Reliability and validity of knowledge, attitude, practice, and perception (KAP2) questionnaire on food poisoning and its prevention among consumers in Bangi and Kajang, Selangor, Malaysia.

Most food poisoning outbreaks are caused by consumers' poor knowledge, attitude, perception, and behaviour in relation to food safety. A valid and reliable tool is thus needed to measure these factors among the consumers. A total of 79 respondents participated in this pilot survey using convenient sampling, and participants self-completed the questionnaire given. Item analysis was conducted to determine the difficulty and discrimination indices of 40 items involved in knowledge construction. Construct validity and reliability were performed on 33 items which measured attitudes, preventive practices, and perceptions. Item analysis showed that more than 80% of respondents answered 19 items correctly. The discrimination index revealed that 16 items scored below 0.20. The Average Variance Extraction for all latent constructs, namely attitude, practice, and perception met acceptable threshold values of 0.527, 0.517, and 0.535, respectively. The Fornell-Larcker criterion suggested that three latent constructs were acceptable for discriminant validity. The internal consistency and reliability for all scaled items in each construct were good, with Cronbach's alpha values of more than 0.7 (0.820, 0.809, and 0.799 for attitude, practice, and perception, respectively). In conclusion, the present work indicated that the knowledge, attitude, practice, and perception (KAP2) questionnaire used could be a valid and reliable measure to evaluate consumer's knowledge, attitude, preventive practice, and perception on food poisoning. [ABSTRACT FROM AUTHOR]