ECONOMETRICS

Econometrics

The application of economic theory, mathematics, and statistical inference to analyze economic phenomena.

Theoretical Econometrics

Focuses on developing methods to measure economic relationships in econometric models.

Economic Statistics

Concerned with collecting, processing, and presenting economic data using charts and tables.

Population Regression Function (PRF)

The set of conditional means of the dependent variable for fixed explanatory variable values. Also called the Conditional Expectation Function (CEF).

Adjusted R-squared

Adjusts the goodness of fit for the number of variables in the regression model. Helps prevent overfitting.

Specification Bias

Error that arises when a key variable is omitted from the regression model.

Coefficient of Partial Determination

Measures the variation in YYY explained by including an additional independent variable.

F-Test (ANOVA)

Evaluates the overall significance of a regression model.

Covariate

A control variable used in models that combine quantitative and qualitative regressors.

Chow Test

Tests for structural stability of regression models. Identifies if regressions differ but does not specify the cause.

Panel Data

Tracks the same units (e.g., a family or firm) over time.

Pooled Data

Combines cross-sectional and time-series data.

Linear Regression Models

Models linear in parameters; may not always be linear in regressand or regressors.

Dummy Variables in Regression

Represent structural changes. A 'slope drifter' indicates how the slope coefficient differs for a specific group.

Linear in Parameters

The relationship between the dependent and explanatory variables must be linear in the model's coefficients.

Independent Explanatory Variables (XXX) from Error Terms

The independent variables should not be correlated with the error term.

Zero Mean Value of the Error Term

The expected value of the error term for any XXX should be zero.

Homoscedasticity

The variance of the error term is constant across observations.

No Autocorrelation

Error terms should not be correlated across observations.

Sufficient Sample Size (n>kn > kn>k)

The number of observations must exceed the number of explanatory variables.

No Exact Collinearity Between XXX Variables

There should be no perfect linear relationship among explanatory variables.

Correct Functional Form (No Specification Bias)

The model must be correctly specified without missing variables or incorrect functional forms.

Test of Significance and Confidence Interval

Two complementary approaches for testing hypotheses.

Ordinary Least Squares (OLS)

Ensures BLUE (Best Linear Unbiased Estimator) properties.

Maximum Likelihood Method

Assumes normal distribution for parameter estimation.

Coincidental Regression

Same slope, same intercept.

Parallel Regression

Same slope, different intercept.

Concurrent Regression

Different slope, same intercept.

Dissimilar Regression

Different slope and intercept.

r^2 in two-variable regression

This indicates the goodness of fit of the model.

r^2 works the same way in multiple regression models.

The adjusted R^2 is used instead to account for additional variables.

Zero correlation implies independence.

Independence is stronger; zero correlation doesn't imply no relationship.

Correlation (r) is symmetrical.

r_{xy} = r_{yx}.

RRR implies cause-effect relationships in strong linear associations.

Correlation measures association, not causation.

Vagueness of Theory

When the theoretical basis for including a variable is unclear.

Unavailability of Data

Data for the variable may not be accessible or reliable.

Core vs. Peripheral Variables

Focus on the most relevant variables and exclude less critical ones.

Intrinsic Randomness in Human Behavior

Human actions may introduce randomness, making some variables unmeasurable.

Poor Proxy Variable

Inability to find a good substitute for an unobservable variable.

Principle of Parsimony

Keep the model as simple as possible to avoid overfitting.

Wrong Functional Form

Errors in specifying the relationship between variables.

Maximum Likelihood Estimation (MLE)

Derives parameter estimates assuming a normal distribution for the error term.