When producing roller-cone drill bits, technological unity, being one of the most important means of ensuring product quality, is realized through the "end-to-end" application of statistical methods. This fact provides building a mathematical model, determining quantitative indicators of quality assurance, reasonable setting of standards for parameters and determining technological standards (tolerances). Systematic monitoring of these indicators in conditions of the current production will allow identification of quality reserves and getting objective data for making a decision on the revision, removal from production of a particular product as well as setting increased quality requirements. The problem of quality assurance of roller cone drill bits is acute for manufacturers of drilling tools and imposes serious requirements on systematic provision and quality control systems. To assess the quality of a products batch, the authors of the article propose to introduce a Kd coefficient, which takes into account both the average value of the quality indicator for a given range of values according to specifications, and the actual average distribution of quality indicators in the general population of products (in the batch). The task of the study is to find such error statistics ε(n) that would help determining the optimal sample size.