Master of Science / Department of Agricultural Economics / Jeffrey M. Peterson / Understanding irrigation water demand is vital to policy decisions concerning water scarcity. This thesis evaluates irrigation water-use responses to changes in prices, while accounting for cross-sectional characteristics of irrigators’ resource settings. An irrigator’s profit-maximizing decision is modeled in two stages. In the first stage, he decides which crop to plant, and in the second stage he decides how much water to apply given the crop choice. This thesis employs an econometric modeling technique not previously used in the irrigation water demand literature, a multinomial logit selectivity model. This econometric technique allows the intensive (change in water use for each crop in the short run) and extensive (change in water use in the long run due to changes in crop-choice) margin effects to be computed in a simultaneous equation system. A multinomial logit selectivity model has applications to many resource issues in production agriculture where the two-stage decision process is common. The model is estimated from field-level data on water use and crop-choice for a 25-county region in western Kansas over the period 1991-2004. Water use was found to be highly inelastic to the price of natural gas, but becomes more elastic as the price increases. The intensive margin effect was significant for natural gas price. The extensive margin effect only comprised half the total effect under high natural gas prices and was negligible for low prices. However, the extensive margin effect under high natural gas prices declined over time due to more efficient irrigation systems and improved crop varieties. The intensive margin effect explained most of the water use response from changes in other variables, including corn price. An increase in corn price has a negligible extensive margin effect because corn is most often substituted with alfalfa, which has a similar water requirement. Inelastic demand implies that policies aiming to conserve the Ogallala Aquifer by increasing the price of water will not accomplish their purpose and will affect irrigators’ incomes. More effective policies would be voluntary or mandatory quantity restrictions. However, efficient restrictions would need to account for spatial variation in the rate of depletion and the remaining saturated thickness.