Considering that BMI Z-score and psychological disorder can have a great impact on the results of the study, to ensure the uniform distribution of these variables in the groups, random allocation by Stratified Randomization and using the Permuted block randomization method with quadruple and binary blocks were used. Based on the sample size of 136 subjects, the quadruple block or double block were produced using the online site (www.sealedenvelope.com). Due to the double-blindness of the study, before starting the study, sets of packages containing Risperidone were prepared by someone other than the researcher, and the placebo was similar in appearance to Risperidone syrup.
Indeed, researchers in the evaluation phase, from the allocation of participants in each of the groups (intervention and control group) until the end of the intervention, were not know the groups whereby the patients were randomized. In order to apply concealment in the randomization process, unique codes were used on the medicine boxes, and the desired code is also generated by the software. With this method of concealment, none of the participants and researchers know which of the two groups received the Risperidone or placebo. These codes were inserted on the packages by the company receiving the supplements and placebos. Upon each person entering the study, based on the sequence generated, the drug package in which the code is recorded was assigned to the parents. Also, the random sequence generated during the study was unpredictable.