Skip To Content Go to the Table Of Contents
Click for DHHS Home Page
Click for the SAMHSA Home Page
Click for the OAS Drug Abuse Statistics Home Page
Click for What's New
Click for Recent Reports and HighlightsClick for Information by Topic Click for OAS Data Systems and more Pubs Click for Data on Specific Drugs of Use Click for Short Reports and Facts Click for Frequently Asked Questions Click for Publications Click to send OAS Comments, Questions and Requests Click for OAS Home Page Click for Substance Abuse and Mental Health Services Administration Home Page Click to Search Our Site

2003 National Survey on Drug Use & Health:  Results

Appendix B: Statistical Methods and Measurement


B.1 Target Population

An important limitation of estimates of drug use prevalence from the National Survey on Drug Use and Health (NSDUH) is that they are only designed to describe the target population of the survey—the civilian, noninstitutionalized population aged 12 or older. Although this population includes almost 98 percent of the total U.S. population aged 12 or older, it excludes some important and unique subpopulations that may have very different drug use patterns. For example, the survey excludes active military personnel, who have been shown to have significantly lower rates of illicit drug use. Also, persons living in institutional group quarters, such as prisons and residential drug treatment centers, are not included in NSDUH, yet they have been shown in other surveys to have higher rates of illicit drug use. Also excluded are homeless persons not living in a shelter on the survey date; they are another population shown to have higher than average rates of illicit drug use. Appendix D describes other surveys that provide data for these populations.


B.2 Sampling Error and Statistical Significance

The national estimates, along with the associated variance components, were computed using a multiprocedure package, SUrvey DAta ANalysis (SUDAAN) Software for Statistical Analysis of Correlated Data. SUDAAN was designed for the statistical analysis of sample survey data from stratified, multistage cluster samples (RTI, 2001). The final, nonresponse-adjusted, and poststratified analysis weights were used in SUDAAN to compute unbiased design-based drug use estimates.

The sampling error (i.e., the standard error [SE]) of an estimate is the error caused by the selection of a sample instead of conducting a census of the population. Sampling error is reduced by selecting a large sample and by using efficient sample design and estimation strategies, such as stratification, optimal allocation, and ratio estimation.

With the use of probability sampling methods in NSDUH, it is possible to develop estimates of sampling error from the survey data. These estimates have been calculated in SUDAAN for all estimates presented in this report using a Taylor series linearization approach that takes into account the effects of the complex NSDUH design features. The sampling errors are used to identify unreliable estimates and to test for the statistical significance of differences between estimates.


B.2.1 Variance Estimation for Totals

Estimates of means or proportions, image representing p hat sub d, such as drug use prevalence rates, take the form of nonlinear statistics whenever the variances cannot be expressed in closed form. Variance estimation for nonlinear statistics in SUDAAN is performed using a first-order Taylor series approximation of the deviations of estimates from their expected values.

Corresponding to estimates of domain means or proportions, image representing p hat sub d, the number of drug users, image representing Y hat sub d, can be estimated as

 ,     D


image representing N hat sub d = estimated population total for domain d, and

image representing p hat sub d = estimated mean or proportion for domain d.

The SE for the total estimate is obtained by multiplying the SE of the mean or proportion by image representing N hat sub d, that is,

 .     D

This approach is theoretically correct when the domain size estimates, image representing N hat sub d, are among those forced to Census Bureau population projections through the weight calibration process (Chen et al., 2004). In these cases, image representing N hat sub d is not subject to sampling error. For a more detailed explanation of the weight calibration process, see Section A.3.2 in Appendix A.

For estimated domain totals, image representing Y hat sub d, where image representing N hat sub d is not fixed (i.e., where domain size estimates are not forced to U.S. Bureau of the Census population projections), this formulation may still provide a good approximation if it can be reasonably assumed that the sampling variation in image representing N hat sub d is negligible relative to the sampling variation in image representing p hat sub d. This is a reasonable assumption in most cases.

For a subset of the tables produced from the 2003 data, the above approach yielded an underestimate of the variance of a total because image representing N hat sub d was subject to considerable variation. In these cases, a different method within SUDAAN was used to estimate variances. SUDAAN provides an option to directly estimate the variance of the linear statistic that estimates a population total. Using this option did not affect the SE estimates for the corresponding proportions presented in the same sets of tables.


B.2.2 Suppression Criteria for Unreliable Estimates

As has been done in past NSDUH reports, direct survey estimates from the 2003 NSDUH considered to be unreliable due to unacceptably large sampling errors are not shown in this report and are noted by asterisks (*) in the tables containing such estimates. The criteria used for suppressing all direct survey estimates were based on the relative standard error (RSE) (defined as the ratio of the SE over the estimate) on nominal sample size and on effective sample size.

Proportion estimates (image representing p hat) within the range [0 < image representing p hat < 1], rates, and corresponding estimated number of users were suppressed if

RSE[-ln(image representing p hat)] > 0.175 when image representing p hat less than or equal to 0.5


RSE[-ln(1 - image representing p hat)] > 0.175 when image representing p hat > 0.5.     D

Using a first-order Taylor series approximation to estimate RSE[-ln(image representing p hat)] and RSE[-ln(1 - image representing p hat)], the following was obtained and used for computational purposes:

computational form


computational form     D

The separate formulas for image representing p hat less than or equal to 0.5 and image representing p hat > 0.5 produce a symmetric suppression rule; that is, if image representing p hat is suppressed, then 1 - image representing p hat will be as well. This ad hoc rule requires an effective sample size in excess of 50. When 0.05 < image representing p hat < 0.95, the symmetric property of the rule produces a local maximum effective sample size of 68 at image representing p hat = 0.5. Thus, estimates with these values of image representing p hat along with effective sample sizes falling below 68 are suppressed. See Figure B.1 for a graphical representation of the required minimum effective sample sizes as a function of the proportion estimated.


Figure B.1 Required Effective Sample as a Function of the Proportion Estimated


A minimum nominal sample size suppression criterion (n = 100) that protects against unreliable estimates caused by small design effects and small nominal sample sizes was employed. Prevalence estimates also were suppressed if they were close to 0 or 100 percent (i.e., if image representing p hat < 0.00005 or if image representing p hat greater than or equal to 0.99995).

Estimates of other totals (e.g., number of initiates), along with means and rates that are not bounded between 0 and 1 (e.g., mean age at first use and incidence rates) were suppressed if the RSEs of the estimates were larger than 0.5. Additionally, estimates of the mean age at first use were suppressed if the sample size was smaller than 10 respondents; also, the estimated incidence rate and number of initiates were suppressed if they rounded to 0.

The suppression criteria for various NSDUH estimates are summarized in Table B.1 at the end of this appendix.


B.2.3 Statistical Significance of Differences

This section describes the methods used to compare prevalence estimates in this report. Customarily, the observed difference between estimates is evaluated in terms of its statistical significance. Statistical significance is based on the p value of the test statistic and refers to the probability that a difference as large as that observed would occur due to random variability in the estimates if there were no difference in the prevalence rates for the population groups being compared. The significance of observed differences in this report is generally reported at the 0.05 and 0.01 levels. When comparing prevalence estimates, the null hypothesis (no difference between prevalence rates) was tested against the alternative hypothesis (there is a difference in prevalence rates) using the standard difference in proportions test expressed as

 ,     D

where image representing p hat sub 1 = first prevalence estimate, image representing p hat sub 2 = second prevalence estimate, var(image representing p hat sub 1) = variance of first prevalence estimate, var(image representing p hat sub 2) = variance of second prevalence estimate, and cov(image representing p hat sub 1, image representing p hat sub 2) = covariance between image representing p hat sub 1 and image representing p hat sub 2. In cases where significance tests between years were performed, the 2002 prevalence estimate becomes the first prevalence estimate and the 2003 estimate becomes the second prevalence estimate.

