at a later time. See Intervals for a Survival Session.
standard error: The standard error of an estimate is a measure of the sampling variability of the estimate.
time-dependent variables: Calculated variables which do not have a fixed value for each subject; rather, they are calculated as needed at different points during analysis.