Sample Size Guidelines for Logistic Regression from Observational Studies with Large Population: Emphasis on the Accuracy Between Statistics and Parameters Based on Real Life Clinical Data.

BACKGROUND: Different study designs and population size may require different sample size for logistic regression. This study aims to propose sample size guidelines for logistic regression based on observational studies with large population. METHODS: We estimated the minimum sample size required based on evaluation from real clinical data to evaluate the accuracy between statistics derived and the actual parameters. Nagelkerke r-squared and coefficients derived were compared with their respective parameters. RESULTS: With a minimum sample size of 500, results showed that the differences between the sample estimates and the population was sufficiently small. Based on an audit from a medium size of population, the differences were within ± 0.5 for coefficients and ± 0.02 for Nagelkerke r-squared. Meanwhile for large population, the differences are within ± 1.0 for coefficients and ± 0.02 for Nagelkerke r-squared. CONCLUSIONS: For observational studies with large population size that involve logistic regression in the analysis, taking a minimum sample size of 500 is necessary to derive the statistics that represent the parameters. The other recommended rules of thumb are EPV of 50 and formula; n = 100 + 50i where i refers to number of independent variables in the final model.

Validation of Malay Version of Body Self- Image Questionnaire-Short Form among Malaysian Young Adults.

BACKGROUND: Body self-image questionnaire-short form (BSIQ-SF) is developed to measure body image perceptions. Due to the cultural, language and environmental differences between western and eastern population, the validity and reliability need to be established. The aim of this study was to determine validity and reliability of Malay version BSIQ-SF. METHODS: A cross-sectional study involved web-based survey was employed. Exploratory factor analysis (EFA) and confirmatory factor analysis (CFA) was performed using SPSS version 22 and Mplus 7.3. RESULTS: There were 688 young adults in Malaysia with mean age of 23.67 (SD = 0.188) and mean body mass index (BMI) of 23.34 (SD = 0.27) participated in the study. Exploratory factor analysis performed and the number domains reduced from nine to four, namely 'Negative Affect', 'Attractiveness Evaluation', 'Physical Functionality Awareness' and 'Height Dissatisfaction'. CFA further confirmed the structure of the model with adequate goodness-of-fit values [CFI = 0.927, TLI = 0.913, SRMR = 0.075, RMSEA = 0.053 (95% CI: 0.047, 0.060)]. CONCLUSION: The revised 21-item of the Malay version BSIQ-SF was a valid and reliable instrument to measure body image perceptions among Malaysian young adults.