<p>Risk difference is a measure used in clinical trials and epidemiological studies to quantify the absolute difference in the risk of an outcome between two groups. It is an easy way to compare the occurrence of an event (such as a disease, death, or adverse effect) between two groups, such as a treatment group and a control group. It is helpful for public health decisions as it shows the actual benefit or harm. Estimating risk difference is widely used to quantify the efficacy of potential treatments. While prior studies have primarily employed nonparametric test procedures to compare risk differences across groups, this study introduces two likelihood-based test methods for evaluating the homogeneity of risk differences under a binomial model. Specifically, we propose a likelihood ratio test and Neyman’s (C(<InlineEquation ID="IEq1"> <EquationSource Format="TEX">\(\alpha \)</EquationSource> <EquationSource Format="MATHML"><math> <mi>α</mi> </math></EquationSource> </InlineEquation>)) test. The purpose of this study is manifold as (i) develop alternative approaches to compare risk differences across groups, (ii) compare the newly proposed and existing methods based on Type I error and power via simulation and lastly (iii) studying the applicability of the proposed methods using observational data. Our proposed methods demonstrate strong performance in maintaining Type I error rates near nominal levels and achieving high statistical power. Extensive Monte Carlo simulation has been performed to show the efficacy of our two proposed methods. Finally, we present two real-world applications to highlight the practical utility of the proposed methods.</p>