1. Linear regression analysis
-Understand the basic concepts of linear regression, such as slope, intercept and error term.
-Learn how to fit linear regression models, including least square method and gradient descent method.
-Familiar with the interpretation of regression coefficients, such as positive slope, negative slope and multiple * * * linearity.
-Learn how to deal with the relationship between independent variables and dependent variables, for example, through scatter plots and correlation coefficient matrices.
2. Multiple linear regression analysis
-Understand the basic concepts of multivariate linear regression, such as multivariate linear regression equation and parameter estimation.
-Learn how to use maximum likelihood estimation and Bayesian estimation to solve parameters.
-Familiar with dimensionality reduction methods such as principal component analysis and partial least squares regression.
-Learn how to deal with multiple linear problems, such as ridge regression and lasso regression.
3. Logistic regression analysis
-Understand the basic concepts of logistic regression, such as Logit function and Probit function.
-Learn how to fit logistic regression models, including maximum likelihood estimation and Bayesian estimation.
-Familiar with the transformation between classified variables and continuous variables, such as logarithmic transformation and Box-Cox transformation.
-Learn how to deal with unbalanced data and multilinear problems.
4. Time series analysis
-Understand the basic concepts of time series analysis, such as stationarity, autocorrelation and intercept term.
-Learn how to fit time series models such as ARIMA model, exponential smoothing method and GARCH model.
-Familiar with stationarity test methods such as seasonal decomposition, trend decomposition and difference method.
-Learn how to deal with nonstationary data and multilinear problems.
5. Panel data analysis
-Understand the basic concepts of panel data analysis, such as fixed effect model and random effect model.
-Learn how to fit panel data models, including fixed effect model, random effect model and small sample panel data model.
—— Familiar with the methods of dealing with endogenous problems such as instrumental variable method and comprehensive control method.
-Learn how to deal with heterogeneity and multilingualism.
6. Quantile regression analysis
-Understand the basic concepts of quantile regression, such as quantile function and quantile regression equation.
-Learn how to use QuantileRegression for forecasting.
-Familiar with how to evaluate goodness of fit and other statistics of quantile regression model.
-Learn how to handle outliers and multiple * * * linear problems.
7. Application and practice of econometric model
-Understand the application of econometric models in practical problems, such as policy evaluation, industrial analysis and social investigation.
-Learn how to collect and organize data, and how to visualize and descriptive statistical analysis data.
-Familiar with how to use econometric software (such as Stata, R, Eviews, etc.). ) for data analysis and modeling.
-Learn how to write econometric reports, including results interpretation, model hypothesis testing and policy recommendations.
In the process of learning, you can refer to textbooks, handouts, cases and academic papers. At the same time, more hands-on practice and more discussion with people are also the key to improve the ability of econometrics.