I need a linear regression analysis. Data must be extracted from publicly available databases. Use secondary data sources like as reports, government records, bank statements. Gather data from at least 35 banks from year 2016-2021 (or until 2020). I need all the data and calculations in one document. I also need precise references to the source from which the data was taken. The data can be analyzed with Excel or R and I would like to get an Excel or R document. In a linear regression analysis, there must be 1 dependent variable and 5 independent variables.
1. After checking that the residual errors are normal, we determine whether the dependent variable Y correlates with the regressors. If the regressors are weakly correlated with Y, do not include them in the model and replace them with others.
2. Draw a regression model and see what is the size of the square R. If the R squared is less than 0.20, the model is not suitable.
3. Check if the ANOVA p value is <0.05. If not, the model is incorrect.
4. Check whether the regressors are statistically significant.
5. Check for multicollinearity.
6. Check for exclusions.
7. Create a Normality Test Table.
8. Evaluate the influence of regressors on the model according to standardized beta coefficients.