library(readxl) 
## Warning: package 'readxl' was built under R version 4.3.3
library(TTR)
## Warning: package 'TTR' was built under R version 4.3.3
library(TSA)
## Warning: package 'TSA' was built under R version 4.3.3
## 
## Attaching package: 'TSA'
## The following objects are masked from 'package:stats':
## 
##     acf, arima
## The following object is masked from 'package:utils':
## 
##     tar
library(tseries)
## Warning: package 'tseries' was built under R version 4.3.3
## Registered S3 method overwritten by 'quantmod':
##   method            from
##   as.zoo.data.frame zoo
library(graphics)
library(forecast)
## Warning: package 'forecast' was built under R version 4.3.3
## Registered S3 methods overwritten by 'forecast':
##   method       from
##   fitted.Arima TSA 
##   plot.Arima   TSA
library(lmtest)
## Warning: package 'lmtest' was built under R version 4.3.3
## Loading required package: zoo
## Warning: package 'zoo' was built under R version 4.3.3
## 
## Attaching package: 'zoo'
## The following objects are masked from 'package:base':
## 
##     as.Date, as.Date.numeric
Data_TSS_Sungai <- read_excel("C:/Users/USER/Downloads/Data TSS Sungai.xlsx", 
                              col_types = c("date", "numeric"))
## Warning: Coercing text to numeric in B123 / R123C2: '49.25'
## Warning: Coercing text to numeric in B124 / R124C2: '48.28'
## Warning: Coercing text to numeric in B192 / R192C2: '12.64'
## Warning: Coercing text to numeric in B478 / R478C2: '37.89'
## Warning: Coercing text to numeric in B479 / R479C2: '31.91'
## Warning: Coercing text to numeric in B546 / R546C2: '36.33'
View(Data_TSS_Sungai)
plot.ts(Data_TSS_Sungai$TSS_Sungai, ylab="TSS Sungai", xlab = "Date", col="purple")

Berdasarkan plot dapat dilihat bahwa tampak rata-rata dan varians data TSS adalah konstan(tidak ada pola trend), walaupun pada beberapa period terlihat rata-rata dan varians mengalami peningkatan. Namun, secara keseluruhan masih dapat dikatakan bahwa rata-rata dan variannya adalah konstan.

BoxCox.lambda(Data_TSS_Sungai$TSS_Sungai)
## [1] -0.04068353

Karena nilai lamda masih dalam rentang -2 sampai 2 maka dapat dikatakan stasioner dalam ragam

tseries::adf.test(Data_TSS_Sungai$TSS_Sungai)
## Warning in tseries::adf.test(Data_TSS_Sungai$TSS_Sungai): p-value smaller than
## printed p-value
## 
##  Augmented Dickey-Fuller Test
## 
## data:  Data_TSS_Sungai$TSS_Sungai
## Dickey-Fuller = -8.9689, Lag order = 8, p-value = 0.01
## alternative hypothesis: stationary

Karena p-value = 0.01 < alpha = 0.05 maka data sudah stasioner dalam rata-rata

Data hasil diatas diketahui bahwa data awal yang dimiliki sudah stasioner dalam ragam dan stasioner dalam rata-rata. Sehingga proses differencing tidak perlu dilakukan atau kata lain d=0

acf(Data_TSS_Sungai$TSS_Sungai, lag.max=30, main="Plot ACF MA(q)")

Pada plot ACF di atas, terlihat bahwa lag mengalami cut off setelah lag ketiga. Sehingga ada indikasi bahwa terbentuk model MA(3).

pacf(Data_TSS_Sungai$TSS_Sungai, lag.max=30, main="Plot PACF AR(p)", ylab="PACF")

Pada plot PACF di atas, terlihat bahwa lag mengalami cut off setelah lag ke2. Sehingga ada indikasi bahwa terbentuk model AR(2).

eacf(Data_TSS_Sungai$TSS_Sungai)
## AR/MA
##   0 1 2 3 4 5 6 7 8 9 10 11 12 13
## 0 x x x o o o o o o o o  o  o  o 
## 1 x o o o o o o o o o o  o  o  o 
## 2 x x o o o o o o o o o  o  o  o 
## 3 x x o o o o o o o o o  o  o  o 
## 4 x x o o o o o o o o o  o  o  o 
## 5 x x o o o o o o o o o  o  o  o 
## 6 x x o x o x o o o o o  o  o  o 
## 7 x x o x x x x o o o o  o  o  o

