Better understanding and management of species populations requires information on habitat requirements. Modeling species presence-absence as a function of environmental variables is one approach to address this question. I used four modeling techniques: generalized linear models; support vector machines; random forests; and artificial neural networks. Principal component analysis was also implemented in an effort to reduce variable dimensionality. I collected data on site-level factors relating to physiography, climate, land-coverage type, and habitat range in an effort to understand Chukar habitat needs and distinguish which algorithms are best suited when limited to these data types. Results for this study indicate the random forests provide the most accurate predictions when comparing data to an external validation data set and principle component analysis did not increase model utility significantly.