Groundwater is a vital water resource which has a significant role in the irrigation and food industry. Drawdown is a change in groundwater level due to various causes, especially pumping from wells. Forecasting water level oscillations is an important necessity for planning the integrated management of any watershed basin. In the present study, the Theis equation was applied to stochastic analysis of groundwater flow in confined aquifers, through the Karhunen–Loeve expansion (KLE) method. The quantification of the uncertainty associated with the statistical moments of hydraulic head is the aim of this research. The KLE method takes two steps; first, aquifer transmissivity (T) as an input random field is decomposed in the form of a set of orthogonal Gaussian random expressions in which eigen structures related to the covariance function of T were obtained from the Fredholm equation. Then, the hydraulic head h(x,t) was expanded with polynomial terms in which some coefficients were computed from the governing equation. The statistical moments (i.e., mean values and variances) of h(x,t) were calculated and compared with Monte Carlo simulations (MCS) to validate the results.