Under the null hypothesis, Z is asymptotically distributed as a normal random variable. Therefore, calculated values of Z can be referred to as the unit normal distribution to determine the corresponding probability level (i.e., p value). Because the covariance term is not necessarily zero, SUDAAN was used to compute estimates of Z along with the associated p values using the analysis weights and accounting for the sample design as described in Appendix A. A similar procedure and formula for Z were used for estimated totals.

When comparing population subgroups defined by three or more levels of a categorical variable, log-linear Chi-square tests of independence of the subgroup and the prevalence variables were conducted first to control the error level for multiple comparisons. If the Chi-square test indicated overall significant differences, the significance of each particular pairwise comparison of interest was tested using SUDAAN analytic procedures to properly account for the sample design. Using the published estimates and SEs to perform independent t tests for the difference of proportions will usually provide the same results as tests performed in SUDAAN. However, where the significance level is borderline, results may differ for two reasons: (1) the covariance term is included in SUDAAN tests whereas it is not included in independent t tests, and (2) the reduced number of significant digits shown in the published estimates may cause rounding errors in the independent t tests.

As part of a comparative analysis, prevalence estimates from the Monitoring the Future (MTF) study, sponsored by the National Institute on Drug Abuse (NIDA), were presented for recency measures of selected substances. The analyses focused on prevalence estimates for adults aged 19 to 28 and the average of 8th and 10th grade prevalence estimates. Published results were available from NIDA for significant differences between 2002 and 2003 prevalence estimates for adults aged 19 to 28, but not for the averaged rates for 8th and 10th graders. The difference between these averages from 2002 and 2003 was estimated and tested. The estimate of the difference of the averages can be expressed as

p bar sub 2 minus p bar sub 1

where p bar sub 1 equals one half the quantity of p hat sub 1 1 plus p hat sub 1 2, image representing p hat sub 11 and image representing p hat sub 12 are the prevalence estimates for the 8th and 10th grades, respectively, for 2002; image representing p line sub 2 is defined similarly for 2003. The variance of some prevalence estimate image representing p hat can be written as

equation     D

where n is the sample size and D is the appropriate design effect obtained from the sampling design. In the MTF study, design effects were available for comparisons between 2002 and 2003 estimates; therefore, the variance of the difference between 2002 and 2003 estimates for a particular grade can be expressed as


where i = 1 indexes the 8th grade, i = 2 indexes the 10th grade, Di is the design effect appropriate for comparisons between 2002 and 2003 estimates, and the nji are the sample sizes corresponding to the indexed year and grade prevalence estimates. Because the 8th and 10th grade samples were independently drawn, the variance of the difference between the 8th and 10th grade averages can be expressed as


The test statistic can therefore be written as


where Z is asymptotically distributed as a standard normal random variable.


B.3 Nonsampling Error

Nonsampling errors can occur from nonresponse, coding errors, computer processing errors, errors in the sampling frame, reporting errors, and other errors not due to sampling. Nonsampling errors are reduced through data editing, statistical adjustments for nonresponse, close monitoring and periodic retraining of interviewers, and improvement in various quality control procedures.

Although nonsampling errors can often be much larger than sampling errors, measurement of most nonsampling errors is difficult or impossible. However, some indication of the effects of some types of nonsampling errors can be obtained through proxy measures, such as response rates and from other research studies.


B.3.1 Screening and Interview Response Rate Patterns

In 2003, respondents continued to receive a $30 incentive in an effort to improve response rates over years prior to 2002. Of the 143,485 eligible households sampled for the 2003 NSDUH main study, 130,605 were successfully screened for a weighted screening response rate of 90.7 percent (Table B.2). In these screened households, a total of 81,631 sample persons were selected, and completed interviews were obtained from 67,784 of these sample persons, for a weighted interview response rate of 77.4 percent (Table B.3). A total of 8,909 (14.7 percent) sample persons were classified as refusals or parental refusals, 3,051 (4.0 percent) were not available or never at home, and 1,887 (3.9 percent) did not participate for various other reasons, such as physical or mental incompetence or language barrier (see Table B.3, which also shows the distribution of the selected sample by interview code and age group). The weighted interview response rate was highest among 12 to 17 year olds (89.6 percent), females (79.0 percent), blacks and Hispanics (80.1 and 79.6 percent, respectively), in nonmetropolitan areas (79.7 percent), and among persons residing in the Midwest (78.6 percent) (Table B.4).

The overall weighted response rate, defined as the product of the weighted screening response rate and weighted interview response rate, was 70.2 percent in 2003. Nonresponse bias can be expressed as the product of the nonresponse rate (1–R) and the difference between the characteristic of interest between respondents and nonrespondents in the population (Pr - Pnr). Thus, assuming the quantity (Pr - Pnr) is fixed over time, the improvement in response rates in 2002 and 2003 over prior years will result in estimates with lower nonresponse bias.


B.3.2 Inconsistent Responses and Item Nonresponse

Among survey participants, item response rates were above 99 percent for most questionnaire items. However, inconsistent responses for some items, including the drug use items, were common. Estimates of substance use from NSDUH are based on responses to multiple questions by respondents, so that the maximum amount of information is used in determining whether a respondent is classified as a drug user. Inconsistencies in responses are resolved through a logical editing process that involves some judgment on the part of survey analysts and is a potential source of nonsampling error.


B.3.3 Validity of Self-Reported Use

NSDUH estimates are based on self-reports of drug use, and their value depends on respondents' truthfulness and memory. Although many studies have generally established the validity of self-report data and NSDUH procedures were designed to encourage honesty and recall, some degree of underreporting is assumed (Harrell, 1997; Harrison & Hughes, 1997; Rouse, Kozel, & Richards, 1985). No adjustment to NSDUH data is made to correct for this. The methodology used in NSDUH has been shown to produce more valid results than other self-report methods (e.g., by telephone) (Aquilino, 1994; Turner, Lessler, & Gfroerer, 1992). However, comparisons of NSDUH data with data from surveys conducted in classrooms suggest that underreporting of drug use by youths in their homes may be substantial (Gfroerer, 1993; Gfroerer, Wright, & Kopstein, 1997).


B.4 Measurement Issues

Several measurement issues are associated with the 2003 NSDUH that may be of interest and are discussed in this section. Specifically, these issues include the impact of questionnaire changes on trends and the methods for measuring nicotine (cigarette) dependence, substance dependence and abuse, incidence, and serious mental illness (SMI). In addition, the results of an analysis of differences in estimates for Native Hawaiians or Other Pacific Islanders in 2002 and 2003 are presented.


