The aim of the study was to evaluate maximal isometric (dynamometer based {MVC-NORM} and isometric squat {MIS-NORM}) and sub-maximal EMG normalisation methods (60%-NORM, 70%-NORM, 80%-NORM) for dynamic back squat exercise (DSQ-EX). The absolute reliability (limits of agreement {LOA}, coefficient of variation {CV%}), relative reliability (intra-class correlation coefficient {ICC}) and sensitivity of each method was assessed. Ten resistance-trained males attended four sessions. Session one assessed maximum back squat strength (three repetition maximum {3RM}). In the remaining three sessions Vastus lateralis (VL) and Bicep femoris (BF) EMG were measured whilst participants completed normalisation tasks and DSQ-EX sets at 65%, 75%, 85% and 95% of 3RM. MIS-NORM produced lower intra-participant CV% compared to MVC-NORM. 80%-NORM produced lower intra-participant CV% than other sub-maximal methods for VL and BF during eccentric and concentric phases. 80%-NORM also produced narrower 95% LOA results than all other normalisation methods. The MIS-NORM method displayed higher ICC values for both muscles during eccentric and concentric phases. The 60%-NORM and 70%-NORM methods were the most sensitive for VL and BF during eccentric and concentric phases. Only normalisation methods for the concentric action of the VL enhanced sensitivity compared to unnormalised EMG. Overall, dynamic normalisation methods demonstrated better absolute reliability and sensitivity for reporting VL and BF EMG within the current study compared to maximal isometric methods.