business analytics

profilebanafshehyen
SCM651HM4-v2.xlsx
Home>Business & Finance homework help>Operations Management homework help>business analytics

1 logit probit

is this all about who will get the loan or who will try for the loan?
what is closer to 0 ? .05 or .0005
intutive how does one differentiate between driving reason v/s another resulting value ( i.e age, mortgage and credit cards are more the reasons for which you WONT get loans not the reason NOT TO get loans)
non intutive
0 no loan
1 loan
Coefficient s:
Estimate Std. Error z value Pr(>|z|)
(Intercept) -11.869015 1.5252815 -7.782 7.17E-15 ***
Income 0.0569836 0.002269 25.113 < 2e-16 *** Income closer to 1 and positive, so higher the income more the chance of loan
Age -0.0680803 0.0573761 -1.187 0.235 Age closer to 0, the higher the age lesseser the chance of loan and being negative the higher the number more -ve it is
Mortgage 0.0005191 0.0005159 1.006 0.314 Mortgage closer to 0, the higher the mortgage lessesr the chance of loan
Family 0.6848979 0.0684911 10 < 2e-16 *** Family closer to 1, bigger the family the more the chance of loan
Experience 0.0781417 0.0570756 1.369 0.171 Experience closer to 1 and positive , higher the experience more the chance of loan
Education 1.6540532 0.1046104 15.812 < 2e-16 *** Education closer to 1, higher the education higher the chances of loan
CreditCard -0.0320181 0.1513677 -0.212 0.832 CreditCard closer to 0 , the higher the credit cards lower changes of loan, and being -ve the higher the number the more -ve its impact
Coefficient s:
Estimate Std. Error z value Pr(>|z|)
(Intercept) -5.9139053 0.7655803 -7.725 1.12E-14 ***
Income 0.0292527 0.0010749 27.214 < 2e-16 *** Income closer to 0, so higher the income lesser the chance or loan
Age -0.0366501 0.0292197 -1.254 0.21 Age closer to 0, the higher the age lessesr the chance of loan, being -ve the higher the value the more negative the impact
Mortgage 0.0003503 0.0002726 1.285 0.199 Mortgage closer to 0, the higher the mortgage lessesr the chance of loan
Family 0.3321379 0.0346591 9.583 < 2e-16 *** Family closer to 1, bigger the family the more the chance of loan
Experience 0.040391 0.029107 1.388 0.165 Experience closer to 0, higher the experience lesser the chance of loan
Education 0.7989227 0.0512123 15.6 < 2e-16 *** Education closer to 1, higher the education higher the chances of loan
CreditCard -0.0075377 0.0783267 -0.096 0.923 CreditCard closer to 0, the higher the credit cards lower changes of loan, and also being -ve the higher the value the more -ve the impact

Sheet2

intutive
non intutive
Logit : 0 no loan
Coefficients: 1 loan
Estimate Std. Error z value Pr(>|z|)
(Intercept) -9.41980941 0.45714157 -20.606 < 2e-16 ***
Age 0.00790014 0.00568947 1.389 0.16497 Age closer to 0 and positive, so higher the age lesser the chances of getting a personal loan
CCAvg 0.06116208 0.03310581 1.847 0.06468 . Credit card avarage closer to 1, the higher the credit card avarage more the chance of loan
CDAccount 3.25884502 0.26617751 12.243 < 2e-16 *** (didn’t picke these) CD account closer to 1, the higher the CD Account more the chance of personal loan
CreditCard -0.98956258 0.18303085 -5.407 0.0000000643 *** Number of Credit Cards closer to 1, but -ve, more the number of credit cards the lesser the changes of getitng personal loan
Family 0.84227277 0.06983048 12.062 < 2e-16 *** (didn’t picke these) Family closer to 1 and positive , bigger the family more the chance of personal loan
Income 0.04261172 0.00201485 21.149 < 2e-16 *** Income closer to 1, higher the income, higher the chances of personal loan
Mortgage 0.00006727 0.00048133 0.14 0.88885 Mortgage closer to 0 , the higher the mortgage lower changes of Personal loan
SecuritiesAccount -0.83243645 0.2534961 -3.284 0.00102 ** Securities account closer to 1 and negative, the higher the number the reduced chances of getting a peronal loan
probit:
Coefficients:
Estimate Std. Error z value Pr(>|z|)
(Intercept) -4.91528737 0.22786528 -21.571 < 2e-16 ***
Age 0.00349745 0.00299645 1.167 0.24313 Age closer to 0 and positive, so higher the age lesser the chances of getting a personal loan
CCAvg 0.04330281 0.0181783 2.382 0.017214 * Credit card avarage closer to 1, the higher the credit card avarage more the chance of loan
CDAccount 1.70007706 0.13661644 12.444 < 2e-16 *** CD account closer to 1, the higher the CD Account more the chance of personal loan
CreditCard -0.48247801 0.09313191 -5.181 0.000000221 *** Number of Credit Cards closer to 1, but -ve, more the number of credit cards the lesser the changes of getitng personal loan
Family 0.40058921 0.03538077 11.322 < 2e-16 *** Family closer to 1 and positive , bigger the family more the chance of personal loan
Income 0.02248318 0.00103494 21.724 < 2e-16 *** Income closer to 1, higher the income, higher the chances of personal loan
Mortgage 0.00007086 0.00026259 0.27 0.787284 Mortgage closer to 0 , the higher the mortgage lower changes of Personal loan
SecuritiesAccount -0.42960788 0.13052363 -3.291 0.000997 *** Securities account closer to 1 and negative, the higher the number the reduced chances of getting a peronal loan