B.4.1 Impact of Questionnaire Changes on Trends

To maintain valid trend measurement, changes to NSDUH core questions on substance use are rarely made. However, small refinements or additions to core questions sometimes are implemented if necessary to improve the questionnaire or obtain new information, when analyses demonstrate that there will be negligible impact on the estimates for which trends are needed. In the 2003 NSDUH, two small changes within the hallucinogens module of the questionnaire were made:

With regard to the first issue, the "fill" refers to text that the computer inserts into a question based on responses to previous questions. In 2002, for respondents who reported lifetime use of LSD and a combination of "no," "don't know," or "refused" to lifetime use of all other hallucinogens, the hallucinogen name "filled" in the questions about age at first use and recency of use was "LSD." In 2003, the "fill" for these respondents was "LSD or any other hallucinogen" because of the uncertainty about their use of other hallucinogens. This same logic applied to respondents who reported use of only PCP or of only Ecstasy (MDMA) and who answered other hallucinogen questions as "don't know" or "refused." This change affected a miniscule number of respondents (three for LSD, none for PCP, and four for Ecstasy). This change was made in 2003 because respondents who did not know or refused to report whether they had ever used other hallucinogens were potentially users of these other hallucinogens. For respondents whose only use was LSD, PCP, or Ecstasy and who answered all other lifetime hallucinogen questions as "no," the respective "fills" continued to be "LSD," "PCP," or "Ecstasy."

A second small change to the questionnaire in 2003 involved the addition of follow-up questions in the hallucinogens module to capture information about the frequency of use in the past 12 months or past 30 days. If respondents reported that they last used any hallucinogen "more than 12 months ago," they were skipped out of questions related to their frequency of use in the past 12 months and past 30 days. If they then, for example, reported that they last used LSD "more than 30 days ago but within the past 12 months," that would trigger a consistency check between these two related recency questions. In 2003, if respondents revised their hallucinogen recency to indicate use more than 30 days ago but within the past 12 months, they were asked to provide the information on their frequency of use in the past 12 months. In 2002, respondents were not asked these follow-up questions in these situations. Therefore, unknown frequency of use data for these cases were replaced with statistically imputed values. In contrast, the inclusion of these follow-up questions in 2003 resulted in fewer cases having unknown frequency of use data that required imputation.

Table B.5 shows some comparisons of estimates between 2002 and 2003. Estimates were produced for 2003 with and without data from the additional follow-up questions. To produce the estimates without the additional questions, the data were reedited and reimputed without taking into account information present in these new questions.

The addition of new follow-up questions in 2003 had little effect on estimates of frequency of use in the past 12 months and past 30 days. In particular, where statistically significant differences in estimates occurred between 2002 and 2003, these differences generally were significant for both versions (with and without follow-up questions) of the 2003 estimate. There were two exceptions. The difference in the estimated of number of days (300 days or more) used hallucinogens in past year among past year users aged 18 to 25 was statistically significant between 2002 and 2003 without follow-up questions. Also, the difference in the estimate of hallucinogen use on 1 or 2 days in the past month for the population aged 12 or older was statistically significant between 2002 and 2003 without the follow-up questions. Yet these two instances do not offer enough evidence to conclude that the addition of the follow-up questions in 2003 had any effect on estimates for the 12–month or 30–day frequency of use of hallucinogens. Because there were multiple comparisons and no correction factors were used to adjust for these multiple comparisons, it is common to expect at least 5 percent of the comparisons to be statistically significant, as was seen here, even if the null hypothesis of no difference is true. Furthermore, because the data were reimputed, statistically significant differences could be attributable to differences in random variation due to imputation.1


B.4.2 Nicotine (Cigarette) Dependence

The 2003 NSDUH computer-assisted interviewing (CAI) instrumentation included questions designed to measure nicotine dependence among current cigarette smokers. Those respondents who only smoked specialty cigarettes (bidis or cloves) in the past month were not defined as current cigarette smokers and therefore could not be defined as being nicotine dependent. Nicotine dependence is based on criteria derived from the Nicotine Dependence Syndrome Scale (NDSS) (Shiffman, Hickcox, Gnys, Paty, & Kassel, 1995; Shiffman, Waters, & Hickcox, 2004) or the Fagerstrom Test of Nicotine Dependence (FTND) (Fagerstrom, 1978; Heatherton, Kozlowski, Frecker, & Fagerstrom, 1991).

The conceptual roots of the NDSS (Edwards & Gross, 1976) are similar to those behind the American Psychiatric Association (APA) Diagnostic and Statistical Manual of Mental Disorders, 4th edition (DSM-IV), concept of dependence (APA, 1994). The 2003 NSDUH contained 19 NDSS questions that addressed five aspects of dependence:

  1. Smoking drive (compulsion to smoke driven by nicotine craving and withdrawal)

    1. After not smoking for a while, you need to smoke in order to feel less restless and irritable.

    2. When you don't smoke for a few hours, you start to crave cigarettes.

    3. You sometimes have strong cravings for a cigarette where it feels like you're in the grip of a force you can't control.

    4. You feel a sense of control over your smoking - that is, you can "take it or leave it" at any time.

    5. You sometimes worry that you will run out of cigarettes.

  2. Nicotine tolerance

    1. Since you started smoking, the amount you smoke has increased.

    2. Compared to when you first started smoking, you need to smoke a lot more now in order to be satisfied.

    3. Compared to when you first started smoking, you can smoke much, much more now before you start to feel anything.

  3. Continuous smoking

    1. You smoke cigarettes fairly regularly throughout the day.

    2. You smoke about the same amount on weekends as on weekdays.

    3. You smoke just about the same number of cigarettes from day to day.

    4. It's hard to say how many cigarettes you smoke per day because the number often changes.

    5. It's normal for you to smoke several cigarettes in an hour, then not have another one until hours later.

  4. Behavioral priority (preferring smoking over other reinforcing activities)

    1. You tend to avoid places that don't allow smoking, even if you would otherwise enjoy them.

    2. There are times when you choose not to be around your friends who don't smoke because they won't like it if you smoke.

    3. Even if you're traveling a long distance, you'd rather not travel by airplane because you wouldn't be allowed to smoke.

  5. Stereotypy (fixed patterns of smoking)

    1. Do you have any friends who do not smoke cigarettes?

    2. The number of cigarettes you smoke per day is often influenced by other things - how you're feeling, or what you're doing, for example.

    3. Your smoking is not affected much by other things. For example, you smoke about the same amount whether you're relaxing or working, happy or sad, alone or with others.

Each of the five domains listed above can be assessed by a continuous measure, but an average score across all domains also can be obtained for overall nicotine dependence (Shiffman et al., 2004). The NDSS algorithm for calculating this average score was based on the respondent's answers to 17 of the 19 questions listed above. The two items regarding nonsmoking friends (4b and 5a) were excluded due to frequently missing data.

In order to optimize the number of respondents who could be classified for nicotine dependence, imputation was utilized for all respondents who answered all but 1 of the 17 nicotine dependence questions that were used in the NDSS algorithm. The imputation was based upon weighted least square regressions using the other 16 NDSS items as covariates in the model (Grau et al., 2003).

Responses to items 1a-c, 1e, 2a-c, 3a-c, 4a, 4c, and 5c were coded from 1 to 5 where

1 = Not at all true of me
2 = Sometimes true of me
3 = Moderately true of me
4 = Very true of me
5 = Extremely true of me

Responses to items 1d, 3d, 3e, and 5b were reverse coded from 5 to 1 where

5 = Not at all true of me
4 = Sometimes true of me
3 = Moderately true of me
2 = Very true of me
1 = Extremely true of me

The NDSS score was calculated as the sum of the responses to the previous questions divided by 17. The NDSS score was only calculated for current cigarette smokers who had complete data for all 17 questions.