Berdasarkan hasil plot EACF di atas, diperoleh model dugaan yang dapat diduga dari data TSS sebagai model tentatifnya yaitu ARIMA (0,0,3)| ARIMA (1,0,1) | AR1MA(2,0,2) | ARIMA(3,0,2). Untuk memastikan model tentatif dari model-model dugaan tersebut, dilakukan uji signifikansi parameter pada setiap model.

fit1 <- arima(Data_TSS_Sungai$TSS_Sungai, order=c(0,0,3), include.mean = TRUE, method = "ML")
fit1
## 
## Call:
## arima(x = Data_TSS_Sungai$TSS_Sungai, order = c(0, 0, 3), include.mean = TRUE, 
##     method = "ML")
## 
## Coefficients:
##          ma1     ma2     ma3  intercept
##       0.3283  0.2157  0.1031    36.1485
## s.e.  0.0368  0.0374  0.0382     1.4150
## 
## sigma^2 estimated as 539.7:  log likelihood = -3332.1,  aic = 6672.2
coeftest(fit1)
## 
## z test of coefficients:
## 
##            Estimate Std. Error z value  Pr(>|z|)    
## ma1        0.328317   0.036752  8.9334 < 2.2e-16 ***
## ma2        0.215721   0.037396  5.7685 7.997e-09 ***
## ma3        0.103121   0.038233  2.6972  0.006993 ** 
## intercept 36.148469   1.415004 25.5466 < 2.2e-16 ***
## ---
## Signif. codes:  0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
fit2 <- arima(Data_TSS_Sungai$TSS_Sungai, order=c(1,0,1), include.mean = TRUE, method = "ML")
fit1
## 
## Call:
## arima(x = Data_TSS_Sungai$TSS_Sungai, order = c(0, 0, 3), include.mean = TRUE, 
##     method = "ML")
## 
## Coefficients:
##          ma1     ma2     ma3  intercept
##       0.3283  0.2157  0.1031    36.1485
## s.e.  0.0368  0.0374  0.0382     1.4150
## 
## sigma^2 estimated as 539.7:  log likelihood = -3332.1,  aic = 6672.2
coeftest(fit2)
## 
## z test of coefficients:
## 
##            Estimate Std. Error z value  Pr(>|z|)    
## ar1        0.566096   0.070253  8.0580 7.758e-16 ***
## ma1       -0.228061   0.081231 -2.8076  0.004992 ** 
## intercept 36.176045   1.529135 23.6579 < 2.2e-16 ***
## ---
## Signif. codes:  0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
fit3 <- arima(Data_TSS_Sungai$TSS_Sungai, order=c(2,0,2), include.mean = TRUE, method = "ML")
## Warning in stats::arima(x = x, order = order, seasonal = seasonal, xreg = xreg,
## : possible convergence problem: optim gave code = 1
fit3
## 
## Call:
## arima(x = Data_TSS_Sungai$TSS_Sungai, order = c(2, 0, 2), include.mean = TRUE, 
##     method = "ML")
## 
## Coefficients:
##          ar1      ar2      ma1     ma2  intercept
##       1.2870  -0.4885  -0.9571  0.2787    36.1639
## s.e.  0.3589   0.1920   0.3585  0.0985     1.3705
## 
## sigma^2 estimated as 538.7:  log likelihood = -3331.45,  aic = 6672.9
coeftest(fit3)
## 
## z test of coefficients:
## 
##            Estimate Std. Error z value  Pr(>|z|)    
## ar1        1.286956   0.358908  3.5858 0.0003361 ***
## ar2       -0.488452   0.192029 -2.5436 0.0109705 *  
## ma1       -0.957118   0.358543 -2.6695 0.0075972 ** 
## ma2        0.278702   0.098479  2.8301 0.0046540 ** 
## intercept 36.163934   1.370464 26.3881 < 2.2e-16 ***
## ---
## Signif. codes:  0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
fit4 <- arima(Data_TSS_Sungai$TSS_Sungai, order=c(3,0,2), include.mean = TRUE, method = "ML")
fit4
## 
## Call:
## arima(x = Data_TSS_Sungai$TSS_Sungai, order = c(3, 0, 2), include.mean = TRUE, 
##     method = "ML")
## 
## Coefficients:
##          ar1      ar2     ar3      ma1     ma2  intercept
##       0.4798  -0.2218  0.0785  -0.1492  0.2849    36.1429
## s.e.  2.1270   0.6000  0.6836   2.1342  1.1800     1.4699
## 
## sigma^2 estimated as 539.3:  log likelihood = -3331.84,  aic = 6675.69
coeftest(fit4)
## 
## z test of coefficients:
## 
##            Estimate Std. Error z value Pr(>|z|)    
## ar1        0.479811   2.127006  0.2256   0.8215    
## ar2       -0.221766   0.599968 -0.3696   0.7117    
## ar3        0.078548   0.683589  0.1149   0.9085    
## ma1       -0.149198   2.134186 -0.0699   0.9443    
## ma2        0.284897   1.179989  0.2414   0.8092    
## intercept 36.142866   1.469861 24.5893   <2e-16 ***
## ---
## Signif. codes:  0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1

