Because of the CPS panel design, a brief longitudinal cohort (overlap sample) was established, with baseline data obtained in May 2010 and follow-up data obtained in May 2011.
Technical Documentation
Data and SAS Read-in Files
SAS code for creating a permanent SAS dataset from the .dat and ASCII text files (called “SAS Read-In Files”) is available for the harmonized and single wave public use files, respectively. Each program reads all variables from the core and the supplement and creates a SAS dataset containing all of the variables.
Replicate Weights
Links to the TUS-CPS Replicate Weight Files, including self-response and nonresponse weights, are provided below.
2010-2011 Questionnaire
What Does the 2010-2011 TUS Data Say about Tobacco Use?
The data tables listed here provide examples of the type of information that researchers can obtain from the TUS. They are based on analyses of the 2010-11 TUS-CPS data files. All tables refer to self responses from self reports only. Note this is a change from previous Waves’ results for cigarette and other non-cigarette tobacco product use status. This is done for two reasons: first to be most consistent with how this data is used with other data that is collected only from self reports, and second because the proxy reports are most similar to self reports for middle-older ages and less so for younger adults (Soulakova et. al. 2009).
When using these tables, please note that:
- Several federal surveys are used to track tobacco usage in the US population, each with slightly different assessments. These tables are examples of analyses of the 2010-11 data files that are available from the Census Bureau.
- The table data are weighted for the sample design and for CPS Smoking Supplement self-response.
- Tabled values may not sum exactly to 100% due to rounding error.
- These tables contain simple parameter estimates (percentages and means), and measures of variance in the form of confidence intervals. These confidence intervals were estimated using replicate weights. Alternative estimates of variance and confidence intervals can be made for simple analyses using Attachment 16 of the 2010-11 Tobacco Use Supplement Files of the US Census Bureau Technical Documentation. Replicate weights necessary for more complex analysis such as regression or analysis of variance are available for download from the Census Website.
- Region:
- Northeast = Connecticut, Maine, Massachusetts, New Hampshire, New Jersey, New York, Pennsylvania, Rhode Island, Vermont;
- Midwest = Illinois, Indiana, Iowa, Kansas, Michigan, Minnesota, Missouri, Nebraska, North Dakota, Ohio, South Dakota, Wisconsin;
- South = Alabama, Arkansas, Delaware, District of Columbia, Florida, Georgia, Kentucky, Louisiana, Maryland, Mississippi, North Carolina, Oklahoma, South Carolina, Tennessee, Texas, Virginia, West Virginia; and
- West = Alaska, Arizona, California, Colorado, Hawaii, Idaho, Montana, Nevada, New Mexico, Oregon, Utah, Washington, Wyoming.