[R] Forecasting tutorial "Basic Forecasting"

[Huzefa Khalil]

Instead of

Tsp = c(2016, 2018, 12)

try

Tsp = c(2016, 2018.25, 12)

Hence, you can specify the object as

structure(c(5973156.76, 5159011.2, 6695766.64, 6365359, 6495218.53,
7226302.39, 6835272.7, 7383501.57, 6962748.19, 7623278.72, 7274994.33,
7919421.8, 7360740.81, 7436693.35, 8545765.55, 7337269.76, 8180585.44,
8376635.05, 7758261.24, 10374641.22, 8000314.11, 9114958.9, 9805149.15,
9336939.45, 10273849.1, 9159308.71, 10184703.33, 10251153.52,
-52340.21, -90911.29, -90135.33, -147196.03, -112831.26, -99443.31,
-72584.09, -161869.48, -117805.41, -81102.39, -175379.25, -190596.12,
-110838.08, -127953.99, -129414.01, -131570.11, -28814.27, -63066.4,
-134587.17, -27610.96, -169293.37, -144034.7, -193376.36, -135743.08,
-151767.63, -156816.35, -113074.01, -160705.61, -700973.75, -891171.15,
-805670.71, -821222.02, -1078184.45, -980080.81, -786506.89,
-1244278.5, -1392779.81, -1186436.41, -1108016.28, -1201663.88,
-1163848.16, -1028830.6, -1507572.01, -1210422.01, -1529691.9,
-1207461.55, -1615971.18, -978028.1, -1354515.28, -1624270.48,
-1596204.33, -1836731.26, -1310376.81, -1337718.49, -1492220.98,
-1421801.16), .Dim = c(28L, 3L), .Dimnames = list(NULL, c("TotalNetRev",
"TotalRevAdjusted", "TotalRevCancelled")), .Tsp = c(2016, 2018.25,
12), class = c("mts", "ts", "matrix"))

You were correct that the error was because of 28 time-points. This is
the fix for it.

Huzefa

On Tue, May 15, 2018 at 2:08 PM, Bill Poling <Bill.Poling using zelis.com> wrote:
> Hi. I am trying to follow this forecasting tutorial at: https://www.r-bloggers.com/basic-forecasting/
>
> Using my own data, I cannot get past the first step, lots of laughs.
>
> dat3 <- structure(c(5973156.76, 5159011.20,  6695766.64,  6365359.00,  6495218.53,  7226302.39,  6835272.70,  7383501.57,  6962748.19,  7623278.72,  7274994.33
>                     ,7919421.80,  7360740.81,  7436693.35, 8545765.55,  7337269.76,  8180585.44,  8376635.05,  7758261.24, 10374641.22,  8000314.11,  9114958.90
>                     ,9805149.15,  9336939.45, 10273849.10,  9159308.71, 10184703.33, 10251153.52
>                     ,-52340.21,  -90911.29,  -90135.33, -147196.03, -112831.26,  -99443.31,  -72584.09, -161869.48, -117805.41,  -81102.39, -175379.25, -190596.12
>                     ,-110838.08, -127953.99, -129414.01, -131570.11,  -28814.27,  -63066.40, -134587.17,  -27610.96, -169293.37, -144034.70, -193376.36, -135743.08
>                     ,-151767.63, -156816.35, -113074.01, -160705.61
>                     ,-700973.75,  -891171.15,  -805670.71,  -821222.02, -1078184.45,  -980080.81,  -786506.89, -1244278.50, -1392779.81, -1186436.41, -1108016.28
>                     ,-1201663.88, -1163848.16, -1028830.60, -1507572.01, -1210422.01, -1529691.90, -1207461.55, -1615971.18,  -978028.10, -1354515.28, -1624270.48
>                     , -1596204.33, -1836731.26, -1310376.81, -1337718.49, -1492220.98, -1421801.16)
>                     ,.Dim = c(28L, 3L)
>                     ,.Dimnames = list(NULL, c("TotalNetRev","TotalRevAdjusted" ,"TotalRevCancelled"))
>                     ,.Tsp = c(2016, 2018, 12)
>                    , class = c("mts", "ts", "matrix"))
>
> Error in attributes(.Data) <- c(attributes(.Data), attrib) :
>   invalid time series parameters specified
>
> I think the error may be due to 28 months of data, complete 2016 & 2017 but only 4 months in 2018 and my Tsp is a value of 12? If so how would I adjust?
>
> I have googled a few references for the error, but the solution is not clear to me.
> https://stackoverflow.com/questions/32369737/error-invalid-time-series-parameters-specified-in-backtesting-r-script
> http://r.789695.n4.nabble.com/How-to-setup-the-tsp-attribute-of-a-dataset-td908269.html
>
> Thanks for any advice.
>
> WHP
>
>
> Confidentiality Notice This message is sent from Zelis. ...{{dropped:15}}
>
> ______________________________________________
> R-help using r-project.org mailing list -- To UNSUBSCRIBE and more, see
> https://stat.ethz.ch/mailman/listinfo/r-help
> PLEASE do read the posting guide http://www.R-project.org/posting-guide.html
> and provide commented, minimal, self-contained, reproducible code.