Berdasarkan hasil uji signifikan diperoleh bahwa model (0,0,3)| ARIMA (1,0,1) | AR1MA(2,0,2) memiliki nilai p-value < 0.05 (teruji signifikan) Selanjutnya untuk menentukan model terbaik dengan cara membandingkan nilai AIC dan diambil nilai AIC terkecil

AIC<- c(fit1$aic, fit2$aic, fit3$aic, fit4$aic)
KndidatModelARIMA <- c("ARIMA(0,0,3)", "ARIMA(1,0,1)", "ARIMA(2,0,2)", "ARIMA(3,0,2)")
compmodelARIMA <- cbind(KndidatModelARIMA, AIC)
colnames(compmodelARIMA) <- c("Kandidat Model", "Nilai AIC")
compmodelARIMA <- as.data.frame(compmodelARIMA)
compmodelARIMA
##   Kandidat Model        Nilai AIC
## 1   ARIMA(0,0,3) 6672.19828482575
## 2   ARIMA(1,0,1) 6671.73411573139
## 3   ARIMA(2,0,2) 6672.89656652721
## 4   ARIMA(3,0,2) 6675.68718038972

Data tabel diatas diketahui bahwa model ARIMA (1,0,1) memiliki nilai AIC terkecil sehingga ARIMA (1,0,1) atau fit2 merupakan model terbaik yang dapat digunakan untuk meramalkan data.

ts.plot(fit2$residuals)

qqnorm(fit2$residuals)
qqline(fit2$residual)

ks.test(fit2$residuals,ecdf(fit2$residuals))
## 
##  Asymptotic one-sample Kolmogorov-Smirnov test
## 
## data:  fit2$residuals
## D = 0.0013699, p-value = 1
## alternative hypothesis: two-sided

Pada asumsi residul diketahui nilai p-value >0,5 sehingga data dikatakan data berdistribusi normal

ARIMA101diag <- stats::arima(Data_TSS_Sungai$TSS_Sungai, order = c(1,0,1), method = "ML")
checkresiduals(ARIMA101diag)

## 
##  Ljung-Box test
## 
## data:  Residuals from ARIMA(1,0,1) with non-zero mean
## Q* = 5.6214, df = 8, p-value = 0.6896
## 
## Model df: 2.   Total lags used: 10

Didapat p-value sebesar 0.6896 yang lebih dari taraf nyata 5% sehingga terima H0 dan menandakan bahwa residual menyebar normal

arima.101y<-arima(Data_TSS_Sungai$TSS_Sungai, order=c(1,0,1), include.mean = TRUE,method="ML")
#ARIMA (1,0,1)
arima.101y
## 
## Call:
## arima(x = Data_TSS_Sungai$TSS_Sungai, order = c(1, 0, 1), include.mean = TRUE, 
##     method = "ML")
## 
## Coefficients:
##          ar1      ma1  intercept
##       0.5661  -0.2281    36.1760
## s.e.  0.0703   0.0812     1.5291
## 
## sigma^2 estimated as 540.8:  log likelihood = -3332.87,  aic = 6671.73
sisaan101 <- arima.101y$residuals

# Eksplorasi
par(mfrow=c(2,2))
qqnorm(sisaan101)
qqline(sisaan101, col = "blue", lwd = 2)
plot(c(1:length(sisaan101)),sisaan101)
acf(sisaan101)
pacf(sisaan101)