A current cigarette smoker was defined as nicotine dependent if his or her NDSS score was greater than or equal to 2.75. If the NDSS score for a current cigarette smoker was less than 2.75 or the NDSS score was not defined, then the respondent was determined to be nondependent based on the NDSS. The threshold of 2.75 was derived by examining the distribution of scores in other samples of smokers administered the NDSS, including a contrast of scores obtained for nondependent smokers (chippers) versus heavy smokers (Shiffman, Paty, Kassel, Gnys, & Zettler-Segal, 1994).

The FTND is a multi-item measure of dependence, but much of its ability to discriminate dependent smokers derives from a single item that assesses how soon after waking that smokers have their first cigarette (Heatherton, Kozlowski, Frecker, Rickert, & Robinson, 1989). Because most nicotine is cleared from the bloodstream overnight, smokers typically wake in nicotine deprivation, and rapid movement to smoke is considered a sign of dependence. A current cigarette smoker was defined as nicotine dependent based on the FTND if the first cigarette smoked was within 30 minutes of waking up on the days that he or she smoked.

Using both the NDSS and the FTND measures described above, a current cigarette smoker was defined as having nicotine dependence in the past month if he or she met either the NDSS or FTND criteria for dependence.


B.4.3 Illicit Drug and Alcohol Dependence and Abuse

The 2003 NSDUH CAI instrumentation included questions that were designed to measure dependence and abuse of illicit drugs and alcohol. For these substances,2 dependence and abuse questions were based on the criteria in the DSM-IV (APA, 1994).

Specifically, for marijuana, inhalants, hallucinogens, and tranquilizers, a respondent was defined as having dependence if he or she met three or more of the following six dependence criteria:

  1. Spent a great deal of time over a period of a month getting, using, or getting over the effects of the substance.

  2. Used the substance more often than intended or was unable to keep set limits on the substance use.

  3. Needed to use the substance more than before to get desired effects or noticed that same amount of substance use had less effect than before.

  4. Inability to cut down or stop using the substance every time tried or wanted to.

  5. Continued to use the substance even though it was causing problems with emotions, nerves, mental health, or physical problems.

  6. The substance use reduced or eliminated involvement or participation in important activities.

For alcohol, pain relievers, cocaine, heroin, sedatives, and stimulants, a respondent was defined as having dependence if he or she met three or more of seven dependence criteria, including the six standard criteria listed above plus a seventh withdrawal symptom criterion. The seventh withdrawal criterion is defined by a respondent reporting having experienced a certain number of withdrawal symptoms that vary by substance (e.g., having trouble sleeping, cramps, hands tremble).

For each illicit drug and alcohol, a respondent was defined as having abused that substance if he or she met one or more of the following four abuse criteria and was determined not to be dependent upon the respective substance in the past year.

  1. Serious problems at home, work, or school caused by substance, such as neglecting your children, missing work or school, doing a poor job at work or school, or losing a job or dropping out of school.

  2. Used substance regularly and then did something that might have put you in physical danger.

  3. Use of substance caused you to do things that repeatedly got you in trouble with the law.

  4. Had problems with family or friends that were probably caused by using the substance and continued to use the substance even though you thought the substance use caused these problems.

Criteria used to determine whether a respondent was asked the dependence and abuse questions included responses from core substance use and frequency of substance use questions, as well as noncore substance use questions. Unknown responses in the core substance use and frequency of substance use questions were imputed. However, the imputation process did not take into account reported data in the noncore CAI modules. Responses to the dependence and abuse questions that were inconsistent with the imputed substance use or frequency of substance use could have existed. Because different criteria and different combinations of criteria were used as skip logic for each substance, different types of inconsistencies may have occurred for certain substances between responses to the dependence and abuse questions and the imputed substance use and frequency of substance use as described below.

For alcohol and marijuana, respondents were asked the dependence and abuse questions if they reported substance use in the past year but did not report their frequency of substance use in the past year. Therefore, inconsistencies could have occurred where the imputed frequency of use response indicated less frequent use than required for respondents to be asked the dependence and abuse questions originally.

For stimulants, heroin, and cocaine, respondents were asked the dependence and abuse questions if they reported past year use in a core drug module or past year use in the noncore special drugs module. Thus, inconsistencies could have occurred when the response to a core substance use indicated no use in the past year, but responses to dependence and abuse questions indicated substance dependence or abuse for the respective substance.

A respondent might have provided ambiguous information about past year use of any individual substance, in which case these respondents were not asked the dependence and abuse questions for that substance. Subsequently, these respondents could have been imputed to be past year users of the respective substance. In this situation, the dependence and abuse data were unknown; thus, these respondents were classified as not dependent on or abusing the respective substance. However, the respondent was never actually asked the dependence and abuse questions.


B.4.4 Incidence

For diseases, the incidence rate for a population is defined as the number of new cases of the disease, N, divided by the person time, PT, of exposure or

 .     D

The person time of exposure can be measured for the full period of the study or for a shorter period. The person time of exposure ends at the time of diagnosis (e.g., Greenberg, Daniels, Flanders, Eley, & Boring, 1996, pp. 16–19). Similar conventions are applied for defining the incidence of first use of a substance.

Beginning in 1999, the survey questionnaire allows for collection of year and month of first use for recent initiates. Month, day, and year of birth also are obtained directly or imputed in the process. In addition, the questionnaire call record provides the date of the interview. By imputing a day of first use within the year and month of first use reported or imputed, the key respondent inputs in terms of exact dates are known. Exposure time can be determined in terms of days and converted to an annual basis. Beginning in 2003, the immigrant population was addressed in the incidence analysis. That is, immigrants who initiated drug use outside the United States were not included in this analysis. However, those immigrants who did not initiate outside the United States were included in the analysis for the time period since they entered the United States. If respondents indicated that they were not born in the United States, the survey questionnaire asked the respondent how long they had lived in the United States. Using this information, an imputation-revised entry age and date were created.

Having exact dates of birth and first use (and if the respondent is an immigrant, his or her exact date of entry) also allows the person time of exposure during the targeted period, t, to be determined. Let the target time period for measuring incidence be specified in terms of dates; for example, the period 1998 would be specified as

t = [t1,t2) = [1 Jan 1998, 1 Jan 1999),     D

a period that includes 1 January 1998 and all days up to but not including 1 January 1999. The target age group also can be defined by a half-open interval as a = [a1,a2). For example, the age group 12 to 17 would be defined by a = [12,18) for persons at least age 12, but not yet age 18. If person i was in age group a and residing in the United States during period t, the time and age interval, Lt,a,i , then can be determined by the intersection:


assuming the time of birth and time of entry into the United States can be written in terms of day (DOBi and DOEi), month (MOBi and MOEi), and year (YOBi and YOEi). Either this intersection will be empty (Lt,a,i = image representing an empty set), or it will be designated by the half-open interval, Lt,a,i = [M1,i,M2,i), where

m1,i = Max{t1,(DOBiMOBiYOBi + a1), DOEiMOEiYOEi}     D


m2,i = Min{t2,(DOBiMOBiYOBi + a2)}.     D

The date of first use, tfu,d,i, also is expressed as an exact date. An incident of first drug d use by person i in age group a occurs in time tfu,d,i image representing element [m1,i,m2,i). The indicator function Ii(d,a,t) used to count incidents of first use is set to 1 when tfu,d,i image representing element [m1,i,m2,i) and to 0 otherwise. The person-time exposure measured in years and denoted by ei(d,a,t) for a person i of age group a depends on the date of first use. If the date of first use precedes the target period (tfu,d,i < m1,i), then ei (d,a,t) = 0. If the date of first use occurs after the target period or if person i has never used drug d, then

