This chapter presents an overview of what data analysis means. This overview is intentionally abstract with few details so that the "big picture" will emerge. Data represents the basic scores or observations, usually but not always numerical. Model is a more compact description or representation of the data. The method available to the data analyst for reducing error and improving models is straightforward and, in the abstract, the same across disciplines. Error can almost always be reduced by making the model's predictions conditional on additional information about each observation. This is equivalent to adding parameters to the model and using data to build the best estimates of those parameters. The number of observations in data imposes an inherent limit on the number of parameters that may be added to model. The estimation of parameters is sometimes referred to as "fitting" the model to the data.