Berdasarkan hasil diatas, secara eksploratif Normal Q-Q Plot menunjukkan bahwa sisaan tidak mengikuti sebaran normal karena banyak titik-titik yang tidak berada di sekitar garis. Selanjutnya, apabila dilihat dari plot ACF dan PACF terlihat bahwa tidak lag yang signifikan. Hal ini menunjukkan bahwa tidak ada gejala autokorelasi pada sisaan. Selanjutnya, untuk memastikan kembali akan dilakukan uji asumsi secara formal. `` Sisaan tidak menyebar normal (pvalue<0.5)

t.test(sisaan101, mu = 0, alternative = "two.sided")
## 
##  One Sample t-test
## 
## data:  sisaan101
## t = -0.00096624, df = 729, p-value = 0.9992
## alternative hypothesis: true mean is not equal to 0
## 95 percent confidence interval:
##  -1.691751  1.690086
## sample estimates:
##     mean of x 
## -0.0008322157

nilai tengah sisaan = 0 ( pvalue >0.05)

Box.test(sisaan101, lag = 30 ,type = "Ljung")
## 
##  Box-Ljung test
## 
## data:  sisaan101
## X-squared = 25.217, df = 30, p-value = 0.7144

Berdasarkan hasil uji Ljung-Box di atas dapat disimpulkan bahwa H0 tidak ditolak karena p-value=0.7144 > 0.05 yang berarti tidak terdapat gejala autokorelasi pada sisaan dari model ARIMA (1,0,1)

Kesimpulan : Asumsi terpenuhi, kecuali sisaan tidak menyebar normal.