 .     D

If the date for first use occurs during the target period Lt,a,i, then

 ,     D

Note that both Ii(d,a,t) and ei(d,a,t) are set to 0 if the target period Lt,a,i is empty (i.e., person i is not in age group a during any part of time t). The incidence rate then is estimated as a weighted ratio estimate:

 ,     D

where the wi are the analytic weights. Starting in 2002, estimates were reported separately for males and females, as well as overall. For a more detailed explanation of the incidence methodology, see Packer, Odom, Chromy, Davis, and Gfroerer (2002).

The estimates of incidence in this report are based on retrospective reports of age at first drug use by survey respondents interviewed during 2002 and 2003. Because they are based on retrospective reports, they may be subject to different types of biases. Bias due to differential mortality occurs because some persons who were alive and exposed to the risk of first drug use in the historical periods shown in the tables died before the 2002 and 2003 NSDUHs were conducted. This bias is probably very small for estimates shown in this report. Incidence estimates also are affected by memory errors, including recall decay (tendency to forget events occurring long ago) and forward telescoping (tendency to report that an event occurred more recently than it actually did). Recall decay would tend to result in a downward bias in estimates for earlier years (e.g., 1960s and 1970s), and telescoping would tend to result in an upward bias for estimates for more recent years. There also is likely to be some underreporting bias due to social acceptability of drug use behaviors and respondents' fear of disclosure. This is likely to have the greatest impact on recent estimates, which reflect more recent use and reporting by younger respondents. Finally, for drug use that is frequently initiated at age 10 or younger, estimates based on retrospective reports 1 year later underestimate total incidence because 11–year–old (and younger) children are not sampled by NSDUH. Prior analyses showed that alcohol and cigarette (any use) incidence estimates could be significantly affected by this. Therefore, for these drugs, only 2002 age-specific rates and the number of initiates aged 18 or older (or 21 or older for applicable tables) were reported. Likewise, for these drugs, 2001 and 2002 estimates were made using 2003 NSDUH data only.

A recent evaluation of NSDUH retrospective estimates of incidence suggests that these types of bias are significant and differ by substance and length of recall (Gfroerer, Hughes, Chromy, Heller, & Packer, 2004). For very recent time periods, bias in estimates of marijuana, cocaine, alcohol, and cigarettes appears to be small, but for all other substances there is significant downward bias. Bias for all substances increases the further back in time the estimates are made, suggesting a relationship with the length of recall. Due to the potential reporting biases described above, comparisons between years, particularly between recent estimates and those 10 or more years prior, should be made with caution.


B.4.5 Serious Mental Illness

For the 2003 NSDUH, mental health among adults was measured using a scale to ascertain serious mental illness (SMI). This scale consisted of six questions that asked respondents how frequently they experienced symptoms of psychological distress during the 1 month in the past year when they were at their worst emotionally. The use of this scale is based on a methodological study designed to evaluate several screening scales for measuring SMI in NSDUH. These scales consisted of a truncated version of the World Health Organization (WHO) Composite International Diagnostic Interview Short Form (CIDI-SF) scale (Kessler, Andrews, Mroczek, Üstün, & Wittchen, 1998), the K10/K6 scale of nonspecific psychological distress (Furukawa, Kessler, Slade, & Andrews, 2003), and the WHO Disability Assessment Schedule (WHO-DAS) (Rehm et al., 1999).

The methodological study to evaluate the scales consisted of 155 respondents selected from a first-stage sample of 1,000 adults aged 18 or older. First-stage respondents were selected from the Boston metropolitan area and screened on the telephone to determine whether they had any emotional problems. Respondents reporting emotional problems at the first stage were oversampled when selecting the 155 respondents at the second stage. The selected respondents were interviewed by trained clinicians in respondents' homes using both the NSDUH methodology and a structured clinical interview. The first interview included the three scales described above using audio computer-assisted self-interviewing (ACASI). Respondents completed the ACASI portion of the interview without discussing their answers with the clinician. After completing the ACASI interview, respondents then were interviewed using the 12–month nonpatient version of the Structured Clinical Interview for DSM-IV (SCID) (First Spitzer, Gibbon, & Williams, 1997) and the Global Assessment of Functioning (GAF) (Endicott, Spitzer, Fleiss, & Cohen, 1976) to classify respondents as either having or not having SMI.

The data from the 155 respondents were analyzed using logistic regression analysis to predict SMI from the scores on the screening questions. Analysis of the model fit indicated that each of the scales alone and in combination were significant predictors of SMI and the best fitting models contained either the CIDI-SF or the K10/K6 alone. Receiver operating characteristic (ROC) curve analysis was used to evaluate the precision of the scales to discriminate between respondents with and without SMI. This analysis indicated that the K6 was the best predictor. The results of the methodological study and the K10/K6 scale of nonspecific psychological distress are described in more detail in Kessler et al. (2003).

To score the six items on the K6 scales, they were first coded from 0 to 4 and summed to yield a number between 0 and 24. This involved transforming response categories for the six questions (DSNERV1, DSHOPE, DSFIDG, DSNOCHR, DSEFFORT, and DSDOWN) given below so that "all of the time" was coded 4, "most of the time" was coded 3, "some of the time" 2, "a little of the time" 1, and "none of the time" 0, with "don't know" and "refuse" also coded 0. Summing across the transformed responses resulted in a score with a range from 0 to 24. Respondents with a total score of 13 or greater were classified as having a past year SMI. This cutpoint was chosen to equalize false positives and false negatives.

The questions comprising the K6 scale are given as follows:

Most people have periods when they are not at their best emotionally. Think of one month in the past 12 months when you were the most depressed, anxious, or emotionally stressed. If there was no month like this, think of a typical month.

During that month, how often did you feel nervous?

  1. All of the time
  2. Most of the time
  3. Some of the time
  4. A little of the time
  5. None of the time

Response categories are the same for the following questions:

During that same month when you were at your worst emotionally . . . how often did you feel hopeless?
During that same month when you were at your worst emotionally . . . how often did you feel restless or fidgety?
During that same month when you were at your worst emotionally . . . how often did you feel so sad or depressed that nothing could cheer you up?
During that same month when you were at your worst emotionally . . . how often did you feel that everything was an effort?
During that same month when you were at your worst emotionally . . . how often did you feel down on yourself, no good, or worthless?


B.4.6 Examination of Differences between 2002 and 2003 Estimates for Non-Hispanic Native Hawaiians or Other Pacific Islanders

Large differences in the estimated rate of SMI for the non-Hispanic Native Hawaiian or Other Pacific Islander (NH/OPI) group were observed between the 2002 and 2003 NSDUHs. Although not statistically significant, the estimated rate of SMI increased from 5.4 to 12.4 percent for this group between the 2 years. There also was a large decrease between 2002 and 2003 in the estimated number of people in the NH/OPI category, from 813,000 in 2002 to 490,000 in 2003.

