摘要:Background: Today, beside immunization coverage the age appropriate vaccination is another helpful index in public health. Evidences have shown that high immunization coverage rates do not necessarily imply age?appropriate vaccination status. The current study aimed to show the predictive factors of delayed vaccination by survival models. Methods: A historical cohort study conducted on 3610 children aged between 24 and 47 months who was living in the suburbs of five big cities of Iran. Time of delay in vaccination of first dose of mumps?measles?rubella (MMR) was calculated from date of vaccination minus age appropriate time according to vaccine card. Kaplan–Maier and Log rank tests were used for comparison the median of delay time. For controlling of confounding variables, multivariate cox model was used and hazard ratio with 95% confidence interval (95%) was reported. Results: The mean ± standard deviation and median interquartile range of delay time was 38.34 ± 73.1 and 16 (11–31) days in delayed group. The Log rank test showed that city of living, nationality, parents’ education, and birth order are related with prolonged delay time in MMR vaccination (P 0.05). Cox regression showed that city of living, mother education, and nationality are the most predictive factors of delay time duration in MMR vaccination. Conclusions: Delay time duration of vaccination increased by faring from capital to the east south. Moreover, concentration of foreign immigrants in big cities and low level of mother education are the most predictors of delayed vaccination. Educational intervention should focus on immigrants and mothers with low education level.