Description
The following can be considered as rough guidelines on the above structure: 1. Short introduction (2-3 paragraphs): what is the main research question, why we should care, is there a previous literatur e discussing your question. Focus on the dependent variable. 2. The model (1 page+): What is the regression model used to answer you research question? Write down the relevant equation and present the independent variables you are using. What are you expecti ng their impact to be? That is, will each of these independent variables have a positive or a negative impact on the dependent variable? Focus on the independent variables. 3. Data description (2-3 paragraphs): What is the source of the data you are using? Provide some discussion of the descriptive st atistics of the dependent and independent variables that you will be using to estimate your regression model. 4. Results (2-3 pages): you can divide the analysis in the following distinct parts o Misspecification Testing Estimate your regression model in the original form Perform testing for assumptions (R ESET, B-P and White’s tests) in the following order: If using RESET, functional form is found to be a problem, transform the model using logarithms, or by adding squared terms of some of your independent variables. 6 Estimate the “updated” model and check again for functional form using RESET. Regardless of whether you find that there is still a problem, move forward by checking the “updated” model for heteroskedasticity (B- P and White’s tests). If heteroskedasticity is not an i ssue, then you are ready to discuss your regression output results. If heteroskedasticity is found, then your re-estimate your “updated” model using Robust Standard Errors and proceed in discussing your regression output results now. o Discussion of Regression Output Overall significance (F-test in the regre ssion output checks if all the variables are insignificant). Goodness-of-fit: what is the adjusted R-squared found? Do you deem it to be large enough that you have explanatory power? Could you add more independent variables? Note that if you decide to ex plore the case of using more independent variables by including them in the “updated” model, please use the general-to-specific approach to evaluate these additions discussed in the next section. Individual Parameter Estimates: Statistical Interpretation If you found a variable to be significant, you proceed in stating so (mention the significance level). If you found a variable to be insignificant, you should report it oo. There is nothing wrong if you have found an independent variable insignificant. It means that based on the data set, you have found no evidence (statistical) of an effect of this independent variable on the dependent variable. It is also of interest to find out whether some independent variables have an y explanatory power or not. If you have two or more independen t variables that are insignificant, you may want to check of whether th ey are jointly insignificant. You can perform an F-test of this restriction. Individual Parameter Estimates: Economic Interpretation You can now interpret the parameter estimates in economic terms, i.e., what effects the independent variables have on the dependent variable. Do you think that the effects are large? Please do so for both statistica lly significant and insignificant parameter estimates. Interpret them accordingly. 5. Conclusion (2 paragraphs): Briefly report the model (in words) you wish to estimate and explain why you care. What are your main findings (independent variables that have some effects on the dependent variab les and magnitude of each effect)? How you could use these results for policy making (practical purposes)
