Group 1 Assignment
Group 1 (WINNERS)
JUMA BRIAN OTIENO BUS-244-060/2021
GITHU PRISCILLA NJERI BUS-244-023/2021
MWANGI MOREEN MBITHE BUS-244-025/2021
LOTHUERA NAOMI ASUNYEN BUS-244-030/2021
KINYANJUI VICTORIA MUGURE BUS-244-072/2021
2025-05-06
Survival
library(survival)
d <- read.csv("SCOM.csv")
head(d)## DATE ISSUER DEALS VOLUME TURNOVER MAX.PRICE MIN.PRICE
## 1 02/01/2019 SCOM 155 1,778,397.00 39,637,648.40 23.00 22.10
## 2 03/01/2019 SCOM 288 12,255,996.00 271,459,760.40 22.60 21.00
## 3 04/01/2019 SCOM 181 2,210,307.00 47,113,391.10 22.00 20.10
## 4 07/01/2019 SCOM 187 6,283,857.00 134,894,261.40 22.00 21.30
## 5 08/01/2019 SCOM 102 1,532,800.00 33,720,640.00 22.20 21.50
## 6 09/01/2019 SCOM 368 21,758,774.00 485,471,249.60 22.75 22.05
## AVG.PRICE Closing.Price
## 1 22.36 22.25
## 2 22.13 22.15
## 3 21.39 21.30
## 4 21.51 21.45
## 5 21.90 22.00
## 6 22.33 22.30Max <- d$MAX.PRICE
min <- d$MIN.PRICE
closing <- d$Closing.Price
hist(Max)
hist(min)
hist(closing)
barplot(Max)
barplot(min)
barplot(closing)
### Regression
x <- d$MAX.PRICE
y <- d$MIN.PRICE
z <- d$Closing.Price
h <- d$volume
summary(lm(x ~ y))##
## Call:
## lm(formula = x ~ y)
##
## Residuals:
## Min 1Q Median 3Q Max
## -1.3034 -0.6291 -0.1917 0.4126 3.8963
##
## Coefficients:
## Estimate Std. Error t value Pr(>|t|)
## (Intercept) 0.90478 0.07021 12.89 <2e-16 ***
## y 1.01662 0.00254 400.27 <2e-16 ***
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Residual standard error: 0.8468 on 1493 degrees of freedom
## Multiple R-squared: 0.9908, Adjusted R-squared: 0.9908
## F-statistic: 1.602e+05 on 1 and 1493 DF, p-value: < 2.2e-16summary(lm(y ~ z))##
## Call:
## lm(formula = y ~ z)
##
## Residuals:
## Min 1Q Median 3Q Max
## -4.9987 -0.6667 0.0102 0.5254 6.9549
##
## Coefficients:
## Estimate Std. Error t value Pr(>|t|)
## (Intercept) 0.461385 0.109983 4.195 2.89e-05 ***
## z 0.961503 0.003892 247.057 < 2e-16 ***
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Residual standard error: 1.333 on 1493 degrees of freedom
## Multiple R-squared: 0.9761, Adjusted R-squared: 0.9761
## F-statistic: 6.104e+04 on 1 and 1493 DF, p-value: < 2.2e-16summary(lm(x ~ z))##
## Call:
## lm(formula = x ~ z)
##
## Residuals:
## Min 1Q Median 3Q Max
## -4.7130 -0.8313 -0.0848 0.7865 7.8276
##
## Coefficients:
## Estimate Std. Error t value Pr(>|t|)
## (Intercept) 1.339324 0.126630 10.58 <2e-16 ***
## z 0.978769 0.004481 218.43 <2e-16 ***
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Residual standard error: 1.535 on 1493 degrees of freedom
## Multiple R-squared: 0.9697, Adjusted R-squared: 0.9696
## F-statistic: 4.771e+04 on 1 and 1493 DF, p-value: < 2.2e-16summary(lm(x ~ y + z))##
## Call:
## lm(formula = x ~ y + z)
##
## Residuals:
## Min 1Q Median 3Q Max
## -1.3834 -0.6151 -0.1825 0.4120 3.7987
##
## Coefficients:
## Estimate Std. Error t value Pr(>|t|)
## (Intercept) 0.89550 0.07002 12.790 < 2e-16 ***
## y 0.96194 0.01638 58.727 < 2e-16 ***
## z 0.05386 0.01594 3.379 0.000747 ***
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Residual standard error: 0.8439 on 1492 degrees of freedom
## Multiple R-squared: 0.9908, Adjusted R-squared: 0.9908
## F-statistic: 8.067e+04 on 2 and 1492 DF, p-value: < 2.2e-16Correlation
cor(x, y)## [1] 0.995373cor(y, z)## [1] 0.9879896cor(x, z)## [1] 0.984712aov(lm(y ~ x))## Call:
## aov(formula = lm(y ~ x))
##
## Terms:
## x Residuals
## Sum of Squares 110136.31 1026.33
## Deg. of Freedom 1 1493
##
## Residual standard error: 0.8291112
## Estimated effects may be unbalancedsummary(lm(y ~ x))##
## Call:
## lm(formula = y ~ x)
##
## Residuals:
## Min 1Q Median 3Q Max
## -3.8182 -0.4459 0.1898 0.6018 1.3895
##
## Coefficients:
## Estimate Std. Error t value Pr(>|t|)
## (Intercept) -0.639294 0.070549 -9.062 <2e-16 ***
## x 0.974570 0.002435 400.269 <2e-16 ***
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Residual standard error: 0.8291 on 1493 degrees of freedom
## Multiple R-squared: 0.9908, Adjusted R-squared: 0.9908
## F-statistic: 1.602e+05 on 1 and 1493 DF, p-value: < 2.2e-16plot(lm(y ~ x))
hist(x)
### fGarch
# Load GARCH library (make sure it's installed already)
library(fGarch)## Warning: package 'fGarch' was built under R version 4.4.3## NOTE: Packages 'fBasics', 'timeDate', and 'timeSeries' are no longer