dugaan <- fitted(arima.101y)
cbind(Data_TSS_Sungai$TSS_Sungai,dugaan)
##          [,1]
##   [1,]  26.00
##   [2,]  20.00
##   [3,] 159.00
##   [4,]  20.00
##   [5,]   6.00
##   [6,]  25.00
##   [7,]  29.00
##   [8,]  47.00
##   [9,]  56.00
##  [10,]  78.00
##  [11,]  18.00
##  [12,]  19.00
##  [13,]  15.00
##  [14,]  87.00
##  [15,]  25.00
##  [16,]  26.00
##  [17,]  74.00
##  [18,]  28.00
##  [19,]  46.00
##  [20,] 143.00
##  [21,]  33.00
##  [22,]  55.00
##  [23,]  81.00
##  [24,]  20.00
##  [25,]  73.00
##  [26,]  19.00
##  [27,]  74.00
##  [28,]   2.00
##  [29,]  10.00
##  [30,]  21.00
##  [31,]  17.00
##  [32,]  37.00
##  [33,]  29.00
##  [34,]  37.00
##  [35,]  53.00
##  [36,]  36.00
##  [37,]  31.00
##  [38,]  55.00
##  [39,]  38.00
##  [40,]  34.00
##  [41,]  23.00
##  [42,]  32.00
##  [43,]  86.00
##  [44,]  53.00
##  [45,]   7.00
##  [46,]  10.00
##  [47,]   9.00
##  [48,]   9.00
##  [49,]   9.00
##  [50,]  10.00
##  [51,]  43.00
##  [52,]  56.00
##  [53,] 102.00
##  [54,]  49.00
##  [55,]  63.00
##  [56,]  39.00
##  [57,]  52.00
##  [58,]  27.00
##  [59,]  21.00
##  [60,]  28.00
##  [61,]  25.00
##  [62,]   9.00
##  [63,]  48.00
##  [64,]  38.00
##  [65,]  15.00
##  [66,]  39.00
##  [67,]  33.00
##  [68,]   6.00
##  [69,]   9.00
##  [70,]  12.00
##  [71,]  14.00
##  [72,]   2.00
##  [73,]   3.00
##  [74,]  14.00
##  [75,]  23.00
##  [76,]  12.00
##  [77,]  12.00
##  [78,]  13.00
##  [79,]  18.00
##  [80,]  64.00
##  [81,]  16.00
##  [82,]  11.00
##  [83,]  17.00
##  [84,]  42.00
##  [85,]  37.00
##  [86,]  67.00
##  [87,]  96.00
##  [88,]  82.00
##  [89,]  79.00
##  [90,]  58.00
##  [91,]  24.00
##  [92,]  22.00
##  [93,]   9.00
##  [94,]  11.00
##  [95,]  45.00
##  [96,]  27.00
##  [97,]  28.00
##  [98,]  43.00
##  [99,]  75.00
## [100,]  85.00
## [101,] 106.00
## [102,]  57.00
## [103,]  27.00
## [104,]  10.00
## [105,]   8.00
## [106,]   9.00
## [107,]   7.00
## [108,]  26.00
## [109,]   3.00
## [110,]  27.00
## [111,]   8.00
## [112,] 102.00
## [113,]  33.00
## [114,]  36.00
## [115,]  21.00
## [116,]  25.00
## [117,]  40.00
## [118,]  80.00
## [119,]  26.00
## [120,]  27.00
## [121,]  17.00
## [122,]  49.25
## [123,]  48.28
## [124,]   6.00
## [125,]   9.00
## [126,]  14.00
## [127,]   9.00
## [128,]  47.00
## [129,]  52.00
## [130,]  60.00
## [131,]  39.00
## [132,]  20.00
## [133,]  74.00
## [134,]  25.00
## [135,]  22.00
## [136,]  32.00
## [137,]  51.00
## [138,]  37.00
## [139,]  48.00
## [140,]  21.00
## [141,]  66.00
## [142,]  24.00
## [143,]  36.00
## [144,]  25.00
## [145,]  44.00
## [146,]  86.00
## [147,]  56.00
## [148,]  22.00
## [149,]  29.00
## [150,]  30.00
## [151,]  70.00
## [152,]  51.00
## [153,]  68.00
## [154,]  60.00
## [155,]  32.00
## [156,]  19.00
## [157,]  22.00
## [158,]  32.00
## [159,]  28.00
## [160,]  26.00
## [161,]  38.00
## [162,]   6.00
## [163,]  32.00
## [164,]  23.00
## [165,]  49.00
## [166,]  28.00
## [167,]  23.00
## [168,]  27.00
## [169,]  23.00
## [170,]  22.00
## [171,]  19.00
## [172,]  23.00
## [173,]  47.00
## [174,]  57.00
## [175,] 108.00
## [176,]  19.00
## [177,]  24.00
## [178,]  43.00
## [179,]  60.00
## [180,]  21.00
## [181,]  88.00
## [182,]  49.00
## [183,]  17.00
## [184,]  35.00
## [185,]  47.00
## [186,]  46.00
## [187,]  21.00
## [188,]  32.00
## [189,]  44.00
## [190,]  29.00
## [191,]  12.64
## [192,]  31.00
## [193,]  39.00
## [194,]   7.00
## [195,]  22.00
## [196,]  27.00
## [197,]  23.00
## [198,]  23.00
## [199,]  21.00
## [200,]  66.00
## [201,]  45.00
## [202,]  52.00
## [203,]  69.00
## [204,]  74.00
## [205,]  50.00
## [206,]  33.00
## [207,]  31.00
## [208,]  18.00
## [209,]  12.00
## [210,]  13.00
## [211,]  17.00
## [212,] 124.00
## [213,]  33.00
## [214,]  51.00
## [215,]  54.00
## [216,]  67.00
## [217,]   7.00
## [218,]  33.00
## [219,]  62.00
## [220,]  25.00
## [221,]  27.00
## [222,]   9.00
## [223,]  33.00
## [224,]  31.00
## [225,]  31.00
## [226,]  38.00
## [227,]  30.00
## [228,]  55.00
## [229,]  53.00
## [230,]  27.00
## [231,]  33.00
## [232,]  17.00
## [233,]  26.00
## [234,]  21.00
## [235,]  46.00
## [236,]  24.00
## [237,]  37.00
## [238,]  31.00
## [239,]  29.00
## [240,]  18.00
## [241,]  11.00
## [242,]  17.00
## [243,]   