Business Intelligence RapidMiner credit_training: https://docs.google.com/spread

Question

Business Intelligence

RapidMiner

credit_training: https://docs.google.com/spreadsheets/d/1y_FHbFDKozPtyD80QiC1cXCNLMtk4I8kT-yE6tTUW4s/edit?usp=sharing

credit_new_customers: https://docs.google.com/spreadsheets/d/11Tpej33rMHqCm8zMzOhoJFAIV3hbsPwzuJryA8Q9T8Y/edit?usp=sharing

You are an analyst for Bear Credit Union (BCU). You have been asked by your manager to create a model to assist with the decision to determine the creditworthiness of customers. You will use the data from 400 customers (CreditRisk_Training.csv) to build your model, then you will use your model to make a recommendation on 25 customers (CreditRisk_NewCustomers.csv) who have applied for various types of credit. The data for those 25 customers includes an ID number that won't be used in the model (Hint: set the role of the ID number to “ID") but will be used in the results when you report who should be granted a loan. team ("the team" from now on) has decades of banking experience but they know almost nothing about what you will be doing to conduct your analysis or how you will do it. You will prepare a report to enlighten them. Here is what your report should address

Explanation / Answer

1) We can test for correlation between "TB patients with known HIV status" and "HIV positive TB patients on ART".

2) We apply the correlation test of the variables mentioned in 1).

> tt <- read.csv("clipboard",sep=" ")
> tt <- na.omit(tt)
> dim(tt)
[1] 123   7
> names(tt)
[1] "Country"                           "Year"                           
[3] "TB.patients.with.known.HIV.status" "HIV.positive.TB.patients.on.ART"
[5] "Tested.TB.patients.HIV.positive"   "Population"                     
[7] "Estimated.Number.of.TBCases"    
> cor.test(tt[,3],tt[,4])

   Pearson's product-moment correlation

data: tt[, 3] and tt[, 4]
t = 0.85183, df = 121, p-value = 0.396
alternative hypothesis: true correlation is not equal to 0
95 percent confidence interval:
-0.1012094 0.2508144
sample estimates:
       cor
0.07720831

3) Since the p-value associated with the correlation test is large, the correlation of 0.0772 is significant between these two variable.

Related Questions

Navigate

• Browse (All)
• Browse B
• Subjects

---

---

Integrity-first tutoring: explanations and feedback only — we do not complete graded work. Learn more.