## attached to the search() path when 'fGarch' is attached.
##
## If needed attach them yourself in your R script by e.g.,
## require("timeSeries")library(timeSeries)## Warning: package 'timeSeries' was built under R version 4.4.3## Loading required package: timeDate## Warning: package 'timeDate' was built under R version 4.4.3##
## Attaching package: 'timeSeries'## The following objects are masked from 'package:graphics':
##
## lines, pointsTimeseries
log.z <- diff(z)
plot(log.z)
ts.plot(log.z)
acf(log.z)
pacf(log.z)
s <- log.z^2
m2 <- garchFit(~garch(1,1), data=log.z, trace=FALSE)
summary(m2)##
## Title:
## GARCH Modelling
##
## Call:
## garchFit(formula = ~garch(1, 1), data = log.z, trace = FALSE)
##
## Mean and Variance Equation:
## data ~ garch(1, 1)
## <environment: 0x000001f975a116b8>
## [data = log.z]
##
## Conditional Distribution:
## norm
##
## Coefficient(s):
## mu omega alpha1 beta1
## -0.0019777 0.0228430 0.2212501 0.6903999
##
## Std. Errors:
## based on Hessian
##
## Error Analysis:
## Estimate Std. Error t value Pr(>|t|)
## mu -0.001978 0.010372 -0.191 0.848784
## omega 0.022843 0.006363 3.590 0.000331 ***
## alpha1 0.221250 0.041738 5.301 1.15e-07 ***
## beta1 0.690400 0.058122 11.878 < 2e-16 ***
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Log Likelihood:
## -830.5222 normalized: -0.5559051
##
## Description:
## Wed May 7 08:35:05 2025 by user: Brian Juma
##
##
## Standardised Residuals Tests:
## Statistic p-Value
## Jarque-Bera Test R Chi^2 931.343560 0.000000e+00
## Shapiro-Wilk Test R W 0.942090 0.000000e+00
## Ljung-Box Test R Q(10) 77.600581 1.480038e-12
## Ljung-Box Test R Q(15) 84.752142 9.347967e-12
## Ljung-Box Test R Q(20) 90.167630 6.929035e-11
## Ljung-Box Test R^2 Q(10) 7.724979 6.556804e-01
## Ljung-Box Test R^2 Q(15) 11.996060 6.793273e-01
## Ljung-Box Test R^2 Q(20) 22.493352 3.143508e-01
## LM Arch Test R TR^2 9.628747 6.484940e-01
##
## Information Criterion Statistics:
## AIC BIC SIC HQIC
## 1.117165 1.131380 1.117151 1.122461plot(m2, which = 1) # Series and conditional SD
plot(m2, which = 2) # ACF of standardized residuals
plot(m2, which = 3) # Normal Q-Q plot
plot(m2, which = 4) # P-values for Ljung-Box statistic
### rugarch install.packages(“rugarch”, dependencies = TRUE)
library(rugarch)## Warning: package 'rugarch' was built under R version 4.4.3## Loading required package: parallel##
## Attaching package: 'rugarch'## The following object is masked from 'package:stats':
##
## sigma# Define the model specification
z <- d$Closing.Price
D3 <- diff(tail(z, 200))
m2 <- ugarchspec(
variance.model = list(model = "gjrGARCH", garchOrder = c(1, 1)),
mean.model = list(armaOrder = c(0, 0), include.mean = FALSE),
distribution.model = "norm"
)
# Fit the model to the data
m2fit <- ugarchfit(spec = m2, data = D3)
f <- ugarchforecast(m2fit, n.ahead = 120)
plot(f, which = 1)
#kaplan meier
library(survival)
library(survminer)## Loading required package: ggplot2## Loading required package: ggpubr##
## Attaching package: 'survminer'## The following object is masked from 'package:survival':
##
## myelomad1=data.frame(time=c(2,10,12,18,4),event=c(1,0,1,1,0))
kmc=with(d1,Surv(time,event));
kmc## [1] 2 10+ 12 18 4+plot(kmc)
plot(kmc,fun="cumhaz")
kmc2=survfit(Surv(time,event)~1,data=d1);kmc2## Call: survfit(formula = Surv(time, event) ~ 1, data = d1)
##
## n events median 0.95LCL 0.95UCL
## [1,] 5 3 12 12 NAsummary(kmc2)## Call: survfit(formula = Surv(time, event) ~ 1, data = d1)
##
## time n.risk n.event survival std.err lower 95% CI upper 95% CI
## 2 5 1 0.8 0.179 0.5161 1
## 12 2 1 0.4 0.297 0.0935 1
## 18 1 1 0.0 NaN NA NA