Univercidad Nacional del Altiplano

series de

estadistica e informatica

ejercicio john hanke capitulo 9 pagina 393

promedios de cierre diario del indice de Trasnportacion

s <- read.csv("D://nube/unap/8/series de tiempo/promediostabla9.csv")
head(s)
##   transportes
## 1      222.34
## 2      222.24
## 3      221.17
## 4      218.88
## 5      220.05
## 6      219.61
s.ts <- ts(s)
class(s.ts)
## [1] "ts"
head(s.ts) 
##      transportes
## [1,]      222.34
## [2,]      222.24
## [3,]      221.17
## [4,]      218.88
## [5,]      220.05
## [6,]      219.61

graficando serie de tiemp

plot(s.ts, sub= "Grafica" , main="Promedio de cierre diario del indice de Transportacion",
     cex.main=0.8,col="red" ,xlab="Tiempo",ylab="ïndice Promedio")

plot(s.ts,type="o", sub="Grafica" , main="Promedio de cierre diario del indice de Transportacion",
     cex.main=0.8,col="red" ,xlab="Tiempo",ylab="ïndice Promedio",bg="seagreen")

AFC y PAFC

acf(s.ts, main="Promedio de cierre diario del indice de Transportacion",cex.main=0.8,col="red" ,ylab="Autocrrelacion")

acf(s.ts, plot=FALSE)$acf
## , , 1
## 
##            [,1]
##  [1,] 1.0000000
##  [2,] 0.9423472
##  [3,] 0.8831387
##  [4,] 0.8204419
##  [5,] 0.7582471
##  [6,] 0.6980549
##  [7,] 0.6401488
##  [8,] 0.5806164
##  [9,] 0.5186525
## [10,] 0.4641670
## [11,] 0.4143524
## [12,] 0.3672203
## [13,] 0.3246434
## [14,] 0.2833773
## [15,] 0.2487379
## [16,] 0.2178359
## [17,] 0.1950445
## [18,] 0.1720530
## [19,] 0.1499563
pacf(s.ts) #funcion de autocorrelacion partica

Primera diferencia

primerad <- diff(s.ts,differences = 1)
primerad  #head(primerad,64)  #65-1 manualmente
## Time Series:
## Start = 2 
## End = 65 
## Frequency = 1 
##       transportes
##  [1,]       -0.10
##  [2,]       -1.07
##  [3,]       -2.29
##  [4,]        1.17
##  [5,]       -0.44
##  [6,]       -3.21
##  [7,]        0.93
##  [8,]        2.36
##  [9,]       -0.37
## [10,]       -1.07
## [11,]        2.05
## [12,]        2.24
## [13,]        1.02
## [14,]       -0.49
## [15,]        2.29
## [16,]        2.24
## [17,]       -0.78
## [18,]        2.87
## [19,]       -0.39
## [20,]       -0.34
## [21,]        1.03
## [22,]        3.06
## [23,]        1.95
## [24,]        1.17
## [25,]        2.14
## [26,]        2.83
## [27,]        0.34
## [28,]        5.26
## [29,]        1.99
## [30,]        0.10
## [31,]       -0.05
## [32,]        0.83
## [33,]        0.29
## [34,]       -3.45
## [35,]        1.12
## [36,]        0.19
## [37,]        0.05
## [38,]        2.87
## [39,]        1.12
## [40,]       -0.73
## [41,]       -3.02
## [42,]        1.71
## [43,]        1.90
## [44,]        1.75
## [45,]       -1.37
## [46,]       -3.26
## [47,]       -1.02
## [48,]        1.51
## [49,]       -1.32
## [50,]        3.46
## [51,]        3.26
## [52,]        3.95
## [53,]        0.63
## [54,]        2.24
## [55,]        3.46
## [56,]        3.26
## [57,]        3.95
## [58,]        0.63
## [59,]        2.24
## [60,]        3.46
## [61,]        3.26
## [62,]        3.95
## [63,]        0.63
## [64,]        2.24
# grafico con  la primera diferencia
acf(primerad)

mostrando los datos de acf de primera diferencia

acf(primerad,16, plot=FALSE)$acf# datos
## , , 1
## 
##               [,1]
##  [1,]  1.000000000
##  [2,]  0.281179397
##  [3,]  0.079765077
##  [4,]  0.189123868
##  [5,]  0.241929771
##  [6,]  0.111908077
##  [7,]  0.014343376
##  [8,]  0.176703382
##  [9,] -0.044213410
## [10,] -0.133395480
## [11,]  0.044898473
## [12,] -0.070064197
## [13,] -0.019387016
## [14,] -0.028492558
## [15,]  0.001757683
## [16,] -0.124115169
## [17,] -0.186528578
pacf(diff(s.ts,1))

-----------
#as <- diff(s.ts)
#head(as,64)  

acf(s.ts, plot=FALSE)$acf
## , , 1
## 
##             [,1]
##  [1,] -1.0000000
##  [2,] -0.9423472
##  [3,] -0.8831387
##  [4,] -0.8204419
##  [5,] -0.7582471
##  [6,] -0.6980549
##  [7,] -0.6401488
##  [8,] -0.5806164
##  [9,] -0.5186525
## [10,] -0.4641670
## [11,] -0.4143524
## [12,] -0.3672203
## [13,] -0.3246434
## [14,] -0.2833773
## [15,] -0.2487379
## [16,] -0.2178359
## [17,] -0.1950445
## [18,] -0.1720530
## [19,] -0.1499563
mc <-arima(s.ts,c(1,1,0))
mc
## 
## Call:
## arima(x = s.ts, order = c(1, 1, 0))
## 
## Coefficients:
##          ar1
##       0.4383
## s.e.  0.1117
## 
## sigma^2 estimated as 3.861:  log likelihood = -134.15,  aic = 272.29
coef(mc)
##       ar1 
## 0.4383256
ms <-arima(s.ts,c(0,1,1))
ms
## 
## Call:
## arima(x = s.ts, order = c(0, 1, 1))
## 
## Coefficients:
##          ma1
##       0.3832
## s.e.  0.1082
## 
## sigma^2 estimated as 4.031:  log likelihood = -135.5,  aic = 275
coef(ms)
##       ma1 
## 0.3831591
summary(s.ts)
##   transportes   
##  Min.   :216.4  
##  1st Qu.:226.8  
##  Median :247.8  
##  Mean   :244.2  
##  3rd Qu.:251.8  
##  Max.   :288.6