Mathematical programming methods are widely used for modelling farmers' decision-making and for economic analysis in agriculture. In this study, a MOTAD risk-programming model is applied to study the effects of risk on cropping pattern and farmers' income in Ramjerd and Sarpaniran districts near Marvdasht in the Fars Province of Iran. Primary data from 194 farmers randomly selected from 31 villages are used in this study. The results indicate that variability of crops gross margins or outcomes has a significant effect on cropping pattern but it varies over different farmers and regions with various conditions. Moreover, it was found that farm plans with more number of crops have a lower return but high degree of certainty. Based on this research, farmers' risk attitudes and expectations and using more sophisticated methods for generating time series data with dependency are some important issues which should be considered in the future studies.