The reasons for these differences were investigated, first by verifying the weighting and estimation procedures that had been used and then by examining the distributions of weights and weight components. It appears that the differences between years are due to a lack of stability in the estimates of the number of people in the NH/OPI group. The U.S. Bureau of the Census estimate of the number of people in the NH/OPI group was about 311,000 in 2000, a very small proportion of the U.S. population. In general, for small population groups, there can be large variability from year to year in the number of persons who are randomly selected for NSDUH and in estimates of substance use and mental health. Poststratification can be used to control the year-to-year variability in the estimated number of people in a particular group. This is done by adjusting the sum of the weights for particular groups to an independent census estimate of the number in that group for the time period in question. However, NSDUH does not currently poststratify to independent estimates of NH/OPI.

More specifically, the differences between 2002 and 2003 arose because relative to 2002, fewer people in 2003 in the older age groups identified themselves as Other Pacific Islanders. Breaking the NH/OPI sample down into NH and OPI shows that the larger weighted count of NH/OPI in 2002 compared with 2003 was due to a larger OPI count for that year. Table B.6 presents the unweighted and weighted counts and percentage distributions by age group for the NH and OPI groups aged 18 or older by year. The weighted number of NH respondents remained fairly consistent between the 2 years, but the number of OPI respondents decreased from 587,033 in 2002 to 274,735 in 2003. This was due to the relatively greater share of older OPI respondents in 2002. In 2002, there were 31 OPI respondents aged 35 or older representing a weighted total of 372,297 persons, but in 2003, there were only 11 OPI respondents aged 35 or older representing a weighted total of 83,399 persons.

In addition, analyses were conducted to examine whether there was a shift in the number of persons reporting more than one race between 2002 and 2003. Persons claiming two or more races in 2002 and 2003 were examined by Hispanicity and by whether they claimed NH/OPI as one of their races. Although more respondents claimed two or more races in 2003 than in 2002, there was not a large shift in the number who included NH/OPI as one of their races.

Given the instability in the estimated number of people selecting the NH/OPI category, the impact on additional estimates from the survey was examined for 2002 and 2003. Lifetime, past year, and past month any illicit drug use, marijuana use, cocaine use, and any hallucinogen use were examined. An additional item, driving while under the influence of any illicit drugs in the past year, was examined because it was the only variable in the detailed NSDUH tables for which there were significant differences for the NH/OPI racial group between the 2 years and that included all age groups. (Comparisons for other variables also were significant, but those variables were collected only for 12 to 17 year olds.)

Table B.7 presents the results of these comparisons. The only significant differences between the 2 years were found in the weighted estimates of driving under the influence of drugs for all NH/OPI respondents aged 18 or older (3.1 percent in 2002 and 9.7 percent in 2003) and for the 18 to 25 age group (6.4 percent in 2002 and 21.4 percent in 2003).


Table B.1 Summary of 2003 NSDUH Suppression Rules
Estimate Suppress if:
Prevalence rate, image representing p hat, with nominal sample size, n, and design effect, deff (1) The estimated prevalence rate, image representing p hat, is < 0.00005 or greater than or equal to 0.99995, or

(2)  when image representing p hat less than or equal to 0.5,     D    or

    when image representing p hat > 0.5,     D    or

(3) Effective n < 100, where Effective N = Effective n is the ratio of n over the design effect or

(4) n < 100.

Note: The rounding portion of this suppression rule for prevalence rates will produce some estimates that round at one decimal place to 0.0 or 100.0 percent but are not suppressed from the tables.

Estimated number (numerator of image representing p hat) The estimated prevalence rate, image representing p hat, is suppressed.

Note: In some instances when image representing p hat is not suppressed, the estimated number may appear as a 0 in the tables; this means that the estimate is greater than 0 but less than 500 (estimated numbers are shown in thousands).

Mean age at first use, image representing x bar, with nominal sample size, n (1) RSE(image representing x bar) > 0.5, or

(2) n < 10.

Incidence rate, image representing r hat (1) The incidence rate, image representing r hat, rounds to < 0.1 per 1,000 person-years of exposure, or

(2) RSE(image representing r hat) > 0.5.

Number of initiates, image representing t hat (1) The number of initiates image representing t hat, rounds to < 1,000 initiates, or

(2) RSE(image representing t hat) > 0.5.

Source: SAMHSA, Office of Applied Studies, National Survey on Drug Use and Health, 2003.


Table B.2 Weighted Percentages and Sample Sizes for 2002 and 2003 NSDUHs, by Screening Result Code
  Sample Size Weighted Percentage
2002 2003 2002 2003
Total Sample 178,013 170,762 100.00 100.00
     Ineligible cases 27,851 27,277 15.27 15.84
     Eligible cases 150,162 143,485 84.73 84.16
Ineligibles 27,851 27,277 15.27 15.84
     Vacant 14,417 14,588 51.55 52.56
     Not a primary residence 4,580 4,377 17.36 17.07
     Not a dwelling unit 2,403 2,349 8.16 8.08
     All military personnel 289 356 1.08 1.39
     Other, ineligible 6,162 5,607 21.86 20.90
Eligible Cases 150,162 143,485 84.73 84.16
     Screening complete 136,349 130,605 90.72 90.72
          No one selected 80,557 74,310 53.14 51.04
          One selected 30,738 30,702 20.58 21.46
          Two selected 25,054 25,593 17.00 18.22
     Screening not complete 13,813 12,880 9.28 9.28
          No one home 3,031 2,446 2.02 1.68
          Respondent unavailable 411 280 0.26 0.18
          Physically or mentally incompetent 307 290 0.20 0.18
          Language barrier—Hispanic 66 42 0.05 0.03
          Language barrier—Other 461 450 0.35 0.39
          Refusal 8,556 8,414 5.86 5.98
          Other, access denied 471 923 0.30 0.81
          Other, eligible 12 12 0.01 0.01
          Resident < 1/2 of quarter 0 0 0.00 0.00
          Segment not accessible 0 0 0.00 0.00
          Screener not returned 15 16 0.01 0.01
          Fraudulent case 479 6 0.21 0.00
          Electronic screening problem 4 1 0.00 0.00
Source: SAMHSA, Office of Applied Studies, National Survey on Drug Use and Health, 2002 and 2003.


