2.3 Statistical Methods

Percentage estimates in the text tables of Chapters 3 and 4 have been rounded to the nearest one-tenth of 1 percent and screened to determine whether they meet a required level of statistical precision. Relative likelihood (odds-ratio) estimates in this report have been rounded to the nearest one-hundredth of 1 percent. Differences between demographic subgroups reported in the text are statistically significant at the .001 level.

Details of the statistical precision requirements, sample weighting, estimation, and statistical testing are discussed in Appendix B. The estimates and the standard errors fully take into account the complex sample design of the NHSDA. Appendix B also presents details of the logistic regression models used in this report.

In interpreting the estimates presented in this report, it is useful to remember that associations between variables are more likely to be statistically significant when the sample size is large. Associations involving measures with low overall prevalence are more difficult to identify as statistically significant than those involving measures with high overall prevalence. The results based on small subgroups should be interpreted cautiously. Interpretation of the findings should be based on broad patterns in the estimates, rather than strictly on the basis of statistical significance. Persistent or recurring patterns in the data are often informative, even when such trends and patterns are not consistently identified in statistical testing.

Table 2.1 Number of Respondents (Unweighted Ns),

by Age Group and Gender: 1994-1996 Combined NHSDAs

		Age Group
Demographic Characteristics		12-13	14-15	16-17	Total
Total		4,602	4,722	4,507	13,831
Gender	Male	2,326	2,415	2,181	6,922
	Femal e	2,276	2,307	2,326	6,909
Source: Office of Applied Studies, SAMHSA, National Household Survey on Drug Abuse, 1994-6

Table 2.2 Estimated Number of People (in Thousands) in the U.S. Civilian Non-institutionalized

Population (Weighted Ns), by Age Group and Gender: 1994-1996 Combined NHSDAs

		Age Group
Demographic Characteristics		12-13	14-15	16-17	Total
Total		7,315	7,732	7,117	22,164
Gender	Male	3,729	4,056	3,559	11,344
	Femal e	3,586	3,676	3,558	10,820
Source: Office of Applied Studies, SAMHSA, National Household Survey on Drug Abuse, 1994-6

Table 2.3 Estimated Percentage of the U.S. Civilian, Non-institutionalized

Population, by Age Group and Gender: 1994-1996 Combined NHSDAs

		Age Group
Demographic Characteristics		12-13	14-15	16-17	Total
Total		33.0	34.9	32.1	100.0
Gender	Male	51.0	52.5	50.0	51.2
	Femal e	49.0	47.5	50.0	48.8
		100.0	100.0	100.0	100.0
Source: Office of Applied Studies, SAMHSA, National Household Survey on Drug Abuse, 1994-6

This page was last updated on August 05, 2008.

SAMHSA, an agency in the Department of Health and Human Services, is the Federal Government's lead agency for improving the quality and availability of substance abuse prevention, addiction treatment, and mental health services in the United States.