Reliability of internet- versus telephone-administered questionnaires in a diverse sample of smokers

Abstract

Background: Smoking is more prevalent among lower-income individuals and certain racial/ethnic minorities. Addressing tobacco cessation among diverse populations is an urgent public health priority. As Internet use continues to rise among all segments of the US population, Web-based interventions have enormous potential to reach priority populations. Conducting Web-based smoking cessation research in priority populations requires psychometrically sound measurement instruments. To date, only one published study has examined the psychometric properties of Internet-administered measures commonly used in Web-based cessation trials. However, the sample was homogeneous with regard to race/ethnicity and income. We sought to replicate and extend these findings in a more diverse sample of smokers.

Objective: The aim was to examine the internal consistency and test-retest reliability of measures commonly used in smoking cessation clinical trials among racial/ethnic minorities and smokers with lower income.

Methods: Participants were enrolled in a randomized trial of the efficacy of an Internet smoking cessation program between June 2005 and September 2006. Following a baseline telephone assessment and randomization into the parent trial, participants were recruited to the reliability substudy. In phase I of recruitment, all participants in the parent trial were recruited to the substudy; in phase II, all consecutive racial/ethnic minority participants in the parent trial were recruited. Race and ethnicity were assessed via self-report using two standard items from the US Office of Management and Budget. An email was sent 2 days after the telephone assessment with a link to the Internet survey. Measures examined were quit methods, perceived stress, depression, social support, smoking temptations, alcohol use, perceived health status, and income. Internal consistency and test-retest reliability of Internet- versus telephone-administered measures were examined within four strata defined by race/ethnicity (non-Hispanic White, racial/ethnic minority) and annual household income (US $40,000 or less, more than $40,000).

Results: Of the 442 individuals invited, 319 participated (72% response rate): 52.4% were non-Hispanic White, 22.9% Black, 11.6% Hispanic, 7.8% Asian, 4.4% American Indian / Alaska Native, and 1% Native Hawaiian / Other Pacific Islander. About half (49.4%) reported an annual household income of US $40,000 or less, and 25.7% had a high school degree or less. Test-retest reliability was satisfactory to excellent across all strata for the majority of measures examined: 9 of 12 continuous variables had intraclass correlation coefficients > or = 0.70, and 10 of 18 binary variables and both ordinal variables had kappa coefficients > or = 0.70. Test-retest reliability of several quit methods varied across strata.

Conclusions: Race/ethnicity and income do not affect the psychometric properties of most Internet-administered measures examined. This knowledge adds to the confidence of conducting Web-based smoking cessation research and strengthens the scientific rigor of collecting information via the Internet on racial/ethnic minority and low-income subgroups.

Trial registration: clinicaltrials.gov NCT00282009 (parent trial).

Figure 1

Flowchart of enrollment in phase I and phase II