A methodological comparison of survey techniques in obtaining self-reports of condom-related behaviors

Measuring Inappropriate Sexual Behavior Among University Students: Using the Randomized Response Technique to Enhance Self-Reporting

This article analyzes the efficacy of the randomized response technique (RRT) in achieving honest self-reporting about sexual behavior, compared with traditional survey techniques. A complex survey was conducted of 1,246 university students in Spain, who were asked sensitive quantitative questions about their sexual behavior, either via the RRT (n = 754) or by direct questioning (DQ) (n = 492). The RRT estimates of the number of times that the students were unable to restrain their inappropriate sexual behavior were significantly higher than the DQ estimates, among both male and female students. The results obtained suggest that the RRT method elicits higher values of self-stigmatizing reports of sexual experiences by increasing privacy in the data collection process. The RRT is shown to be a useful method for investigating sexual behavior.

Behavioral Risk Profile of Men Who Have Sex with Men in Beijing, China: Results from a Cross-sectional Survey with Randomized Response Techniques

Background:

Human immunodeficiency virus (HIV) is spreading rapidly among men who have sex with men (MSM) in China. Anonymous questionnaires or direct interviews have been frequently used to study their behavior. The aim of the study was to describe the behavioral risk profile of the MSM in Beijing using the randomized response techniques (RRTs).

Methods:

A cross-sectional survey of sexual behavior among a sample of MSM was conducted in two HIV counseling and testing clinics in Beijing. The survey was carried out with an anonymous questionnaire containing sensitive questions on sexual behavior. To obtain the honest responses to the sensitive questions, three distinctive RRTs were used in the questionnaire: (1) Additive randomized response model for quantitative questions, (2) randomized response model for multiple choice questions, and (3) Simmons randomized response model for binomial questions. Formulae for the point estimate, variance, and confidence interval (CI) were provided for each specific model.

Results:

Using RRTs in a sample of 659 participants, the mean age at first homosexual encounter was estimated to be 21.7 years (95% CI: 21.2–22.2), and each had sex with about three (2.9, 95% CI: 2.4–3.4) male partners on average in the past month. The estimated rate for consistent condom use was 56.4% (95% CI: 50.1–62.8%). In addition, condom was estimated to be used among 80.0% (95% CI: 74.1–85.9%) of the population during last anal sex with a male partner.

Conclusions:

Our study employed RRTs in a survey containing questions on sexual behavior among MSM, and the results showed that RRT might be a useful tool to obtain truthful feedback on sensitive information such as sexual behavior from the respondents, especially in traditional Chinese cultural settings.

Effect of perceived anonymity in assessments of eating disordered behaviors and attitudes

OBJECTIVE

The present study assessed the effect of perceived anonymity on endorsements of eating disordered behaviors and attitudes across multiple response formats.

METHOD

Four hundred sixty-nine undergraduate women responded using one of three questionnaire formats: a nominally anonymous true/false condition, an unmatched count condition, or a randomized-response condition. Both the unmatched count and randomized response conditions provided complete response anonymity.

RESULTS

Significantly different endorsement rates were found for the majority of items when comparing the standard and unmatched count conditions, whereas differences were found for fewer items when comparing the standard and randomized response conditions. Perceived anonymity significantly differed across conditions, with the highest and lowest perceptions of anonymity found for the unmatched count and standard conditions, respectively.

DISCUSSION

Perceived anonymity and response format affect endorsements of eating disordered behaviors and attitudes, highlighting the necessity of understanding factors that contribute to response bias.

Defining welfare spells. Coping with problems of survey responses and administrative data

The authors explore how to define a welfare spell and how well surveys measure welfare spells. By comparing survey and administrative data from the Work Pays Demonstration Project in California on the receipt of Aid to Families with Dependent Children (AFDC), they find that a substantial amount of administrative churning occurs in administrative data. Through a mixing model of several break lengths, the authors find that a single definition of a break in welfare is not applicable to all respondents. Additionally, it appears that there is substantial variation in the break lengths respondents utilize. Finally, the authors show that the complexity of defining an accurate break in spells creates difficulties for detecting biases in survey responses.

Validity of self-reported sexual behaviors in adolescent women using biomarker outcomes

OBJECTIVES

To determine the criterion-related validity of alternative approaches to the measurement of sexual intercourse using sexually transmitted diseases (STD) as a biomarker (the criterion).

STUDY DESIGN

Analyses are based on an urban sample of 255 adolescent women, 15 to 19 years of age, treated for genitourinary infections with Neisseria gonorrhoeae, Chlamydia trachomatis or Trichomonas vaginalis who returned 3 months later for reexamination. Subjects completed self-administered questionnaires at enrollment and at 3 months. Genitourinary cultures were obtained at enrollment, 2 to 4 weeks later at a test-of-treatment visit (TOT), and at 3 months.

RESULTS

Two hundred fourteen of the 255 adolescents also returned for a TOT culture; 186 of these 214 (73%) were free of infection 2 to 4 weeks after enrollment and 30% (56/186) acquired a subsequent STD by 3 months. The validity of questions about sexual behavior differed. No adolescent who denied interim intercourse by reporting "0" sexual partners or "0" coitions acquired an interval STD. Adolescents who denied regular intercourse (vaginal sex) or failed to indicate the number of interim coitions were at high risk for new STD-23% and 21%, respectively. A new measure of sexual intercourse using both the number of sexual partners and the number of coitions contained no missing data; adolescents classified as not having had interim sexual intercourse were free of infection at 3 months, whereas 32% of those who reported intercourse acquired an interim infection.

CONCLUSIONS

These data suggest that high-risk urban adolescent women can accurately report whether they have engaged in vaginal intercourse. The validity of the report appears sensitive to the wording and content of the questions.