5 . 5 . Suppose we collect suspicion of elder financial exploitation data for a group of...
Fantastic news! We've Found the answer you've been seeking!
Question:
5. Suppose we collect suspicion of elder financial exploitation data for a group of bank clients.
The observed variables are X1= Age of client in years, X2= a binary variable as to whether
Power of Attorney has been granted to an agent (X2=1) or not (X2=0). X3= a binary
variable as to whether, as indicated by a proprietorial algorithm, abnormal transaction behavior
is evident on an account (X3=1) or not (X3=0). Outcome variable, Y, is equal to 1 if
analysts suspect an instance of elder financial abuse and Y =0 if not.
We tabulate results as follows:
Coefficient Std. error t−ratio p−value
alpha −0.700.064−10.970.0000
beta 10.620.2472.4850.0347
beta 2−0.090.141−0.6450.5181
beta 30.030.0083.5420.0003
a. Write down the general form of logistic regression and interpret the results for the
Age of Clients and Abnormal Transaction Behavior coefficients. (30 marks)
b. Estimate the probability that a 79 year old bank customer who has not granted Power
of Attorney to an agent and has suspicious transaction activity (i.e. as per
proprietorial algorithm), on her account, is suffering elder financial abuse via this
account. (20 marks)
c. Write comments on any reservations you have regarding the estimated probability in
Q.5(b)(20 marks)
d. Explain the main difference(s) between Linear Probability models and Logit/Probit
models.
Related Book For
Applied Regression Analysis and Other Multivariable Methods
ISBN: 978-1285051086
5th edition
Authors: David G. Kleinbaum, Lawrence L. Kupper, Azhar Nizam, Eli S. Rosenberg
Posted Date: