#TITLE_ALTERNATIVE#
Survival analysis can be used for analysis of lifetime data such as the duration of loan data. Commonly, lifetime data can not be observed completely, later <br /> <br /> <br /> called censored data. In this thesis, we deal with determining risk of costumer who will be default by...
Saved in:
| Main Author: | |
|---|---|
| Format: | Final Project |
| Language: | Indonesia |
| Online Access: | https://digilib.itb.ac.id/gdl/view/15285 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| Institution: | Institut Teknologi Bandung |
| Language: | Indonesia |
| id |
id-itb.:15285 |
|---|---|
| spelling |
id-itb.:152852017-09-27T11:43:10Z#TITLE_ALTERNATIVE# PURNAMA (NIM : 10107005); Pembimbing : Khreshna I.A. Syuhada, M.Sc, Ph.D, DASEP Indonesia Final Project INSTITUT TEKNOLOGI BANDUNG https://digilib.itb.ac.id/gdl/view/15285 Survival analysis can be used for analysis of lifetime data such as the duration of loan data. Commonly, lifetime data can not be observed completely, later <br /> <br /> <br /> called censored data. In this thesis, we deal with determining risk of costumer who will be default by using Cox's proportional hazard model. This model is <br /> <br /> <br /> employed to analyze and determine survival of customers which are influenced by one or more causes of failure. To determine some unknown parameters of model, maximum likelihood approach is carried out. Specifically, we derive Breslow, Cox, and Efron likelihood functions. By using 95% confidence level, Cox's proportional hazard model for simulation data without the ties is influenced significantly by the age (-0.04175) and the company's omzet per month (0.0009). Meanwhile, for simulation data with ties, the model is influenced significantly by the age (-0.00874) and the ways of companies marketing their <br /> <br /> <br /> product (-0.53999). text |
| institution |
Institut Teknologi Bandung |
| building |
Institut Teknologi Bandung Library |
| continent |
Asia |
| country |
Indonesia Indonesia |
| content_provider |
Institut Teknologi Bandung |
| collection |
Digital ITB |
| language |
Indonesia |
| description |
Survival analysis can be used for analysis of lifetime data such as the duration of loan data. Commonly, lifetime data can not be observed completely, later <br />
<br />
<br />
called censored data. In this thesis, we deal with determining risk of costumer who will be default by using Cox's proportional hazard model. This model is <br />
<br />
<br />
employed to analyze and determine survival of customers which are influenced by one or more causes of failure. To determine some unknown parameters of model, maximum likelihood approach is carried out. Specifically, we derive Breslow, Cox, and Efron likelihood functions. By using 95% confidence level, Cox's proportional hazard model for simulation data without the ties is influenced significantly by the age (-0.04175) and the company's omzet per month (0.0009). Meanwhile, for simulation data with ties, the model is influenced significantly by the age (-0.00874) and the ways of companies marketing their <br />
<br />
<br />
product (-0.53999). |
| format |
Final Project |
| author |
PURNAMA (NIM : 10107005); Pembimbing : Khreshna I.A. Syuhada, M.Sc, Ph.D, DASEP |
| spellingShingle |
PURNAMA (NIM : 10107005); Pembimbing : Khreshna I.A. Syuhada, M.Sc, Ph.D, DASEP #TITLE_ALTERNATIVE# |
| author_facet |
PURNAMA (NIM : 10107005); Pembimbing : Khreshna I.A. Syuhada, M.Sc, Ph.D, DASEP |
| author_sort |
PURNAMA (NIM : 10107005); Pembimbing : Khreshna I.A. Syuhada, M.Sc, Ph.D, DASEP |
| title |
#TITLE_ALTERNATIVE# |
| title_short |
#TITLE_ALTERNATIVE# |
| title_full |
#TITLE_ALTERNATIVE# |
| title_fullStr |
#TITLE_ALTERNATIVE# |
| title_full_unstemmed |
#TITLE_ALTERNATIVE# |
| title_sort |
#title_alternative# |
| url |
https://digilib.itb.ac.id/gdl/view/15285 |
| _version_ |
1820737435933343744 |