Book contents
- Frontmatter
- Contents
- Preface
- Acknowledgments
- Symbols
- Acronyms
- 1 An introduction to empirical modeling
- 2 Probability theory: a modeling framework
- 3 The notion of a probability model
- 4 The notion of a random sample
- 5 Probabilistic concepts and real data
- 6 The notion of a non-random sample
- 7 Regression and related notions
- 8 Stochastic processes
- 9 Limit theorems
- 10 From probability theory to statistical inference*
- 11 An introduction to statistical inference
- 12 Estimation I: Properties of estimators
- 13 Estimation II: Methods of estimation
- 14 Hypothesis testing
- 15 Misspecification testing
- References
- Index
1 - An introduction to empirical modeling
Published online by Cambridge University Press: 06 July 2010
- Frontmatter
- Contents
- Preface
- Acknowledgments
- Symbols
- Acronyms
- 1 An introduction to empirical modeling
- 2 Probability theory: a modeling framework
- 3 The notion of a probability model
- 4 The notion of a random sample
- 5 Probabilistic concepts and real data
- 6 The notion of a non-random sample
- 7 Regression and related notions
- 8 Stochastic processes
- 9 Limit theorems
- 10 From probability theory to statistical inference*
- 11 An introduction to statistical inference
- 12 Estimation I: Properties of estimators
- 13 Estimation II: Methods of estimation
- 14 Hypothesis testing
- 15 Misspecification testing
- References
- Index
Summary
Introduction
In an attempt to give some idea of what empirical modeling is all about, we begin the discussion with an epigrammatic demarcation of its intended scope:
Empirical modeling is concerned with the parsimonious description of observable stochastic phenomena using statistical models.
The above demarcation is hardly illuminating because it involves the unknown terms stochastic phenomenon and statistical model which will be explained in what follows. At this stage, however, it suffices to note the following distinguishing features of empirical (as opposed to other forms of) modeling:
(a) the stochastic nature of the phenomena amenable to such modeling,
(b) the indispensability of the observed data, and
(c) the nature of the description in the form of a statistical model.
The primary objective of empirical modeling is to provide an adequate description of certain types of observable phenomena of interest in the form of stochastic mechanisms we call statistical models. A statistical model purports to capture the statistical systematic information (see sections 2−3), which is different from the theory information (see section 4). In contrast to a theory model, a statistical model is codified exclusively in terms of probabilistic concepts and it is descriptive and anti-realistic in nature (see chapter 10 for further discussion). The adequacy of the description is assessed by how well the postulated statistical model accounts for all the statistical systematic information in the data (see section 5). In section 6 we provide a preliminary discussion of certain important dimensions of the constituent element of empirical modeling, the observed data.
- Type
- Chapter
- Information
- Probability Theory and Statistical InferenceEconometric Modeling with Observational Data, pp. 1 - 30Publisher: Cambridge University PressPrint publication year: 1999