6.00
## [244,]  14.00
## [245,]  17.00
## [246,]  27.00
## [247,]  15.00
## [248,]  41.00
## [249,]  51.00
## [250,] 119.00
## [251,]  96.00
## [252,]  24.00
## [253,]  25.00
## [254,]  21.00
## [255,]  27.00
## [256,]  20.00
## [257,]  39.00
## [258,]  21.00
## [259,]  33.00
## [260,]  45.00
## [261,]  19.00
## [262,]  22.00
## [263,]  14.00
## [264,]  18.00
## [265,]  17.00
## [266,]  18.00
## [267,]  24.00
## [268,]  29.00
## [269,]  34.00
## [270,]  66.00
## [271,]  18.00
## [272,]  37.00
## [273,]  31.00
## [274,]  17.00
## [275,]  21.00
## [276,]  39.00
## [277,]  30.00
## [278,]  63.00
## [279,]  77.00
## [280,]  73.00
## [281,]  18.00
## [282,]  35.00
## [283,]  84.00
## [284,]  44.00
## [285,]  67.00
## [286,]  69.00
## [287,]  96.00
## [288,] 125.00
## [289,]  18.00
## [290,]  55.00
## [291,]   9.00
## [292,]  19.00
## [293,]  34.00
## [294,]  37.00
## [295,]  36.00
## [296,]  22.00
## [297,]  68.00
## [298,]  26.00
## [299,]  57.00
## [300,] 111.00
## [301,]  61.00
## [302,]  74.00
## [303,]  52.00
## [304,]  20.00
## [305,]  21.00
## [306,]  77.00
## [307,]  20.00
## [308,]  24.00
## [309,]  18.00
## [310,]  31.00
## [311,]  43.00
## [312,]  31.00
## [313,]  42.00
## [314,]  43.00
## [315,]  29.00
## [316,] 149.00
## [317,]  74.00
## [318,] 129.00
## [319,] 105.00
## [320,]  72.00
## [321,]  39.00
## [322,]  45.00
## [323,]  48.00
## [324,]  51.00
## [325,]  29.00
## [326,]  38.00
## [327,]  33.00
## [328,]  30.00
## [329,]  22.00
## [330,]  26.00
## [331,]  16.00
## [332,]  11.00
## [333,]  14.00
## [334,]  14.00
## [335,]  28.00
## [336,]  25.00
## [337,]  10.00
## [338,]  28.00
## [339,]  35.00
## [340,]  34.00
## [341,]  58.00
## [342,]  83.00
## [343,]  71.00
## [344,]  95.00
## [345,]  39.00
## [346,]  24.00
## [347,]  23.00
## [348,]  46.00
## [349,]  66.00
## [350,]  14.00
## [351,]  21.00
## [352,]  35.00
## [353,]  33.00
## [354,]  22.00
## [355,]  40.00
## [356,]  30.00
## [357,]  31.00
## [358,]  36.00
## [359,]  24.00
## [360,]  13.00
## [361,]  22.00
## [362,]  21.00
## [363,]  15.00
## [364,]  12.00
## [365,]  25.00
## [366,] 176.00
## [367,]  99.00
## [368,]  88.00
## [369,]  52.00
## [370,]  51.00
## [371,]  28.00
## [372,]  13.00
## [373,]  38.00
## [374,]  21.00
## [375,]  36.00
## [376,]  13.00
## [377,]  21.00
## [378,]  31.00
## [379,]  34.00
## [380,]  57.00
## [381,]  25.00
## [382,]  15.00
## [383,]  80.00
## [384,]  38.00
## [385,] 128.00
## [386,]  35.00
## [387,]  24.00
## [388,]  19.00
## [389,]  17.00
## [390,]  28.00
## [391,]  75.00
## [392,]  97.00
## [393,]  57.00
## [394,]  75.00
## [395,]  82.00
## [396,]  45.00
## [397,]  12.00
## [398,]  23.00
## [399,]  22.00
## [400,]  29.00
## [401,]  32.00
## [402,]  72.00
## [403,]  14.00
## [404,]  11.00
## [405,]  20.00
## [406,]  16.00
## [407,]   5.00
## [408,]  25.00
## [409,]  31.00
## [410,]  48.00
## [411,] 133.00
## [412,]  44.00
## [413,]  81.00
## [414,]  71.00
## [415,]  41.00
## [416,]  50.00
## [417,]  22.00
## [418,]  17.00
## [419,]  48.00
## [420,]  46.00
## [421,]  17.00
## [422,]  25.00
## [423,]  17.00
## [424,]  25.00
## [425,]  73.00
## [426,]  40.00
## [427,]  33.00
## [428,]  27.00
## [429,]  26.00
## [430,]  77.00
## [431,] 117.00
## [432,]  63.00
## [433,]  41.00
## [434,]  32.00
## [435,]  30.00
## [436,]  78.00
## [437,]  56.00
## [438,]  76.00
## [439,]  25.00
## [440,]  15.00
## [441,]  80.00
## [442,]  89.00
## [443,]  35.00
## [444,]  33.00
## [445,]  20.00
## [446,]  35.00
## [447,]  25.00
## [448,]  28.00
## [449,]  24.00
## [450,]  49.00
## [451,]  50.00
## [452,]  25.00
## [453,]  41.00
## [454,]  24.00
## [455,]  19.00
## [456,]  35.00
## [457,]  26.00
## [458,]  11.00
## [459,]  28.00
## [460,]   6.00
## [461,]  15.00
## [462,]  32.00
## [463,]  23.00
## [464,]  32.00
## [465,]  41.00
## [466,]  46.00
## [467,]  43.00
## [468,]  19.00
## [469,]  34.00
## [470,]  15.00
## [471,]  27.00
## [472,]  25.00
## [473,]  39.00
## [474,]  27.00
## [475,]  82.00
## [476,]  35.00
## [477,]  37.89
## [478,]  31.91
## [479,]  24.00
## [480,]  45.00
## [481,]  16.00
## [482,]  30.00
## [483,]  43.00
## [484,] 179.00
## [485,] 155.00
## [486,]  41.00
## [487,]  58.00
## [488,]  48.00
## [489,]  71.00
## [490,]  34.00
