DAT 610 Module 6
docx
keyboard_arrow_up
School
Southern New Hampshire University *
*We aren’t endorsed by this school
Course
610
Subject
Industrial Engineering
Date
Jan 9, 2024
Type
docx
Pages
6
Uploaded by ymedo521
DAT 610 Optimization & Risk Assessment
6-1 Module Six Exercise: Determine Key Risk Indicators
Southern New Hampshire University
Load data in R Studio
>iihs_data<-read.csv(“~/iihs_data.csv”)
>View(iihs_data)
Principal Component Analysis (PCA)
Describe how the results of the principal components analysis in R might be used to derive KRIs.
The principal components analysis in R studio might be used to derive KRIs as PCA is a component analysis method of extracting important variables from large sets of variables in a dataset. This method extracts low dimensional data sets of features from high dimensional data sets with the goal of capturing as much information as it can. PCA has a greater impact when dealing with 3 or more dimensional data sets.
>model<-princomp(~.,iihs_data[1:75,3:8], na.action=na.omit)
>summary(model)
>screeplot(model)
Your preview ends here
Eager to read complete document? Join bartleby learn and gain access to the full version
- Access to all documents
- Unlimited textbook solutions
- 24/7 expert homework help
Linear Regression
Describe how the results of linear regression analysis in R might be used to derive KRIs.
Simple linear regression predicts scores based on one variable from the scores of the second. The variables that we are predicting are called the criterion variable and is referred to as Y, the variables that we are basing our predictions on is called the predictor variable and will be referred to as X. In the event of one predictor variable its called simple regression, so in a simple
linear regression which is this section, the prediction of Y when plotted as a function of X forms a straight line.
Logistic Regression
Describe how the results of logistic regression analysis in R might be used to derive KRIs.
Logistical regression analysis can be used to derive KRIs as the model can analyze all the variables in the data. Logistics regression is a predictive modelling algorithm that comes into play when the Y variable is categorical. The goal of all this is to determine the math equation that can be used to predict probability of 1. Once the equation is established then it can be used to predict Y when only X is known. R studio makes it easier to utilize logistic regression model. The function used with logistic regression is called glm() and is different than what is used in linear regression. This helps identify the KRIs, when the model is visualized.
What does the “Estimate” column values for the loss categories signify in terms of value and sign for possible KRI assignment?
The “Estimate” column is loss within the data that is provided. This can also assign loss categories and create KRIs depending on losses.
Set of KRIs
The analysis from above stating to identify an appropriate set of KRIs for determining the lowest
total average insurance loss for the auto model. KRIs are an important tool when it comes to risk
management and can be used to monitor and lessen the risks and risk reporting. When KRIs are effective they should be measurable, predictable, and informational. Variables that have been identified are Collion, Property Damage, Bodily Injury, Medical payments and Personal Injury, each one of these are able to be measured and compared.
Your preview ends here
Eager to read complete document? Join bartleby learn and gain access to the full version
- Access to all documents
- Unlimited textbook solutions
- 24/7 expert homework help