ekonometrics.com

Basic Symbols

1. Y: Dependent variable
   • Meaning: The variable being predicted or explained.
2. X: Independent variable
   • Meaning: The variable used to predict or explain the dependent variable.
3. β: Coefficient
   • Meaning: Measures the change in the dependent variable for a one-unit change in the independent variable.
4. α: Intercept
   • Meaning: The expected value of the dependent variable when all independent variables are zero.
5. ϵ: Error term
   • Meaning: Captures the effect of all other variables not included in the model.

Model Specification

1. Y=α+βX+ϵY : Simple linear regression model
   • Meaning: Predicting YYY using XXX.
2. Yi=α+βXi+ϵi​: Index notation for the ith observation
   • Meaning: Regression model for the ith observation.
3. Y: Predicted value of the dependent variable
   • Meaning: The estimated value of YYY from the regression model.
4. β^​: Estimated coefficient
   • Meaning: The estimated value of the coefficient β\betaβ.

Statistical Concepts

1. E(Y): Expected value of Y
   • Meaning: The mean value of Y.
2. Var(Y): Variance of Y
   • Meaning: The dispersion of Y around its mean.
3. Cov(X,Y): Covariance between X and Y
   • Meaning: The degree to which X and Y vary together.
4. ρ(X,Y): Correlation coefficient between X and Y
   • Meaning: The strength and direction of the linear relationship between X and Y.

Econometrics Symbols in Hypothesis Testing

1. H0​: Null hypothesis
   • Meaning: A statement that there is no effect or no difference.
2. H1: Alternative hypothesis
   • Meaning: A statement that there is an effect or a difference.
3. t-statistic: Test statistic
   • Meaning: Used to test hypotheses about coefficients.
4. p-value: Probability value
   • Meaning: The probability of observing the data if the null hypothesis is true.
5. F-statistic: Test statistic
   • Meaning: Used to test hypotheses about multiple coefficients simultaneously.

Matrices in Multiple Regression

1. X: Matrix of independent variables
   • Meaning: Contains all independent variables for multiple regression.
2. Y: Vector of dependent variable
   • Meaning: Contains all values of the dependent variable.
3. β: Vector of coefficients
   • Meaning: Contains all coefficients for multiple regression.
4. e: Vector of error terms
   • Meaning: Contains all error terms.
5. X: Transpose of matrix X
   • Meaning: The transpose of the matrix of independent variables.

Generalized Least Squares (GLS)

1. Ω: Variance-covariance matrix of the error terms
   • Meaning: The covariance structure of the error terms.
2. βGLS​: Coefficients estimated using GLS
   • Meaning: The coefficients estimated using the Generalized Least Squares method.

Maximum Likelihood Estimation (MLE)

1. L(θ): Likelihood function
   • Meaning: A function of the parameters given the data.
2. ln⁡L(θ): Log-likelihood function
   • Meaning: The natural logarithm of the likelihood function.
3. θ^: Maximum likelihood estimator
   • Meaning: The value of the parameter that maximizes the likelihood function.

Time Series Analysis

1. yt​: Value of the time series at time t
   • Meaning: The value of the variable at time t.
2. ϕ: Coefficient in an autoregressive model
   • Meaning: The coefficient of the lagged value of the variable.
3. θ: Coefficient in a moving average model
   • Meaning: The coefficient of the lagged error term.
4. Δyt​: First difference of the time series yty_tyt​
   • Meaning: The change in the variable from time t−1 to time t.
5. ρ: Autocorrelation coefficient
   • Meaning: Measures the correlation of the time series with its past values.

Econometrics Symbols in More Advanced Concepts

1. σ2: Variance of the error term
   • Meaning: The variance of the errors in the regression model.
2. R2: Coefficient of determination
   • Meaning: The proportion of variance in the dependent variable explained by the independent variables.
3. Yˉ: Mean of the dependent variable
   • Meaning: The average value of the dependent variable.
4. ϵ^: Residual
   • Meaning: The difference between the observed value and the predicted value.

Dummy Variables

1. D: Dummy variable
   • Meaning: A binary variable that takes the value 0 or 1.
2. δ: Coefficient for the dummy variable
   • Meaning: The change in the dependent variable when the dummy variable is 1.

