As with any scientific discipline, there is some nomenclature in econometrics that one should get familiar with before one appreciates applications to practical problems. This nomenclature mainly originates from statistics and mathematics, although there are also some concepts that are specific only to econometrics. Naturally, there are many ways to define concepts and to assign meaning to words. In this chapter I aim to provide some intuitively appealing meanings, and of course, they are far from precise. Again, this should not be seen as a problem, as the textbooks to be consulted by the reader at a later stage will be much more precise.

This chapter contains five sections. The first deals with probability densities, which are key concepts in statistics. In the second section, I will bring these concepts a few steps closer to econometrics by discussing the notions of conditional and unconditional expectations. An unconditional expectation would be that there is a 60 per cent chance that tomorrow's Amsterdam stock return is positive, which would be a sensible statement if this happens on average on sixty out of the 100 days. In contrast, a conditional expectation would be that tomorrow's Amsterdam stock market return will be positive with a 75 per cent chance, where today's closing return in New York was positive, too. In the third section, I will link the conditional expectation with samples and a data generating process, and treat parameter estimation and some of its related topics. I will also dedicate a few words to the degree of uncertainty in practice, thereby demonstrating that econometrics is not a discipline like physics or chemistry but that it comes much closer to psychology and sociology.