ACG 6455 Final

library(tidyverse)
Final <- read_csv("Desktop/Final.csv")

C<-Final$CIK
SC<-Final$SIC
SQRTL<-sqrt(Final$LAG)
B4<-factor(Final$BIG4)
BZ<-factor(Final$BUSY)
FGC<-factor(Final$GC)
LOS<-factor(Final$LOSS)
S<-Final$SALES
I<-Final$NI
A<-Final$TA
LS<-log(S)
LA<-log(A)
STO<-S/A
ROS<-I/S

hist(SQRTL)

Question A

resultA<-lm(SQRTL~LA+B4+BZ+FGC+LOS+STO+ROS)
summary(resultA)

Call:
lm(formula = SQRTL ~ LA + B4 + BZ + FGC + LOS + STO + ROS)

Residuals:
    Min      1Q  Median      3Q     Max 
-5.1563 -0.4468 -0.0396  0.3994  5.7533 

Coefficients:
             Estimate Std. Error t value Pr(>|t|)    
(Intercept) 11.548464   0.141469  81.633  < 2e-16 ***
LA          -0.165475   0.007069 -23.409  < 2e-16 ***
B41         -0.351120   0.030441 -11.534  < 2e-16 ***
BZ1          0.104631   0.029802   3.511 0.000451 ***
FGC1         0.450492   0.077374   5.822 6.25e-09 ***
LOS1         0.224634   0.029912   7.510 7.20e-14 ***
STO         -0.007488   0.003112  -2.406 0.016168 *  
ROS          0.001011   0.000848   1.192 0.233299    
---
Signif. codes:  0 ‘***’ 0.001 ‘**’ 0.01 ‘*’ 0.05 ‘.’ 0.1 ‘ ’ 1

Residual standard error: 0.7914 on 4155 degrees of freedom
Multiple R-squared:  0.3126,    Adjusted R-squared:  0.3114 
F-statistic: 269.9 on 7 and 4155 DF,  p-value: < 2.2e-16

cINTa=11.548464
cLAa=-0.165475
cB4a=-0.351120
cBZa=0.104631
cFGCa=0.450492
cLOSa=0.224634
cSTOa=-0.007488
cROSa=0.001011
nLA=log(800000000)
nB4=1
nBZ=1
nFGC=0
nLOS=0
nSTO=700000000/800000000
nROS=28000000/800000000
SOLUTIONa<-(cINTa+cLAa*nLA+cB4a*nB4+cBZa*nBZ+cFGCa*nFGC+cLOSa*nLOS+cSTOa*nSTO+cROSa*nROS)^2
print(SOLUTIONa)

[1] 62.46058

Question B

FINALB<-subset(Final,SIC>2000 & SIC<3999)
bC<-FINALB$CIK
bSC<-FINALB$SIC
bSQRTL<-sqrt(FINALB$LAG)
bB4<-factor(FINALB$BIG4)
bBZ<-factor(FINALB$BUSY)
bFGC<-factor(FINALB$GC)
bLOS<-factor(FINALB$LOSS)
bS<-FINALB$SALES
bI<-FINALB$NI
bA<-FINALB$TA
bLS<-log(bS)
bLA<-log(bA)
bSTO<-bS/bA
bROS<-bI/bS

resultB<-lm(bSQRTL~bLA+bB4+bBZ+bFGC+bLOS+bSTO+bROS)
summary(resultB)

Call:
lm(formula = bSQRTL ~ bLA + bB4 + bBZ + bFGC + bLOS + bSTO + 
    bROS)

Residuals:
    Min      1Q  Median      3Q     Max 
-2.9886 -0.4126 -0.0311  0.3755  4.9748 

