Overall Health Knowledge in Philippine: Multilevel Confirmatory Factor Analysis of Philippine National Demography Heath Survey 2022 Data

Objective: To confirm the underlying structure among the knowledge of communicable and noncommunicable diseases using multilevel confirmatory factor analysis and to determine if the structure differ according to gender or residence. Methods A secondary data analysis of Household Questionnaire from the 2022 PNDHS was conducted. PNDHS data is a two-level data; level-1 is within household (household questionnaire), and level-2 is between households (primary sampling unit (PSU)), so multilevel confirmatory factor analysis was implemented (two-level CFA and two-level variance CFA). Also, multigroup analysis was done to assess the structure difference between male/female and urban/rural. All computations were performed using STATA version 16.0. Results Knowledge of cancer, heart disease, diabetes, dengue fever, TB, and COVID − 19 found 96.7%, 94.9%, 97.8%, 98.4%, 96.7%, and 92.8%, respectively. According to two-level CFA, the coefficient loading of each item toward the two levels were all statistically significant (P < 0.001). Regarding two level variance CFA, the variance of level-1 is higher than the variance of the level-2 (13 and 6.7 respectively). The multigroup analysis discover that the model has measurement non-invariant (not equal) across gender and residence (P = 0.000, P = 0.000, respectively). Conclusion The level-1 has great effect compared to level-2 as the variance of level-1 is greater than level-2. The factor loading toward the two levels are different according to gender and residence, so more investigation is needed to determine the causes of this difference.