Quality Quandaries*: Time Series Model Selection and Parsimony.

The article considers the use of a model fitting criterion in analyzing parsimonious time-series data, as well as in the decision-making process. The authors selected specific models based on the properties of the sample autocorrelation function (ACF) and the sample partial autocorrelation function (PACF). They also assesses the impulse response function for each model by reviewing time-series theory. Analyses of Internet server users are provided to expound some of the issues related to selecting an adequate model.