Editing Data: What Difference Do Consistency Checks Make?

Chronic Disease Epidemiology Section, Bureau of Epidemiology, Division of Disease Control, Florida Department of Health, Tallahassee 32399-1734, USA.
American Journal of Epidemiology (Impact Factor: 5.23). 06/2000; 151(9):921-6. DOI: 10.1093/oxfordjournals.aje.a010296
Source: PubMed


In 1998, the Florida Department of Health undertook a self-administered school-based survey of tobacco use, attitudes, and behaviors among nearly 23,000 public school students in grades 6-12. The survey design did not use skip patterns; therefore, students had multiple opportunities to contradict themselves. By using examples from the high school portion (grades 9-12) of the survey, the authors examined five possible approaches to handling data inconsistencies and the effect that each has on point estimates. Use of these approaches resulted in point estimates of current cigarette use ranging from 25.6% to 29.7%. The number of missing respondents varied from 33 (less than 1%) to 1,374 (13%), depending on which approach was used. After stratification by gender and race, the prevalence estimates changed marginally for girls but strikingly for boys. Non-Hispanic White students were substantially more likely than non-Hispanic Black students to report current cigarette use, but the magnitude of this difference varied significantly according to the analytical approach used. The approach used to check data consistency may influence point estimates and comparability with other studies. Therefore, this issue should be addressed when findings are reported.

Download full-text


Available from: Tammie M. Johnson,
  • Source
    • "Some evidence demonstrates that editing procedures may affect point estimates and cross-study comparability (Bauer & Johnson, 2000; Gfroerer, Wright, & Kopstein, 1997). In particular, Fendrich and Johnson (2001) stressed that study differences in editing protocols beg for increased methodological research into the validity of school-based drug surveys. "
    [Show abstract] [Hide abstract]
    ABSTRACT: This article compares prevalence estimates of substance use and delinquent behavior in Washington State, United States and Victoria, Australia, two states chosen for their different policy environments around problem behavior. Few comparisons of international differences on rates of multiple problem behavior exist, and most are based on methods that are not matched, raising the question of whether findings are based on methodological differences rather than actual rate differences. The International Youth Development Study used standardized methods to recruit and administer an adaptation of the Communities That Care Youth Survey to representative state samples of fifth-, seventh-, and ninth-grade students in each state. Rates of delinquent behavior were generally comparable. However, striking differences in substance use were noted, with Victoria students reporting higher rates of alcohol use, alcohol misuse, smoking, and inhalant use, whereas Washington State students reported higher rates of marijuana use. Implications for conducting international comparisons are discussed.
    Health Education & Behavior 09/2007; 34(4):634-50. DOI:10.1177/1090198106286272 · 2.23 Impact Factor
  • Source
    [Show abstract] [Hide abstract]
    ABSTRACT: Many states are developing tobacco use prevention and reduction programs, and current data on tobacco use behaviors and how these change over time in response to program activities are needed for program design, implementation, and evaluation. To assess changes in youth cigarette use and intentions following implementation of the Florida Pilot Program on Tobacco Control. Self-administered survey conducted prior to program implementation (1998), and 1 and 2 years (1999, 2000) later among a sample of Florida public middle school and high school students who were classified as never users, experimenters, current users, and former users of cigarettes based on survey responses. Changes in cigarette use status, intentions, and behaviors among students over a 2-year period. Surveys were completed by 22,540, 20,978, and 23, 745 students attending 255, 242, and 243 Florida public middle and high schools in 1998, 1999 and 2000, respectively. Response rates for the 3 survey years ranged from 80% to 82% and 72% to 82% for the middle school and high school surveys, respectively. After 2 years, current cigarette use dropped from 18.5% to 11.1% (P<.001) among middle school students and from 27.4% to 22.6% (P =.01) among high school students. Prevalence of never use increased from 56.4% to 69. 3% (P<.001) and from 31.9% to 43.1% (P =.001) among middle school and high school students, respectively. Prevalence of experimenting decreased among middle school and high school students from 21.4% to 16.2% (P<.001) and from 32.8% to 28.2% (P<.001), respectively. Among never users, the percentage of committed nonsmokers increased from 67.4% to 76.9% (P<.001) and from 73.7% to 79.3% (P<.001) among middle school and high school students, respectively. Among experimenters, the percentage of students who said they will not smoke again increased from 30.4% to 42.0% (P<.001) in middle school and from 44.4% to 51.0% (P<.001) in high school. Progress toward reduction of youth tobacco use was observed in each of the 2 years of Florida's Pilot Program on Tobacco Control. Our results suggest that a comprehensive statewide program can be effective in preventing and reducing youth tobacco use. JAMA. 2000;284:723-728
    JAMA The Journal of the American Medical Association 08/2000; 284(6):723-8. DOI:10.1001/jama.284.6.723 · 35.29 Impact Factor
  • [Show abstract] [Hide abstract]
    ABSTRACT: To identify characteristics associated with youth bidi use. The New Jersey Youth Tobacco Survey is a self-administered school-based survey that uses a 2-stage cluster sample design to obtain a representative statewide sample; 9589 students (grades 7-12) participated. Logistic regression was used to generate an adjusted odds ratio (OR) for current bidi use for each variable, controlling for gender, race, and school grade. Higher odds for current bidi use were noted for black and Hispanic students, users of other tobacco products, and students that perceived bidis as safer than cigarettes. These results suggest specific groups that should be targeted for intervention.
    American journal of health behavior 03/2004; 28(2):173-9. DOI:10.5993/AJHB.28.2.8 · 1.31 Impact Factor
Show more