The specific problem of generalized linear regression utilizing a set of continuous explanatory variables is considered to model an exponential family response. An asymptotically biased principal component parameter estimation technique is developed and presented. This can be understood as an option to traditional maximum likelihood estimation for generalized linear regression. Both iterative and one-step principal component estimators are derived, compared, and shown to be particularly useful in the presence of an ill-conditioned information matrix. The bias, variance and mean squared error of these estimators are given. An example with Poisson response data demonstrates the approach.