Credit Analysis Project – Loan_Reason Analysis Issue

[norahx]

Up

0

Down

The chi-square test and Group factor analysis gave me conflicted results, have anyone had the same problem?

I. Chi-Square test –

I tried to see how does Loan_Reason impact on Bad rate. So I did chi-square test.

Null Hypothesis is DebtCon and HomeImp doesn’t have significant difference on Bad rate.

Result Pvalue=0.0001, Hypothesis is rejected.

So it shows DebtCon and HomeImp have difference on Bad rate.

And through comparing observed and expected table I found

Good Group(Bad=0) has more DebtCon percentage than HomeImp.

II. Group factor

When I took a look at the DebtCon Ratio, I found ,

In the Best group DebtCon percentage=62%,

In the worst group DebtCon percentage=68%.

It conflicts with the chi-square conclusion.

• This discussion was modified 3 years, 5 months ago by  norahx.
• This discussion was modified 3 years, 5 months ago by  norahx.
• This discussion was modified 3 years, 5 months ago by  norahx.
• This discussion was modified 3 years, 5 months ago by  norahx.

[Tundra.L]

Up

0

Down

My finding is: for both best and worst tier, 0 group’s debtCon/homelep ratio is always higher than 1 group, and the trends is almost the same cross those 10 tiers(decile)

[norahx]

Up

0

Down

Thanks for reply. Your observation is consistent with my chi-square test, which is Good group people tend to have more “debt consolidation “ Loan reason. Because both of them are relationships between “Loan reason “and “BAD“.. But when we observe the credit model, best group doesn’t seem to have more “DebtCondolidation” than worst group. That’s what I’m confused.