Scribd
Upload
5 views

ITIS5433 2024 Assignment2

Uploaded by

cyindying
Copyright
© © All Rights Reserved
Available Formats
Download as DOCX, PDF, TXT or read online on Scribd
5 views

ITIS5433 2024 Assignment2

Uploaded by

cyindying
Copyright
© © All Rights Reserved
Available Formats
Download as DOCX, PDF, TXT or read online on Scribd
You are on page 1/ 1

ITIS5433 Assignment 2

The data set is taken from an actual nonprofit organization that was soliciting donations.

 A veteran’s organization seeks continued contributions from lapsing donors. Use lapsing donor
response from an earlier campaign to predict future lapsing donor response.

 Extracted from previous year's campaign

 Sample balances response/non-response rate

 Actual response rate approximately 5%

Instructions: Please submit via Brightspace the following files before November 8th th , 2022.

A copy of the answer sheet (you may use this one) with the following naming convention
YOURSTUDENT#BITIS5433_ASSIGN2_answers.doc

1. Please use SAS Visual Statistics


2. Please complete the analysis on the datasets named in the assignment

Assignment Guide

1. Open a new explore and visualize data tab in SAS Visual Statistics
2. Open the SVS083/pva.sasbhat data set. You can search PVA in Discover Information Assets.
Choose the data set that was created on September 30 2024 , 11:12 AM.
3. Target B will be target (dependent Variable). Do not include any of the variables with target in
their name as inputs.
4. Explore the variables for missing and skewed data. Do not transform binary data.
You will recall - As a rule of thumb: If skewness is less than -1 or greater than 1, the distribution is
highly skewed. If skewness is between -1 and -0.5 or between 0.5 and 1, the distribution is
moderately skewed. If skewness is between -0.5 and 0.5, the distribution is approximately symmetric
and therefore no transformation is required. A log transform will remedy the other skewed variables.
(see page 1-23 in course notes)

5. Make the appropriate transformations


6. Convert Target_Gift_FLAG to a category
7. Include all log transforms that you created and any variables that you didn’t transform as
Continuous
8. Add Gender, Cluster, and Home ownership as categorical inputs
9. Create a logistical regression model and answer the questions below. Use stepwise as a variable
selection, selection criteria=significance level and link function=logit Use informed missingness

Questions:

1. How many records are in the data set? (2 mark)


2. What variables have null values? (2 mark)
3. Display the misclassification Chart (2 mark)
4. What is the Parameter Estimates/equation (4 marks)
5. What is the R square of the model – and what does this metric mean (5 mark)

You might also like