Careless responses in survey data and the validity of a screening instrument
Engelsk titel: Careless responses in survey data and the validity of a screening instrument
Läs online
Författare:
Roivainen, Eka
;
Veijola, Juha
;
Miettunen, Jouko
Email: eka.roivainen@verve.fi
Språk: Eng
Antal referenser: 31
Dokumenttyp:
Artikel
UI-nummer: 16045338
Sammanfattning
Careless responding was studied in the context of a large-scale survey-based study (Northern
Finland 1966 Birth Cohort; n = 5024) wherein the Chapman Infrequency Scale (CIS) was used as the
validity scale. Careless responding was infrequent in comparison to earlier studies that used
students as subjects. Logistic regression analyses showed that the odds ratio for careless
responding was 2.1 (95% confidence interval: 0.9-5.0) for respondents with a psychiatric diagnosis
relative to healthy respondents. Male sex and lack of secondary education were other factors that
correlated positively with CIS score. It is concluded that the common procedure of excluding careless
respondents from final samples may affect the results of survey-based studies that target psychiatric
patients. It is suggested that cutoff scores for exclusion should be flexible and chosen in line with the
demographic and health characteristics of the sample.