vesion 1 intutive

Coefficients :
Estimate Std. Error z value Pr(>|z|) definition input output
(Intercept) -9.127745 0.341828 -26.7 <2e-16 *** (Intercept) always1 1 -9.127745
CreditCard 0.006744 0.136021 0.05 0.96 CreditCard number of cards 1 0.006744
Income 0.045151 0.001708 26.44 <2e-16 *** Income in thousand $ 200 9.0302
Family 0.843572 0.065089 12.96 <2e-16 *** Family number of family members 4 3.374288
---
sum 3.283487
exp(sum) 26.6686041769
probability exp(sum)/(1+exp(sum)) 96%

version 2 non intutive

sensitivity analysis
Coefficients : family members
Estimate Std. Error z value Pr(>|z|) definition input output 99% 1 2 3 4
(Intercept) -9.18953 0.3619 -25.393 < 2e-16 *** (Intercept) always1 1 -9.18953 income 10 0% 1% 1% 3%
CDAccount 2.8646 0.22651 12.647 < 2e-16 *** CDAccount no idea 1 2.8646 20 0% 1% 2% 5%
CreditCard -0.88961 0.17821 -4.992 0.000000598 *** CreditCard number of cards 1 -0.88961 30 1% 2% 3% 8%
Family 0.84717 0.06939 12.21 < 2e-16 *** Family number of family members 4 3.38868 40 1% 2% 5% 11%
Income 0.04461 0.00179 24.92 < 2e-16 *** Income income in 1000 $ 200 8.922 50 2% 4% 8% 17%
sum 5.09614 60 2% 6% 12% 24%
exp(sum) 163.3900030974 70 4% 8% 18% 33%
probability exp(sum)/(1+exp(sum)) 99% 80 6% 12% 25% 44%
90 9% 18% 34% 55%
100 13% 26% 45% 65%
110 19% 35% 56% 75%
120 27% 46% 66% 82%
130 36% 57% 76% 88%
140 47% 67% 83% 92%
150 58% 76% 88% 95%
160 68% 83% 92% 96%
170 77% 89% 95% 98%
180 84% 92% 97% 99%
190 89% 95% 98% 99%
200 93% 97% 99% 99%
210 95% 98% 99% 100%
220 97% 99% 99% 100%

probit - sensitive analysis

sensitivity analysis
Coefficient s: family members
Estimate Std. Error z value Pr(>|z|) definition input output 100% 1 2 3 4
(Intercept) -4.8230308 0.176111 -27.386 < 2e-16 *** (Intercept) always1 1 -4.8230308 10 0% 0% 1% 3%
CDAccount 1.5112701 0.1178771 12.821 < 2e-16 *** CDAccount no idea 1 1.5112701 20 0% 1% 2% 5%
CreditCard -0.434615 0.0908606 -4.783 0.00000172 *** CreditCard number of cards 1 -0.434615 30 0% 1% 3% 8%
Family 0.4034737 0.0351834 11.468 < 2e-16 *** Family number of family members 4 1.6138948 40 1% 2% 6% 12%
Income 0.0238448 0.0009083 26.251 < 2e-16 *** Income income in 1000 $ 200 4.76896 50 2% 4% 9% 17%
sum 2.6364791 60 3% 7% 13% 24%
70 5% 10% 19% 32%
probability 100% 80 8% 15% 26% 41%
90 12% 21% 35% 51%
100 17% 29% 44% 60%
110 24% 38% 53% 69%
120 32% 47% 63% 77%
130 40% 56% 71% 83%
140 50% 65% 79% 89%
150 59% 74% 85% 93%
160 68% 81% 90% 95%
170 76% 87% 94% 97%
180 83% 91% 96% 98%
190 88% 94% 98% 99%
200 92% 97% 99% 100%
210 95% 98% 99% 100%
220 97% 99% 100% 100%

moderating effects

Coefficients:
Estimate Std. Error z value Pr(>|z|) definition input output
(Intercept) -3.6146848 0.4796968 -7.535 4.87E-14 *** (Intercept) always1 1 -3.6146848
Family -1.4895358 0.2119153 -7.029 2.08E-12 *** Family number of family members 4 -5.9581432
Income 0.0001998 0.0038434 0.052 0.959 Income income in 1000 $ 200 0.03996
Family:Income 0.0202891 0.0018521 10.955 < 2e-16 *** Family:Income moderating effect 800 16.23128
sum 6.698412
exp(sum) 811.1167485149
probability exp(sum)/(1+exp(sum)) 100%