The fatigue failure of critical parts of tractors over the whole life cycle has received much attention in recent years. Load extrapolation is a crucial step in load spectrum compilation and can extrapolate the product's life cycle load based on limited load data measurements. The traditional time-domain extrapolation method is limited because it neglects the time interval between the load changes and the load reconstruction within the threshold range. To address this problem, a time-domain extrapolation method for tractor drive shaft load based on the Markov chain Monte Carlo-peak over threshold (MCMC-POT) model is proposed. Firstly, an improved time-domain load reconstruction method based on MCMC that can reproduce the load change interval based on the measured load change characteristics was proposed. Secondly, in the POT model extrapolation process, an improved threshold selection algorithm that is an optimisation of the traditional mean excess function (MEF) method was proposed. This method avoids the errors caused by subjective factors under the premise of ensuring the fitting accuracy. Finally, the dynamic torque spectrum was obtained by extrapolating the tractor drive shaft load data measured under ploughing conditions. Case analysis results showed that the method can obtain extrapolation models with high fitting accuracy. The power spectral density values of the dynamic torque spectrum before and after extrapolation were very consistent with the mean correlation coefficient of 0.909. The spectrum can effectively reproduce the time-frequency characteristics of the load. Furthermore, the precision of the load spectrum is improved. • A time-domain load reconstruction method based on Markov chain Monte Carlo model. • The threshold selection method based on peak over threshold model was improved. • A load extrapolation method that can retain complete time-frequency information. • Tractor transmission shaft testing was implemented under ploughing conditions. • The extrapolated load has the consistent frequency spectrum with the measured.