Table B.3 Weighted Percentages and Sample Sizes for 2002 and 2003 NSDUHs, by Final Interview Code
Final Interview Code Persons Aged 12 or Older Persons Aged 12 to 17 Persons Aged 18 or Older
Sample Size Weighted Percentage Sample Size Weighted Percentage Sample Size Weighted Percentage
2002 2003 2002 2003 2002 2003 2002 2003 2002 2003 2002 2003
Total 80,581 81,631 100.00 100.00 26,230 25,387 100.00 100.00 54,351 56,244 100.00 100.00
Interview Complete 68,126 67,784 78.56 77.39 23,659 22,696 89.99 89.57 44,467 45,088 77.20 75.96
No One at Dwelling Unit 1,359 1,242 1.81 1.60 182 158 0.70 0.62 1,177 1,084 1.94 1.71
Respondent Unavailable 1,893 1,809 2.71 2.44 329 310 1.20 1.25 1,564 1,499 2.89 2.58
Break-Off 48 33 0.10 0.09 9 2 0.04 0.01 39 31 0.11 0.10
Physically/Mentally Incompetent 692 755 1.75 1.82 161 150 0.57 0.60 531 605 1.89 1.96
Language Barrier - Hispanic 138 177 0.19 0.21 9 6 0.04 0.02 129 171 0.21 0.23
Language Barrier - Other 327 364 1.09 1.13 24 11 0.13 0.07 303 353 1.21 1.25
Refusal 6,276 7,433 12.73 14.10 464 486 1.81 1.74 5,812 6,947 14.03 15.56
Parental Refusal 1,307 1,476 0.55 0.61 1,307 1,476 5.15 5.81 0 0 0.00 0.00
Other 415 558 0.52 0.62 86 92 0.38 0.31 329 466 0.53 0.65
Source: SAMHSA, Office of Applied Studies, National Survey on Drug Use and Health, 2002 and 2003.


Table B.4 Response Rates and Sample Sizes for 2002 and 2003 NSDUHs, by Demographic Characteristics
  Selected Persons Completed Interviews Weighted Response Rate
2002 2003 2002 2003 2002 2003
Total 80,581 81,631 68,126 67,784 78.56% 77.39%
Age in Years
     12–17 26,230 25,387 23,659 22,696 89.99% 89.57%
     18–25 27,216 27,259 23,271 22,941 85.16% 83.47%
     26 or older 27,135 28,985 21,196 22,147 75.81% 74.63%
     Male 39,453 40,008 32,766 32,627 77.06% 75.72%
     Female 41,128 41,623 35,360 35,157 79.99% 78.96%
     Hispanic 10,250 10,753 8,692 8,985 80.93% 79.55%
     White 55,594 55,958 46,834 46,294 78.23% 77.21%
     Black 9,385 9,466 8,143 8,099 82.24% 80.12%
     All other races 5,352 5,454 4,457 4,406 70.50% 69.88%
     Northeast 16,490 16,736 13,706 13,655 75.57% 75.20%
     Midwest 22,588 22,665 19,180 18,993 80.01% 78.56%
     South 24,530 24,725 20,900 20,612 79.99% 78.38%
     West 16,973 17,505 14,340 14,524 77.33% 76.51%
County Type
     Large metropolitan 32,294 36,610 26,792 29,759 76.85% 75.49%
     Small metropolitan 28,121 27,661 23,944 23,349 79.50% 79.51%
     Nonmetropolitan 20,166 17,360 17,390 14,676 81.38% 79.72%
Source: SAMHSA, Office of Applied Studies, National Survey on Drug Use and Health, 2002 and 2003.


Table B.5 Number of Days Used Hallucinogens in the Past Year among Past Year Users and the Number of Days Used Hallucinogens in the Past Month among Past Month Users, with and without Follow-Up Questions, by Age Group: Percentages, 2002 and 2003
Frequency of Use Total AGE GROUP (Years)
12–17 18–25 26 or Older
2002 2003
with Follow-Up Questions
without Follow-Up Questions
2002 2003
with Follow-Up Questions
without Follow-Up Questions
2002 2003
with Follow-Up Questions
without Follow-Up Questions
2002 2003
with Follow-Up Questions
without Follow-Up Questions
Number of Days Used in Past Year among Past Year Users
     1–11 72.4 73.3 73.7 63.5 67.2 65.2 74.2 74.8 74.9 75.5 74.9 77.6
     12–49 18.4 17.0 16.0 22.0 19.4 20.6 17.7 16.4 16.2 17.1 16.4 12.1
     50–99 6.1 5.8 6.5 8.3 7.5 8.1 4.8 5.9 6.4 7.0 4.3 5.3
     100–299 3.1 3.4 3.4 6.0 5.1 5.3 3.2 2.5 2.0 0.4 * *
     300 or More 0.1 0.5a 0.5a 0.2 0.7 0.7 0.1 0.5 0.6a * 0.3 0.3
Number of Days Used in Past Month among Past Month Users
     1–2 81.1 75.0 74.0a 63.6 74.6a 75.1a 77.8 76.8 76.3 * * *
     3–5 13.3 14.6 15.2 21.9 9.8b 9.9b 17.4 15.3 15.9 * * *
     6–19 3.9 8.9a 9.2a 11.5 13.4 12.8 2.8 6.2a 6.0a * * *
     20 or More 1.7 1.5 1.5 2.9 2.3 2.2 2.1 1.7 1.8 * * *
*Low precision; no estimate reported.
a Difference between estimate and 2002 estimate is statistically significant at the 0.05 level.
b Difference between estimate and 2002 estimate is statistically significant at the 0.01 level.
Source: SAMHSA, Office of Applied Studies, National Survey on Drug Use and Health, 2002 and 2003.


Table B.6 Native Hawaiian (NH) and Other Pacific Islander (OPI) Respondents Aged 18 or Older: 2002 and 2003
Age 2002 2003
Unweighted Weighted Unweighted Weighted
n % n % n % n %
     18+ 61   144,415   67   140,171  
     18–25 25 40.98% 18,296 12.67% 31 46.27% 19,229 13.72%
     26–34 15 24.59% 44,960 31.13% 11 16.42% 36,362 25.94%
     35–49 13 21.31% 53,081 36.76% 20 29.85% 48,640 34.70%
     50+ 8 13.11% 28,079 19.44% 5 7.46% 35,940 25.64%
     18+ 129   587,033   101   274,735  
     18–25 83 64.34% 151,238 25.76% 77 76.24% 139,834 50.90%
     26–34 15 11.63% 63,498 10.82% 13 12.87% 51,502 18.75%
     35–49 21 16.28% 128,071 21.82% 8 7.92% 29,056 10.58%
     50+ 10 7.75% 244,226 41.60% 3 2.97% 54,343 19.78%
Source: SAMHSA, Office of Applied Studies, National Survey on Drug Use and Health, 2002 and 2003.


