Table 4.
Design effectsa for prevalence estimates of DSM-IV/CIDI disorder clustersb and for associationsc between socio-demographic variables and these clusters in the NCS-A household sample, school sample, and combined sample
| Household | School | Combined | |
|---|---|---|---|
| Prevalence estimates of DSM-IV/CIDI disordersb | 1.5 | 3.1 | 3.3 |
| 30-day | 1.6 | 4.6 | 4.1 |
| 12-month | 1.4 | 4.3 | 4.5 |
| Lifetime | |||
| Socio-demographic associationsc | 1.7 | 2.9 | 2.4 |
| 30-day | 1.4 | 3.5 | 2.9 |
| 12-month | 1.4 | 3.5 | 2.9 |
| Lifetime | |||
| (n) | (879) | (9,244) | (10,123) |
Design effects are the squares of the ratios of the standard errors of design-based estimates and estimates based on the assumption of simple random sampling. See the text for a more detailed discussion of the substantive interpretation of design effects.
The five DSM-IV/CIDI disorder clusters considered in each of three time frames (30-day prevalence, 12-month prevalence, and lifetime prevalence) are any anxiety disorder, any mood disorder, any impulse-control disorder, any substance disorder, and any disorder.
Associations were estimated in logistic regression equations that used information about respondent age, sex, and race-ethnicity (Non-Hispanic White versus all others) to predict each of the five outcomes in each of the three time frames.