Linear_SVM_Census_6512_results.txt

fevd(x = aa, threshold = t, type = type_name, units = "Time", 
    time.units = "days", period.basis = "1 unit = 365 sample")

[1] "Estimation Method used: MLE"


 Negative Log-Likelihood Value:  244.8948 


 Estimated parameters:
      scale       shape 
18.75897210  0.00000001 

 Standard Error Estimates:
     scale      shape 
1.95402544 0.06331569 

 Estimated parameter covariance matrix.
           scale        shape
scale  3.8182154 -0.038330103
shape -0.0383301  0.004008877

 AIC = 493.7896 

 BIC = 498.2286 
[1] "the length of array 0 is 148"
[1] "threshold_0 is :  250.172"
[1] "num. items over threshold t :  68"
[1] "computation time 2.471923828125"
[1] "The mean and std=: 177.851351351351" "The mean and std=: 115.625640384778"
[1] "The error for mean and std: 9.50436909289549" "The error for mean and std: 6.72060383648623"
fevd(x = aa, threshold = t, type = type_name, units = "Time", 
    time.units = "days", period.basis = "1 unit = 365 sample")

[1] "Normal Approx."

                                                  95% lower CI Estimate 95% upper CI
1.36986301369863-1 unit = 365 sample return level     318.2976 352.1756     386.0536
2.73972602739726-1 unit = 365 sample return level     320.5147 365.1783     409.8419
5.47945205479452-1 unit = 365 sample return level     325.0352 378.1810     431.3268
13.6986301369863-1 unit = 365 sample return level     328.5719 395.3697     462.1675
27.3972602739726-1 unit = 365 sample return level     328.2002 408.3724     488.5447
54.7945205479452-1 unit = 365 sample return level     330.4538 421.3752     512.2965
136.986301369863-1 unit = 365 sample return level     324.4965 438.5638     552.6312

fevd(x = aa, threshold = t, type = type_name, units = "Time", 
    time.units = "days", period.basis = "1 unit = 365 sample")

[1] "Normal Approx."

                                                  95% lower CI Estimate 95% upper CI
1.36986301369863-1 unit = 365 sample return level     318.2976 352.1756     386.0536
2.73972602739726-1 unit = 365 sample return level     320.5147 365.1783     409.8419
5.47945205479452-1 unit = 365 sample return level     325.0352 378.1810     431.3268
13.6986301369863-1 unit = 365 sample return level     328.5719 395.3697     462.1675
27.3972602739726-1 unit = 365 sample return level     328.2002 408.3724     488.5447
54.7945205479452-1 unit = 365 sample return level     330.4538 421.3752     512.2965
136.986301369863-1 unit = 365 sample return level     324.4965 438.5638     552.6312

[1] "--------------------------"
There were 50 or more warnings (use warnings() to see the first 50)
> 
> print("Bayesian Factor Method:")
[1] "Bayesian Factor Method:"
> print(ind)
[1] 148
> print(max_index)
[1] 56
> print(max_observed)
[1] 401
> print("--------------------------")
[1] "--------------------------"
> print("Actual observed Time:")
[1] "Actual observed Time:"
> # what are actual timing after these steps:
> for(i in c(500, 1000, 2000, 3000, 4000, 5000, 10000))
+ {
+   print(i)
+   print(max(a$V1[1:i], na.rm = TRUE))
+ }
[1] 500
[1] 401
[1] 1000
[1] 538
[1] 2000
[1] 538
[1] 3000
[1] 538
[1] 4000
[1] 538
[1] 5000
[1] 538
[1] 10000
[1] 538