Interaction Terms

1. X1​×X2​: Interaction term
   • Meaning: The product of two independent variables, capturing their joint effect.
2. β12: Coefficient for the interaction term
   • Meaning: The change in the dependent variable due to the interaction between X1X_1X1​ and X2X_2X2​.

Panel Data

1. i: Index for cross-sectional units
   • Meaning: Identifies individual units (e.g., individuals, firms).
2. t: Index for time periods
   • Meaning: Identifies different time periods.
3. Yit​: Value of the dependent variable for unit i at time t
   • Meaning: The value of the dependent variable for the ith unit at time t.
4. Xit​: Value of the independent variable for unit i at time t
   • Meaning: The value of the independent variable for the ith unit at time t.

Instrumental Variables (IV)

1. Z: Instrumental variable
   • Meaning: A variable that is correlated with the independent variable but uncorrelated with the error term.
2. X^: Predicted value of the endogenous variable using the instrument
   • Meaning: The fitted value of the endogenous variable from the first-stage regression.
3. βIV​: IV estimate of the coefficient
   • Meaning: The coefficient estimated using the instrumental variables method.

Heteroskedasticity and Autocorrelation

1. σi2: Variance of the error term for the ith observation
   • Meaning: Indicates heteroskedasticity when it varies across observations.
2. ρ: Autocorrelation coefficient
   • Meaning: Measures the correlation of the error terms across different observations.

Generalized Method of Moments (GMM)

1. g(θ): Moment condition
   • Meaning: A function of the parameters that equals zero at the true parameter values.
2. W: Weighting matrix
   • Meaning: A matrix used to weight the moment conditions in GMM estimation.
3. θ^GMM​: GMM estimator
   • Meaning: The parameter value that satisfies the moment conditions weighted by W.

Logit and Probit Models

1. Λ(⋅): Logistic function
   • Meaning: Used in logit models to transform the linear combination of predictors to probabilities.
2. Φ(⋅): Cumulative distribution function of the standard normal distribution
   • Meaning: Used in probit models to transform the linear combination of predictors to probabilities.
3. βlogit: Coefficient in a logit model
   • Meaning: The effect of the independent variable on the log-odds of the dependent variable.
4. βprobit​: Coefficient in a probit model
   • Meaning: The effect of the independent variable on the latent variable underlying the probit model.

Model Selection Criteria

1. AIC: Akaike Information Criterion
   • Meaning: A measure used to compare models, penalizing for the number of parameters.
2. BIC: Bayesian Information Criterion
   • Meaning: A measure used to compare models, with a stronger penalty for the number of parameters than AIC.
3. log⁡L: Log-likelihood value
   • Meaning: The logarithm of the likelihood function, used in model comparison.

Multicollinearity

1. VIF: Variance Inflation Factor
   • Meaning: A measure of multicollinearity in a regression model, indicating how much the variance of a coefficient is inflated due to collinearity.

Time Series Concepts

1. ACF: Autocorrelation function
   • Meaning: Measures the correlation between a time series and its lagged values.
2. PACF: Partial autocorrelation function
   • Meaning: Measures the correlation between a time series and its lagged values, controlling for the values of the time series at all shorter lags.
3. AR(p): Autoregressive model of order p
   • Meaning: A model where the current value of the series is based on the past p values.
4. MA(q): Moving average model of order q
   • Meaning: A model where the current value of the series is based on past error terms.
5. ARMA(p,q): Autoregressive moving average model
   • Meaning: Combines AR(p) and MA(q) models.
6. ARIMA(p,d,q): Autoregressive integrated moving average model
   • Meaning: Extends ARMA by including differencing ddd to make the series stationary.

Cointegration

1. βc​: Cointegration vector
   • Meaning: Indicates a long-term equilibrium relationship between time series.
2. ξt: Error correction term
   • Meaning: The term that corrects deviations from the long-term equilibrium.

Forecasting

1. Y^t+h​: Forecasted value of Y at time t+h
   • Meaning: The predicted value of Y h periods ahead.
2. RMSE: Root Mean Squared Error
   • Meaning: A measure of the accuracy of a forecasting model.

Causality Testing

1. γ: Coefficient in Granger causality test
   • Meaning: Measures whether one time series can predict another.

If you want to learn econometrics basics with fun and from noble prize winner MIT Economist Joshua Angrist then here is a free course.

And if you don’t know where to start learning econometrics then here is a complete road map to study econometrics.