## [491,]  26.00
## [492,]  29.00
## [493,]  29.00
## [494,]  24.00
## [495,]  22.00
## [496,]  53.00
## [497,]  17.00
## [498,]  17.00
## [499,]  15.00
## [500,]  20.00
## [501,]  22.00
## [502,]   6.00
## [503,]  17.00
## [504,]  17.00
## [505,]  66.00
## [506,]  24.00
## [507,]  44.00
## [508,]  39.00
## [509,]  34.00
## [510,]  37.00
## [511,]  23.00
## [512,]  33.00
## [513,]  28.00
## [514,]  26.00
## [515,]  33.00
## [516,]  27.00
## [517,]  38.00
## [518,]  41.00
## [519,]  31.00
## [520,]  24.00
## [521,]  24.00
## [522,]  25.00
## [523,]  70.00
## [524,]  83.00
## [525,]  36.00
## [526,]  50.00
## [527,]  21.00
## [528,]  26.00
## [529,]  17.00
## [530,]  40.00
## [531,]  49.00
## [532,]  57.00
## [533,]  62.00
## [534,]  34.00
## [535,]  31.00
## [536,]  21.00
## [537,]  51.00
## [538,]  36.00
## [539,]  28.00
## [540,]  23.00
## [541,]  20.00
## [542,]  19.00
## [543,]  16.00
## [544,]  62.00
## [545,]  36.33
## [546,]  29.00
## [547,]  35.00
## [548,]  35.00
## [549,]  63.00
## [550,]  68.00
## [551,]  14.00
## [552,]  35.00
## [553,]  60.00
## [554,]  53.00
## [555,]  39.00
## [556,]  47.00
## [557,]  44.00
## [558,]  23.00
## [559,]  38.00
## [560,]  40.00
## [561,]  38.00
## [562,]  55.00
## [563,]  45.00
## [564,]  46.00
## [565,]  26.00
## [566,]  40.00
## [567,]  34.00
## [568,]  17.00
## [569,]  32.00
## [570,]  40.00
## [571,]  23.00
## [572,]  22.00
## [573,]  24.00
## [574,]  29.00
## [575,]  22.00
## [576,]  29.00
## [577,]  39.00
## [578,]  26.00
## [579,]  40.00
## [580,]  14.00
## [581,]  19.00
## [582,]  14.00
## [583,]  15.00
## [584,]  13.00
## [585,]  46.00
## [586,]  36.00
## [587,]  22.00
## [588,]  29.00
## [589,]  17.00
## [590,]  19.00
## [591,]  26.00
## [592,]  26.00
## [593,]  21.00
## [594,]  19.00
## [595,]  31.00
## [596,]  43.00
## [597,]  31.00
## [598,]  41.00
## [599,]  40.00
## [600,]  46.00
## [601,]  38.00
## [602,]  51.00
## [603,]  37.00
## [604,]  30.00
## [605,]  24.00
## [606,]  22.00
## [607,]  23.00
## [608,]  10.00
## [609,]  11.00
## [610,]  11.00
## [611,]  26.00
## [612,]  26.00
## [613,]  21.00
## [614,]  20.00
## [615,]  22.00
## [616,]  13.00
## [617,]  16.00
## [618,]  15.00
## [619,]  34.00
## [620,]  41.00
## [621,]  28.00
## [622,]  23.00
## [623,]  44.00
## [624,]  30.00
## [625,]  29.00
## [626,]  89.00
## [627,]  27.00
## [628,]  49.00
## [629,]  30.00
## [630,]  44.00
## [631,]  22.00
## [632,]  14.00
## [633,]  17.00
## [634,]  19.00
## [635,]  14.00
## [636,]  15.00
## [637,]  15.00
## [638,]   9.00
## [639,]  24.00
## [640,]  10.00
## [641,]  34.00
## [642,]   8.00
## [643,]  15.00
## [644,]  20.00
## [645,]   5.00
## [646,]  19.00
## [647,]  22.00
## [648,]  65.00
## [649,]  51.00
## [650,] 110.00
## [651,]  50.00
## [652,]  74.00
## [653,]  68.00
## [654,]  34.00
## [655,]  21.00
## [656,]  19.00
## [657,]  28.00
## [658,]  19.00
## [659,]  13.00
## [660,]  14.00
## [661,]  22.00
## [662,]  26.00
## [663,]  21.00
## [664,]  26.00
## [665,]  42.00
## [666,]  38.00
## [667,]  27.00
## [668,]  26.00
## [669,]  18.00
## [670,]  31.00
## [671,]  26.00
## [672,]  39.00
## [673,]  33.00
## [674,]  21.00
## [675,]  23.00
## [676,]  26.00
## [677,]  18.00
## [678,]   5.00
## [679,]  12.00
## [680,]  14.00
## [681,]  13.00
## [682,]  18.00
## [683,]  12.00
## [684,]  21.00
## [685,]  19.00
## [686,]  19.00
## [687,]  22.00
## [688,]  17.00
## [689,]  10.00
## [690,]  14.00
## [691,]  16.00
## [692,]  10.00
## [693,]  11.00
## [694,]  12.00
## [695,]  15.00
## [696,]  52.00
## [697,]  87.00
## [698,]  46.00
## [699,]  35.00
## [700,]  38.00
## [701,]  44.00
## [702,]  18.00
## [703,]  56.00
## [704,]  46.00
## [705,]  64.00
## [706,]  34.00
## [707,]  63.00
## [708,]  15.00
## [709,]  47.00
## [710,]  12.00
## [711,]  10.00
## [712,]  15.00
## [713,]  19.00
## [714,]  27.00
## [715,]  18.00
## [716,]  30.00
## [717,]  28.00
## [718,]  20.00
## [719,]  23.00
## [720,]  10.00
## [721,]  11.00
## [722,]   8.00
## [723,]  25.00
## [724,]  60.00
## [725,]  67.00
## [726,]  30.00
## [727,]  72.00
## [728,]  46.00
## [729,]   7.00
## [730,]  20.00
plot.ts(Data_TSS_Sungai$TSS_Sungai, xlab="Date",ylab="Data")
points(Data_TSS_Sungai$TSS_Sungai)
par(col="pink")
lines(dugaan)

