Econometrics with Eviews: Time Series, and Panel Data

Learn to download data from World development indicators for econometrics with EViews, selecting countries and variables like gdp and gdp per capita, and exporting as excel.

Learn how to download IMF data for one or multiple countries, select variables like net foreign direct investment as a percentage of GDP, and export datasets to Excel.

Learn to convert time series data into panel data by assembling country data (Pakistan, India, Bangladesh, Sri Lanka) for inflation, GDP, and FDI, using cross section IDs and start-end dates.

Explore the major data types in econometrics: qualitative and quantitative data, primary and secondary data, and time series, cross-sectional, and panel data.

Open EViews, create a new workfile, set the data form and dates, then import data from Excel by copying or by importing from a file.

Learn to create data manually in eviews by setting observations, defining series for GDP, inflation, and investment, entering data, and generating line and bar graphs.

Learn to test time series stationarity using the augmented Dickey-Fuller test in EViews, interpret p-values and test statistics, and use first differences to achieve stationarity.

Examine the stationarity of panel data using tests like adf and hariri, interpret p-values, and decide whether gdp, cpi, and fdi are stationary.

Explain unit root results in EViews using the adf test, determine stationary status (level, first or second difference) via p-values, and summarize in a table with decisions and significance stars.

Identify stationary versus non-stationary time series by examining constant mean, variance, and autocorrelation. Learn why stationarity matters, and apply ADF or Phillips Pearson tests to assess data.

Convert non-stationary data to stationary using the difference method in EViews, demonstrated with GDP. Verify stationarity via correlogram and autocorrelation checks, and note alternative options such as log transformations.

Learn to perform an ordinary least squares regression in EViews, using GDP as the dependent variable and external debt and foreign aid as predictors, and interpret coefficients and significance.

Learn how to compute descriptive statistics in EViews for panel data and time series, including mean, median, max, min, standard deviation, skewness, kurtosis, Jarque-Bera, and sums across 64 observations.

Derive the ols estimators for cross‑sectional data: beta naught and beta one from minimizing squared errors, giving beta one equals sum((yi−ybar)(xi−xbar))/sum((xi−xbar)^2) and beta naught equals ybar−beta one xbar, with example.

Learn the alternative method for deriving ols estimators by minimizing the sum of squared errors, and compute beta naught (intercept) and beta one (slope) from the regression.

Learn how f statistics in eviews test the overall significance of independent variables on the dependent variable, using f = msr/mse and the p-value threshold of 0.05.

Explore how r-squared measures the variation in the dependent variable explained by the independent variables, and how adjusted r-squared refines model fit and significance.

Learn to test the stability of econometric models using the Cusum square test in Eviews, to detect structural breaks, ensure constant variance, and validate forecasting reliability.

Learn how to import data into eviews, run an ols regression with gdp as the dependent variable, and obtain the residuals via the actual and fitted residual options.

Use the Ramsey reset test to diagnose whether the IV and DV relationship is linear, quadratic, or cubic. Interpret p-value at 0.05 to judge if the model is correctly specified.

the omitted variable test shows whether excluding relevant variables biases the dependent variable and lowers r-squared; if p<0.05, reject the null in eviews.

Learn to create lags in Eviews, including one lag and two lags, using generate and the command window, with GDP lag one and GDP lag two.

Learn to select the optimal lag in an EViews var by comparing criteria (LR, FPE, AIC, SC, HQ) and choosing the lag supported by the majority of tests.

Identify outliers using leverage and influence diagnostics in EViews after running a simple OLS, then transform data (growth rates or logs) to reduce bias for regression.

Learn how MIDAS enables mixed frequency data analysis by modeling low frequency dependent variables with high frequency regressors, preserving information for nowcasting and forecasting, with practical steps in EViews.

Explore the assumptions of the classical linear regression model for reliable OLS results, including linearity in parameters, variable x, x non-stochastic, homoscedasticity, zero conditional mean, exogeneity, and correct specification.

Apply the first OLS assumption: linearity in parameters enables estimation; nonlinear in parameters blocks estimation unless you transform to a linear form.