Coefficients:
             Estimate Std. Error t value Pr(>|t|)    
(Intercept) 12.676714   0.248782  50.955  < 2e-16 ***
bLA         -0.231536   0.012834 -18.041  < 2e-16 ***
bB41        -0.119601   0.053797  -2.223 0.026362 *  
bBZ1        -0.010586   0.043980  -0.241 0.809817    
bFGC1        0.209953   0.108425   1.936 0.053023 .  
bLOS1        0.185632   0.048407   3.835 0.000131 ***
bSTO        -0.005552   0.003302  -1.681 0.092984 .  
bROS         0.006784   0.003021   2.246 0.024866 *  
---
Signif. codes:  0 ‘***’ 0.001 ‘**’ 0.01 ‘*’ 0.05 ‘.’ 0.1 ‘ ’ 1

Residual standard error: 0.7432 on 1391 degrees of freedom
Multiple R-squared:  0.396, Adjusted R-squared:  0.393 
F-statistic: 130.3 on 7 and 1391 DF,  p-value: < 2.2e-16

cINTb=12.676714
cLAb=-0.231536
cB4b=-0.119601
cBZb=-0.010586
cFGCb=0.209953
cLOSb=0.185632
cSTOb=-0.005552
cROSb=0.006784
SOLUTIONb<-(cINTb+cLAb*nLA+cB4b*nB4+cBZb*nBZ+cFGCb*nFGC+cLOSb*nLOS+cSTOb*nSTO+cROSb*nROS)^2
print(SOLUTIONb)

[1] 60.76811

Question C

FINALC<-subset(Final,SIC>6020 & SIC<6023)
cC<-FINALC$CIK
cSC<-FINALC$SIC
cSQRTL<-sqrt(FINALC$LAG)
cB4<-factor(FINALC$BIG4)
cBZ<-factor(FINALC$BUSY)
cFGC<-factor(FINALC$GC)
cLOS<-factor(FINALC$LOSS)
cS<-FINALC$SALES
cI<-FINALC$NI
cA<-FINALC$TA
cLS<-log(cS)
cLA<-log(cA)
cSTO<-cS/cA
cROS<-cI/cS

resultC<-lm(cSQRTL~cLA+cB4+cBZ+cFGC+cLOS+cSTO+cROS)
summary(resultC)

Call:
lm(formula = cSQRTL ~ cLA + cB4 + cBZ + cFGC + cLOS + cSTO + 
    cROS)

Residuals:
    Min      1Q  Median      3Q     Max 
-1.7006 -0.3391 -0.0508  0.3009  4.9393 

Coefficients:
             Estimate Std. Error t value Pr(>|t|)    
(Intercept) 14.497921   0.613952  23.614   <2e-16 ***
cLA         -0.266749   0.027447  -9.719   <2e-16 ***
cB41         0.035156   0.092779   0.379   0.7050    
cBZ1        -0.312962   0.264542  -1.183   0.2377    
cFGC1        0.573001   0.461294   1.242   0.2151    
cLOS1       -0.081953   0.245237  -0.334   0.7385    
cSTO        -0.001510   0.006153  -0.245   0.8063    
cROS        -0.615477   0.304999  -2.018   0.0444 *  
---
Signif. codes:  0 ‘***’ 0.001 ‘**’ 0.01 ‘*’ 0.05 ‘.’ 0.1 ‘ ’ 1

Residual standard error: 0.6305 on 327 degrees of freedom
Multiple R-squared:  0.3416,    Adjusted R-squared:  0.3275 
F-statistic: 24.23 on 7 and 327 DF,  p-value: < 2.2e-16

cINTc=14.497921
cLAc=-0.266749 
cB4c=0.035156
cBZc=-0.312962
cFGCc=0.573001
cLOSc=-0.081953
cSTOc=-0.001510
cROSc=-0.615477
nB4c=0
SOLUTIONc<-(cINTc+cLAc*nLA+cB4c*nB4c+cBZc*nBZ+cFGCc*nFGC+cLOSc*nLOS+cSTOc*nSTO+cROSc*nROS)^2
print(SOLUTIONc)

[1] 75.58058