Importar datos

library(quantmod)
## Warning: package 'quantmod' was built under R version 4.2.3
## Loading required package: xts
## Warning: package 'xts' was built under R version 4.2.3
## Loading required package: zoo
## Warning: package 'zoo' was built under R version 4.2.3
## 
## Attaching package: 'zoo'
## The following objects are masked from 'package:base':
## 
##     as.Date, as.Date.numeric
## Loading required package: TTR
## Warning: package 'TTR' was built under R version 4.2.3
## Registered S3 method overwritten by 'quantmod':
##   method            from
##   as.zoo.data.frame zoo
data_slb = getSymbols("SLB", from ="2017-12-31",
                      to = "2020-01-01",
                      auto.assign = F)
data_Tbill = getSymbols("BIL", from ="2017-12-31",
                      to = "2020-01-01",
                      auto.assign = F)

En este caso se traen los datos de TBill y Schlumberger Limited

head(data_slb)
##            SLB.Open SLB.High SLB.Low SLB.Close SLB.Volume SLB.Adjusted
## 2018-01-02    68.07    69.83   67.60     69.52    8678200     58.11513
## 2018-01-03    69.97    71.64   69.13     71.33    9529200     59.62820
## 2018-01-04    71.76    73.19   71.26     73.10   12252300     61.10781
## 2018-01-05    72.95    73.68   72.25     73.60    8552700     61.52580
## 2018-01-08    73.35    74.92   72.71     74.80    9778900     62.52893
## 2018-01-09    74.78    75.30   74.56     74.90    9370300     62.61252
head(data_Tbill)
##            BIL.Open BIL.High BIL.Low BIL.Close BIL.Volume BIL.Adjusted
## 2018-01-02    91.41    91.43   91.41     91.41     790000     81.80923
## 2018-01-03    91.43    91.43   91.42     91.43     218300     81.82709
## 2018-01-04    91.44    91.44   91.42     91.44    1098100     81.83607
## 2018-01-05    91.43    91.44   91.43     91.44     247600     81.83607
## 2018-01-08    91.43    91.45   91.43     91.45     199800     81.84500
## 2018-01-09    91.43    91.45   91.43     91.45     185900     81.84500

Se calculan los retornos con la diferencia porcentual

ret_Slb = Delt(data_slb$SLB.Adjusted)
ret_Tbill=Delt(data_Tbill$BIL.Adjusted)

rets = cbind(ret_Slb, ret_Tbill)

Se observa el comportamiento de los retornos

head(rets)
##            Delt.1.arithmetic Delt.1.arithmetic.1
## 2018-01-02                NA                  NA
## 2018-01-03       0.026035652        0.0002183178
## 2018-01-04       0.024814003        0.0001098344
## 2018-01-05       0.006840170        0.0000000000
## 2018-01-08       0.016304186        0.0001090765
## 2018-01-09       0.001336906        0.0000000000
names(rets) = c("SLB", "TBILL")
head(rets,6)
##                    SLB        TBILL
## 2018-01-02          NA           NA
## 2018-01-03 0.026035652 0.0002183178
## 2018-01-04 0.024814003 0.0001098344
## 2018-01-05 0.006840170 0.0000000000
## 2018-01-08 0.016304186 0.0001090765
## 2018-01-09 0.001336906 0.0000000000

se le suma 1 para ver los retornos acumulados Donde los retornos acumulados son:

\[ 1 +r_{total}=\prod_{i=1}^T (1+r) \]

rets[1,] = c(0,0)
gross_rets= 1 + rets

head(gross_rets,3)
##                 SLB    TBILL
## 2018-01-02 1.000000 1.000000
## 2018-01-03 1.026036 1.000218
## 2018-01-04 1.024814 1.000110
cum_rets = cumprod(gross_rets)

head(cum_rets)
##                 SLB    TBILL
## 2018-01-02 1.000000 1.000000
## 2018-01-03 1.026036 1.000218
## 2018-01-04 1.051496 1.000328
## 2018-01-05 1.058688 1.000328
## 2018-01-08 1.075949 1.000437
## 2018-01-09 1.077388 1.000437
tail(cum_rets)
##                  SLB    TBILL
## 2019-12-23 0.6408304 1.037705
## 2019-12-24 0.6386308 1.037818
## 2019-12-26 0.6295187 1.037932
## 2019-12-27 0.6284190 1.037818
## 2019-12-30 0.6347033 1.037932
## 2019-12-31 0.6315612 1.037932
plot(cum_rets)

Se puede ver los retornos de los activos:

plot(rets$SLB, col = "red",
     main="retornos SLB y Tbills")

lines(rets$TBILL, col = "darkgreen", lwd=4)

y se observa la volatilidad de SLB y el ETF estable.

Se observan los retornos del activo mas volatil:

plot(cum_rets$SLB, col ="blue")

¿como medir el riesgo? Markowitz (1950) desviacion standar y la varianza muestral,donde:

$$

^2= _{i=1}^T(r_i - {r})^2

\[ \] sd= = $$ ###El activo con mas riesgo tiene una mayor desviacion standar.

returns=rets[-1,]

sd_slb=sd(returns$SPY)
sd_slb
## [1] NA
sd_bill = sd(returns$TBILL)
sd_bill
## [1] 0.0001182067

El activo mas reisgoso es SLB con una sd=0.01887704 , en cambio Tbill tiene una sd=0.0001182195

El riesgo cambia en el tiempo se tiene que anualizar

\[ \sqrt{T} \sigma_T \]

sd_2017 = apply(X =returns["2017"],MARGIN=2,FUN= sd)
sd_2017
## numeric(0)
sd_2018 = apply(X =returns["2018"],MARGIN=2,FUN= sd)
sd_2018
##          SLB        TBILL 
## 0.0160610846 0.0001171382
sd_2019 = apply(X =returns["2019"],MARGIN=2,FUN= sd)
sd_2019
##          SLB        TBILL 
## 0.0212166301 0.0001192197
sd_2020 = apply(X =returns["2020"],MARGIN=2,FUN= sd)
sd_2020
## numeric(0)

Combinar rows

sd_all = rbind(sd_2020, sd_2017
                ,sd_2018,sd_2019)

T= 252 dias de transaccion.

sd_all_anual = sqrt(252)*sd_all
sd_all_anual
##               SLB       TBILL
## sd_2018 0.2549618 0.001859512
## sd_2019 0.3368036 0.001892554
barplot(t(sd_all_anual),beside = T
        , col = c("blue","red")
        ,main = "Desn.Est.anualizada",
        legend.text = c("SLB","T-Bills")
        )