Analysis of questionnaires with embarrassing items

• Grant number: 06/05984-5
• Support Opportunities: Regular Research Grants
• Start date: January 01, 2007
• End date: December 31, 2008
• Field of knowledge: Physical Sciences and Mathematics - Probability and Statistics
• Principal Investigator: Mariana Cúri
• Grantee: Mariana Cúri
• Host Institution: Instituto de Ciências Matemáticas e de Computação (ICMC). Universidade de São Paulo (USP). São Carlos , SP, Brazil

Abstract

In psychiatric scientific research subjective characteristics of the individual such as depression, anxiety and phobias are often evaluated. Data are collected through questionnaires with items in an attempt to identify the presence of certain symptoms associated with some psychiatric disease. Some of these items may embarrass the respondents since they are related to questionable or even illegal social behaviors. An Item Response Theory model is proposed to differentiate the relationship between the probability of the presence of the symptom and the gravity of the disease of embarrassed and non-embarrassed individuals. Items that need this differentiation are called differential item functioning (DIF). Additionally, the model assumes that individuals embarrassed with one particular item could lie across other answers to omit a possible condition. The parameter estimators will be obtained through different methods (maximum likelihood, marginal Bayesian, marginal maximum likelihood and Monte Carlo Markov chain) and implemented in the software R. Simulations will be realized in order to study the properties of the estimators. An example with real data, collected to evaluate teenager depression, highlights the importance of this project. (AU)