par(col="blue")

erorsma <- Data_TSS_Sungai$TSS_Sungai - fitted(arima.101y)[1:length(Data_TSS_Sungai$TSS_Sungai)]
SSE <- sum(erorsma[5:length(Data_TSS_Sungai$TSS_Sungai)]^2)
MSE <- mean(erorsma[5:length(Data_TSS_Sungai$TSS_Sungai)]^2)
MAPE<- mean(abs((erorsma[5:length(Data_TSS_Sungai$TSS_Sungai)]/Data_TSS_Sungai$TSS_Sungai[5:length(Data_TSS_Sungai$TSS_Sungai)])*100))

akurasi <- matrix(c(SSE, MSE, MAPE))
row.names(akurasi)<- c("SSE", "MSE", "MAPE")
colnames(akurasi) <- c("Akurasi")
akurasi
##      Akurasi
## SSE       NA
## MSE       NA
## MAPE      NA

Karena nilai Mape 69% sehingga kemampuan model untuk meramalakan tidak bagus. Sehingga bisa menggunakan analisis lain selain ARIMA, seperti metode SARIMA Adapun data yang diramal sebanyak 365 hari atau 1 tahun terlalu banyak, sehingga hasil ramalan tidak mendapat hasil yang optimal

Berikut contoh peramalan yang lebih lengkap https://rpubs.com/khusniank/ARIMARes7 https://rpubs.com/andikaputri/ARIMA https://rpubs.com/yossymaynaldi/ARIMA https://rpubs.com/novikaa08/745379 https://rpubs.com/dheapuspitadhea/kel15pertemuan8