Abstract
Theists have claimed that the existence of God can be approached as a scientific hypothesis, and that His existence can be establised with a high degree of confirmation by observational evidence. The design argument proceeds from "the curious adapting of means to end" throughout all nature which resembles "the productions of human contrivance" to an "Author of Nature" who being "somewhat similar to the mind of men" is responsible for all these phenomena. Arguments by analogy, which are much more subtle and complex than simple analogies, occur also in certain areas of scientific research and have been classified as an important type of inductive argument. Their function is to evaluate causal hypotheses. So, they are best understood when subjected to analysis appropriate to arguments offered in support of causal hypotheses in science. Analysis of the inference by which scientific hypotheses are confirmed by observational evidence shows that its structure is given by Bayes's theorem. This schema could be used to turn the hypothetico-deductive method into a valid one by supplementing it by two kinds of probabilities. First, we must assess the probability that our observational results would obtain even if the hypothesis under consideration were false. The smaller the probability the stronger the degree of confirmation. This seems a natural interpretation of Popper's methodological requirement that scientific hypotheses must be audatious and take risks. We must also assess the prior probability of the hypothesis we are considering. This is a reasonable interpretation of Hanson's demand for plausibility arguments. The probabilities that enter into this Bayesian schema are interpreted as frequencies. This enables us to show the relevance of probabilities to prediction, theory and practical decision. On the Bayesian analysis, the design argument, far from supporting the existence of God, provides strong evidence to the contrary.