We examine the gender gap in school attendance of children aged 7-14 in India using National Family Health Survey Three (NFHS-3). We demonstrate that the choice of the sample examined has important implications for policy. A household decision model is used to motivate whether a child attends school and/or works. A bivariate probit model and Blinder-Oaxaca Decomposition are applied to see how changing sample groups and adding regressors impact results, and the implications this has upon gender gap and effectiveness of centralized policy as opposed to decentralized policy. Results show the gender gap is sensitive to the sub samples chosen (e.g. a particular state, a specific location (urban or rural), and gender) and to the choice of regressors, and that centralized policy may be less effective than decentralized policy. Parental education, wealth, location and gender are found to be the most volatile and influential variables in the household decision process.