University enrollment dataset 1971–1990 with fuzzylised universe (13000, 20000)¶

Element · All elements
Evidence · no claims cited

Description¶

The article uses real enrollment data for a United States university from 1971 to 1990, with a maximum enrollment of 19328 and a minimum of 13055. The universe (13000, 20000) was selected and fuzzylised into seven even intervals u1–u7, each of length 1000, with seven fuzzy sets A1–A7 defined on it. Yearly memberships (Table 1), model outputs (Table 2), and FTM versus LRM residuals against actual values (Table 3) are reported.

Design Implications¶

Context¶

Requirements¶

• Historical enrollment records spanning the forecasting horizon and a universe interval larger than the data's maximum–minimum range.

Constraints¶

• The dataset covers a single university; the article does not claim generalization to other institutions.

Target Learners¶

• higher education planners and educational researchers

Target Learning Goals¶

• benchmarking enrollment forecasting methods against actual enrollments

Claims¶

Related Elements¶

Examples¶

• Apply three membership-based principles to translate fuzzy forecast outputs into numeric values
• Two-step fuzzy forecasting pattern: fuzzylise the universe, then interpret the fuzzy output
• Use fuzzy forecasting when historical data are scarce but experience knowledge is available, because the method tolerates imperfect data

Key Sources¶

• Song, Qiang; Chissom, Brad S. (1991). Forecasting Enrollments with Fuzzy Time Series. https://eric.ed.gov/?id=ED340733