The possible association between Particulate Matter 2.5 (PM2.5) and lung cancer mortality can be partitioned into components, within similar observational units, and across different observational units. Within unit's covariates are very similar and across unit's covariates can be, and usually are, very different. Hence, there is a need to understand the possible effect of PM2.5 on mortality considering within and between observational units. To know the important covariates, our idea is to use Local Control Analysis (LCA) to estimate these two components and determine how much of the variation in estimates can be attributed. To determine if the treatment (PM2.5) effects vary significantly across clusters, we have calculated Local Treatment Difference (LTD) for LTD approach, slope, and intercept for Local Control Regression (LCR) approach. For that evaluation, we have used the method of Recursive Partitioning (RP). Moreover, the superiority of LCR approach over LTD approach has been discussed. The benefit of this study is twofold. First, we use a reliable strategy (LCA) for observational data. Second and importantly, most of the existing research explains the impact of air quality on lung cancer; however, there is subgroup heterogeneity in the effect of PM2.5 on lung cancer mortality. This study investigates this heterogeneity which is largely explained by different environmental quality factors such as sociodemographic, land and built.