In many social science researches, data are in the form of ordinal or ordered categorical data. The same data structure also arises in the analysis of repeated measurements, where the response of each experimental unit or subject is observed on multiple occasions to record the presence/absence level of a specific event. Responses of this type are known as multivariate or correlated categorical responses. The overall objective of this analysis was to measure the impact of the fortified biscuits on the nutritional status of pre-school aged children. Also to compare the nutritional status of the CHT pre-school aged children between intervention and comparison areas in terms of some measured nutritional indicators, such as, haemoglobin, height-for-age Z-scores, weight-for-age Z-scores, weight-for-height Z-scores, and body mass index. In this study, we have describe the application of probit Model for ordered categorical data. The Ordered Probit Model were considered for each outcome variable separately using computer package R. Only the children of the intervention area who participated in the baseline survey received the fortified biscuits for one year at the Para Centres and Children of the comparison areas did not receive any biscuits. A positive value of the change indicates the improvement of the nutritional status of the children over the study period. It shows that besides BMI all the outcome variables show the improvement of the children’s nutritional status over the 12 months period in both the areas. We found that fortified biscuit has significant effect only on improving the haemoglobin concentration level. Average haemoglobin level significantly improves in Chakma children and Marma children compared to the Bengali children. For Girls, mean change of height-for-age was significantly higher than that of boys. Also WID is an important factor for height-for-age. It shows that for children with Rich family background height-for-age improves more.