Explore the second OLS assumption: x-values are fixed and non-stochastic, allowing Y variation to reflect the drug's effect while X remains constant across samples.

Ensure variability in x values to properly estimate the x-y relationship in OLS, since constant x yields zero variance and prevents measuring the impact, as in education on income.

Explains homoscedasticity as the constant variance of the error term across all levels of the independent variable in the classical linear regression model, and contrasts it with heteroscedasticity.

Understand zero conditional mean of residuals in the classical linear regression model, with residuals random and uncorrelated with predictors, and identify violations like omitted variables, measurement error, and model specification.

Explain the no exogeneity assumption in classical linear regression, requiring zero covariance between x and the error term to keep ols unbiased and consistent; endogeneity from omitted variables biases results.

Understand why in ordinary least squares regression, the number of observations must exceed the number of parameters to ensure unique, reliable estimates and avoid underdetermined models.

No multicollinearity is a key assumption in linear regression; perfect multicollinearity prevents estimating individual effects, and detection uses correlation matrices and the variance inflation factor.

Discuss the no autocorrelation assumption in the classical linear regression model, explaining that correlated error terms bias standard errors and undermine t and f tests, widening confidence intervals.

Ensure regression models are correctly specified with the right functional form and relevant variables. Avoid irrelevant variables and measurement error to prevent bias, inefficiency, and incorrect conclusions.

Compare simple and multiple linear regression, where simple uses one independent variable and multiple uses two or more to explain income, with an intercept, coefficients, and an error term.

Derive the ordinary least squares estimator for a two-variable multiple regression with x1 and x2, using mean centering and normal equations to obtain beta1, beta2, and beta0.

Compute the multiple regression estimators beta hat one, beta hat two, and beta hat naught from a numerical example, using means, sums, and cross products with x1, x2, and y.

Examine hypothesis testing and inference in multiple regression with multiple independent variables. Learn to state hypotheses, check assumptions, and perform t-tests to assess each predictor's effect.

Use the Chow test in Eviews to detect structural breaks, test null versus alternative hypotheses, and assess model stability with stability and break-point tests.

Apply the Brij Bhushan test to identify peak and trough turning points in the business cycle—boom, recession, depression, and recovery—and guide policy decisions.

Explore identifying multiple structural breaks using the Bai-Perron test in EViews, by importing data, selecting GDP and inflation, and running stability diagnostics for break points.

Explore quantile regression in EViews for time series data and compare with OLS across 25th, median, and 75th percentiles. Interpret heterogeneous effects on GDP growth through distribution tails.

Explore ARIMAX, an extension of ARIMA with exogenous variables, including theory, assumptions, and practical interpretation for time series data, with notes on panel data limitations and exogeneity.

Explore the theoretical features of a good regression model—high r-squared values, significant f-stat and coefficients, lack of multicollinearity, normal residuals, homoscedasticity, no autocorrelation, theoretical grounding, and parsimony.

Demonstrates practical regression analysis in EViews, applying ordinary least squares, evaluating model fit with R-squared and F-statistics, and diagnosing residuals using Jarque-Bera, Breusch-Pagan, and serial correlation tests.

Learn the difference between homoscedastic and heteroscedastic data, and how constant residual variance underpins OLS estimation, identified via tests and graphs.

Detect heteroscedasticity using an informal graphical method by plotting squared residuals against predicted y, and confirm with the Park test by regressing ln(e^2) on ln(x) to test beta significance.

Learn practical methods to detect heteroscedasticity in regression using residual diagnostics and tests like Breusch-Pagan and White, interpret p-values, and assess data quality.

Explore the seven causes of heteroscedasticity, including changing relationship, outlier, incorrect model, omitted variable, measurement error, increasing variability over time, and aggregation of data. See explanations accompany each cause.

Explore how heteroscedasticity makes OLS estimates unbiased and consistent but inefficient due to larger variances, inflating standard errors and weakening t and F tests.

Explore remedial measures for heteroscedasticity in regression analysis, including weighted least squares, generalized least squares, variable transformations, and model specification to achieve homoskedasticity.

Identify heteroscedasticity using diagnostic tests, then remove it through log transformations, outlier handling, and dividing by the standard deviation to stabilize variance.