Abstract Estimates of tractor repair and maintenance costs are important for farm machinery replacement decisions and for general farm budgeting. The aim of this study was to provide a statistical analysis for the repair and maintenance costs of tractors in order to present an appropriate mathematical model based on farm records and to compare the derived repair cost function with other estimates. The study was also regarded as an exploratory exercise to assess the feasibility and form of a more comprehensive study on the using of PM in agriculture projects. In this context a study was conducted to predict accumulated R&M costs of three typical tractors namely JD-3140, MF-285 and JD-3350 based on total working hours (X) by using Preventive Maintenance Program (PMP) in Kavardeh Agribusiness Company in Iran. To present the model, the stratified random sampling method on the basis of tractor age per year was used. The mean accumulated repair and maintenance costs and also the mean working hours (h/year) were calculated for per class separately. Calculated data was analyzed on the five models, linear, logarithmic, polynomial, power and exponential. Finally, it was found that power model gave better cost prediction with higher confidence and less variation than other models.

Keywords