You may define time points or intervals using calendar units or by defining your own system. For instance, you may identify temporal intervals by their order (1, 2, 3, .....).
|
Sample data |
Format Option 1 |
Format Option 2* |
Example |
Notes |
Valid range |
|
Yearly |
YYYY |
YY |
1998 |
|
0001 to 9999 |
|
Monthly |
YYYYMM |
YYMM |
199801 |
monthly values (MM) range from 01-12 |
000101 to 999912 |
|
Weekly |
YYYYWW |
YYWW |
199843 |
weekly values (WW) range from 01-52 |
000101 to 999952 |
|
Daily |
MM/DD/YYYY |
MM/DD/YY |
1/2/2001 |
month and date values may be expressed as single digits |
12/30/1899 to 12/31/9999 |
|
User-defined |
user-defined |
user-defined |
5 |
positive whole numbers that may represent points in time or non-overlapping, successive temporal intervals. In this scale, the intervals are naturally ordered by their magnitude (5 comes after 4) and there is a known unit distance between any 2 successive numbers. |
0 to 4.2 billion |
Census data must be submitted referenced to yearly time units. Data to be associated with the population-at-risk counts extrapolated from census data must be referenced to calendar-based units (any system other than user-defined). For some methods, you can specify study period limits to shorten the time period or to be able to omit time periods with zero case counts.
Duplicate time intervals cannot be submitted for purely temporal analysis. For spatio-temporal analysis, time intervals can be duplicated across regions, but not within regions.
*For the years, you can omit the first two numbers of the date for any date in the 1900s. Thus, if you use "89," for example, ClusterSeer will assume that the preceding numbers were "19," or "1989." You can use dates with two and four numbers in the same file as long as the dates other than those in the 1900s have four digits.