Step Analysis | Toolbar | Syntax |
Declaration of the sample design | Menu tools → Statistics → Survey data analysis → Setup and utilities → Declare survey design for dataset → Survey data settings (Number of stages: 1, Primary sampling units: psu_aj, Strata: strata_aj, Sampling weight variable: V4611, SE: Strata with a single sampling unit: Treat as certainty units))] | gen double county=UPA gen double strata_aj=. gen double psu_aj=. replace strata_aj = UF*100000000 + county if V4107 ≥ 1 & V4107 ≤ 2 replace psu_aj=V0102*1000 if V4107 ≥ 1 & V4107 ≤ 2 replace strata_aj = UF*100000000 + 99*1000000 + V4602*10000 if V4107 == 3 replace psu_aj = UF*1000000 + V4602*10000 + county if V4107==3 svyset psu_aj [pw = V4611], strata(strata_aj) vce(linearized) singleunit(certainty) clear |
IRT (Generalized Partial Credit Model)* | Menu tools → Statistics → Survey data analysis → IRT (item response theory) → Model [(Ordered item models: Generalized partial credit model)/(Items: V1-V7)] → Fit model | svy: irt gpcm V1-V7 predict theta, latent |