Table B.7 Estimates of Key Measures for Native Hawaiians (NH) and Other Pacific Islanders (OPI) in 2002 and 2003
Measure Age Group 2002 2003 2002 Versus 2003 (Based on ANALWT)
n Un-weighted Weighted n Un-weighted Weighted Difference of Mean SE (Difference) P value
Serious Mental Illness
Past Year 18+ 190 11.58% 5.44% 168 11.90% 12.42% -6.99% 4.01% 0.11
(18–25) 108 14.81% 14.27% 108 12.04% 17.58% -3.31% 7.11% 0.65
(26–34) 30 6.67% 4.31% 24 8.33% 12.25% -7.95% 10.38% 0.46
(35+) 52 7.69% 2.40% 36 13.89% 7.62% -5.22% 4.15% 0.23
Any Illicit Drug
Lifetime Overall 273 54.21% 44.21% 252 53.17% 51.01% -6.81% 8.37% 0.4318
(12–17) 83 38.55% 36.10% 84 35.71% 35.85% 0.24% 10.94% 0.9825
(18–25) 108 66.67% 65.12% 108 58.33% 51.72% 13.41% 8.42% 0.1373
(26–34) 30 60.00% 72.96% 24 70.83% 72.30% 0.65% 15.26% 0.9666
(35+) 52 50.00% 30.98% 36 66.67% 46.01% -15.03% 14.67% 0.3258
Past Year Overall 273 27.11% 17.02% 252 25.40% 18.53% -1.51% 5.28% 0.7805
(12–17) 83 26.51% 19.02% 84 25.00% 22.53% -3.51% 8.28% 0.6788
(18–25) 108 36.11% 35.08% 108 32.41% 31.40% 3.68% 8.84% 0.6847
(26–34) 30 20.00% 18.02% 24 12.50% 15.02% 2.99% 13.87% 0.8327
(35+) 52 13.46% 9.67% 36 13.89% 6.37% 3.30% 6.19% 0.6038
Past Month Overall 273 12.45% 7.89% 252 15.08% 11.10% -3.21% 3.63% 0.3938
(12–17) 83 14.46% 11.02% 84 16.67% 14.63% -3.61% 6.79% 0.6040
(18–25) 108 12.04% 9.55% 108 18.52% 16.93% -7.38% 6.17% 0.2552
(26–34) 30 13.33% 14.94% 24 4.17% 11.14% 3.80% 13.81% 0.7877
(35+) 52 9.62% 5.01% 36 8.33% 3.97% 1.04% 3.98% 0.7977
Lifetime Overall 273 45.05% 35.88% 252 46.83% 47.54% -11.66% 8.18% 0.1797
(12–17) 83 24.10% 17.63% 84 19.05% 17.22% 0.41% 7.77% 0.9590
(18–25) 108 61.11% 62.68% 108 57.41% 50.55% 12.13% 8.42% 0.1754
(26–34) 30 56.67% 71.97% 24 66.67% 70.97% 1.00% 15.34% 0.9493
(35+) 52 38.46% 20.52% 36 66.67% 46.01% -25.49% 13.94% 0.0925
Past Year Overall 273 17.58% 9.36% 252 19.05% 12.95% -3.59% 3.54% 0.3298
(12–17) 83 15.66% 7.41% 84 14.29% 13.11% -5.71% 6.73% 0.4132
(18–25) 108 26.85% 28.40% 108 27.78% 26.07% 2.32% 8.65% 0.7930
(26–34) 30 16.67% 17.03% 24 8.33% 3.89% 13.15% 9.37% 0.1859
(35+) 52 1.92% 0.76% 36 11.11% 5.20% -4.44% 3.16% 0.1856
Past Month Overall 273 8.79% 4.42% 252 10.71% 7.28% -2.87% 2.52% 0.2765
(12–17) 83 9.64% 5.87% 84 9.52% 10.62% -4.74% 6.39% 0.4725
(18–25) 108 11.11% 8.79% 108 14.81% 13.23% -4.44% 5.62% 0.4441
(26–34) 30 13.33% 14.94% 24 0.00% 0.00% 14.94% 9.05% 0.1249
(35+) 52 0.00% 0.00% 36 8.33% 3.97% -3.97% 2.74% 0.1738
Lifetime Overall 273 12.45% 12.61% 252 12.70% 18.57% -5.96% 5.83% 0.3266
(12–17) 83 4.82% 1.80% 84 3.57% 10.18% -8.38% 6.20% 0.2016
(18–25) 108 11.11% 9.77% 108 11.11% 12.99% -3.22% 5.59% 0.5758
(26–34) 30 30.00% 35.25% 24 12.50% 17.75% 17.50% 16.65% 0.3139
(35+) 52 17.31% 10.21% 36 38.89% 28.05% -17.84% 11.39% 0.1431
Past Year Overall 273 2.93% 2.39% 252 2.78% 4.25% -1.86% 2.66% 0.4965
(12–17) 83 3.61% 1.19% 84 2.38% 4.92% -3.73% 4.52% 0.4252
(18–25) 108 2.78% 3.48% 108 3.70% 4.63% -1.15% 3.43% 0.7434
(26–34) 30 6.67% 11.60% 24 4.17% 11.14% 0.46% 13.66% 0.9737
(35+) 52 0.00% 0.00% 36 0.00% 0.00% 0.00% 0.00% .
Past Month Overall 273 1.10% 0.61% 252 1.19% 3.50% -2.89% 2.26% 0.2250
(12–17) 83 1.20% 0.21% 84 1.19% 4.55% -4.34% 4.44% 0.3469
(18–25) 108 0.93% 1.50% 108 0.93% 2.49% -0.99% 2.86% 0.7349
(26–34) 30 3.33% 2.10% 24 4.17% 11.14% -9.04% 10.59% 0.4100
(35+) 52 0.00% 0.00% 36 0.00% 0.00% 0.00% 0.00% .
Any Hallucinogen
Lifetime Overall 273 13.19% 11.86% 252 14.29% 11.56% 0.30% 4.40% 0.9467
(12–17) 83 8.43% 3.81% 84 4.76% 5.22% -1.41% 4.88% 0.7777
(18–25) 108 15.74% 15.86% 108 21.30% 23.55% -7.68% 7.44% 0.3220
(26–34) 30 16.67% 21.77% 24 12.50% 4.51% 17.26% 10.68% 0.1320
(35+) 52 13.46% 9.45% 36 16.67% 6.75% 2.71% 6.40% 0.6800
Past Year Overall 273 3.30% 1.12% 252 3.57% 3.18% -2.06% 1.51% 0.1982
(12–17) 83 4.82% 2.87% 84 3.57% 5.19% -2.33% 4.82% 0.6375
(18–25) 108 3.70% 2.66% 108 5.56% 7.36% -4.70% 4.06% 0.2699
(26–34) 30 3.33% 2.10% 24 0.00% 0.00% 2.10% 2.06% 0.3285
(35+) 52 0.00% 0.00% 36 0.00% 0.00% 0.00% 0.00% .
Past Month Overall 273 0.00% 0.00% 252 0.79% 0.76% -0.76% 0.70% 0.3025
(12–17) 83 0.00% 0.00% 84 2.38% 4.92% -4.92% 4.44% 0.2898
(18–25) 108 0.00% 0.00% 108 0.00% 0.00% 0.00% 0.00% .
(26–34) 30 0.00% 0.00% 24 0.00% 0.00% 0.00% 0.00% .
(35+) 52 0.00% 0.00% 36 0.00% 0.00% 0.00% 0.00% .
Driving Under Influence of Any Illicit Drugs
Past Year Overall 273 5.49% 3.10% 252 11.51% 9.67% -6.57% 2.69% 0.0307*
(12–17) 83 3.61% 1.46% 84 7.14% 7.62% -6.16% 4.83% 0.2262
(18–25) 108 7.41% 6.35% 108 18.52% 21.39% -15.04% 6.43% 0.0375*
(26–34) 30 10.00% 5.44% 24 4.17% 2.44% 3.00% 2.82% 0.3077
(35+) 52 1.92% 1.61% 36 5.56% 3.28% -1.67% 2.90% 0.5774
* Difference significant at the p < 0.05 level.
Source: SAMHSA, Office of Applied Studies, National Survey on Drug Use and Health, 2002 and 2003.


End Notes

1 More details concerning random imputation can be found in Grau et al. (2003).

2 Substances include alcohol, cocaine, heroin, pain relievers, sedatives, marijuana, tranquilizers, stimulants, hallucinogens, and inhalants.

Go to the Table of Contents

This page was last updated on June 03, 2008 .