Skip to content

Commit

Permalink
change
Browse files Browse the repository at this point in the history
  • Loading branch information
Kelly064 committed Dec 4, 2023
1 parent 7869c5d commit 5974e0c
Show file tree
Hide file tree
Showing 2 changed files with 4 additions and 4 deletions.
Binary file modified Group7_Final_Report.pdf
Binary file not shown.
8 changes: 4 additions & 4 deletions Group7_Final_Report.qmd
Original file line number Diff line number Diff line change
Expand Up @@ -243,10 +243,6 @@ BB composite, which measures credit rating, holds a negative correlation with cr

Editda margin measures a company's operating profitability as a percentage of its revenue. The estimated coefficient suggests that as Editda margin increases by one unit, credit spread will decrease by 0.2333926 units. This inverse correlation is supported by its financial implications. A higher EBITDA margin indicates that a company is generating substantial earnings from its operations relative to its revenue, suggesting better financial health and efficiency. Thus companies with higher EBITDA margins are generally seen more capable of covering their interest expenses and other financial obligations. It can also increase investor confidence, which leads to lower yields demanded by investors. These all translate into lower credit spreads.

##### Interaction term

Interaction terms, (*shown in Appendix A*), though not statistically significant, do provide some potential practical significance as indicated by their results. Sector seems to have a large impact on the relationship between score and credit spread. This is shown by a negative estimated coefficient for some sectors (energy, finance, insurance), and positive for others. On the other hand, debt to assets seem to hold a positive relationship with credit spread regardless of the sectors. These inferences can be tested further with larger sample size and cleaner dataset.

```{r echo=FALSE, results='hide'}
credit_spread <- lm(credit_spread ~ Sector +
Duration +
Expand Down Expand Up @@ -282,6 +278,10 @@ Table 1: Credit Spread Selected Variable Linear Regression Model Output (Partial

*Please find full model output in Appendix A.*

##### Interaction term

Interaction terms, (*shown in Appendix A*), though not statistically significant, do provide some potential practical significance as indicated by their results. Sector seems to have a large impact on the relationship between score and credit spread. This is shown by a negative estimated coefficient for some sectors (energy, finance, insurance), and positive for others. On the other hand, debt to assets seem to hold a positive relationship with credit spread regardless of the sectors. These inferences can be tested further with larger sample size and cleaner dataset.

#### Model Assessment

The Selected variable model refers to the final model used to answer research question 1. The selected variable model uses Recursive Feature Elimination to make a reduced model from the Priori model. The selected variables in this model can be seen in *Table 8* in the *Appendix A* section.
Expand Down

0 comments on commit 5974e0c

Please sign in to comment.