Statistical inference is about drawing conclusions regarding the state of nature or society based on statistical data, statements equipped with appropriate measures of uncertainties. The Bayesian and the frequentist are the two main schools of statistical inference. They agree that a model specifying the distribution of the data is necessary to make inference regarding the question at hand. They disagree however on whether a prior distribution not based on the data is needed.
Tore Schweder, co-author of Confidence, Likelihood, Probability, examines whether or not prior distribution is needed if it is not based on data. Read his full post: On priors and posteriors in statistical inference, Bayesian always and everywhere?
For more information on Confidence, Likelihood, Probability visit our website.
Have your say!