Time-series moving average question

classic Classic list List threaded Threaded
7 messages Options
Reply | Threaded
Open this post in threaded view
|

Time-series moving average question

Bill Poling
Good morning, I hope someone can help with these questions, or perhaps suggest one of the other R-lists?

I have two questions:


  1.  Why am I getting this warning?
  2.  Why is the second example "Point Forecast" the same value, I do not see that in previous attempts with similar but different data sets as in example 1?

Example1:
dat3 <- structure(c(3539122.86, 3081383.87, 4158672.31, 4137518.78, 4123682.08, 4819375.2, 4342687.77, 5028674.58, 4472145.07, 4967277.73, 4516240.31, 4876194.63, 4816446.59,
                    4887399.37, 5478504.85, 4871385.27, 5487543.68, 5464193.69, 5252591.03, 7071416.89, 5524350.89, 6107166.69, 6530003.55, 6445929.08, 7356743.81, 6750025.03,
                    6934714.08, 6656194.35

                    ,-13913, -29385.31, -39633.37, -23487.13, -18202.86, -57335.49, -26061.45, -60880.07, -17589.45, -35970.08, -89133.94,
                    -84694.58, -31724.89, -29847.95, -65421.74, -34334.22, -48511.98, -30298.97, -38729.46, -29292.89, -46098.4, -65909.49,
                    -85879.23, -71845.28, -69017.07, -93161.03, -70847.29, -85106.04

                    ,-357694.19, -444792.75, -361349.57, -386717.55, -547422.05, -518259.22, -417613.76, -578631.46, -804516.81, -572875.52, -510487.53,
                    -666294.87, -673233.37, -556564.45, -963346.75, -639288.2, -910104.23, -773428.8, -1008078.84, -546685.3, -729932.94, -987098.23,
                    -964001.63, -986995.93, -680066.58, -728854.58, -730766.92, -753861.59)
                    ,.Dim = c(28L, 3L)
                    ,.Dimnames = list(NULL, c("OONNetRev","OONAdjusted" ,"OONCancelled"))
                    ,.Tsp = c(2016, 2018.25, 12), class = c("mts", "ts", "matrix"))
head(dat3); nrow(dat3)

TNR_moving_average <- forecast(ma(dat3[1:28], order=3), h=8)
TNR_moving_average

# Warning message:
#   In ets(object, lambda = lambda, biasadj = biasadj, allow.multiplicative.trend = allow.multiplicative.trend,  :
#            Missing values encountered. Using longest contiguous portion of time series
#          > Point Forecast         Lo 80         Hi 80         Lo 95         Hi 95
#         28  7007065.99688 6675015.72012 7339116.27365 6499238.92148 7514893.07229
#         29  7135745.42473 6721543.41996 7549947.42950 6502278.12345 7769212.72601
#         30  7264424.85258 6779532.18065 7749317.52450 6522845.50541 8006004.19974
#         31  7393104.28042 6844496.10189 7941712.45896 6554080.47486 8232128.08599
#         32  7521783.70827 6914203.11991 8129364.29663 6592569.38486 8450998.03168
#         33  7650463.13612 6987355.72657 8313570.54567 6636327.86794 8664598.40429
#         34  7779142.56396 7063123.29787 8495161.83005 6684085.59434 8874199.53358
#         35  7907821.99181 7140937.69145 8674706.29217 6734973.66528 9080670.31834




Example2:
dat3 <- structure(c(994320.58, 811664.54, 1045259.43, 951659.48, 669458.94, 986741.09, 1023344.82, 938971.65, 897670.06, 1040074.6, 1090310.01,
                    1289821.17, 1187806.23, 971485.76, 1161147.42, 870585.04, 1021301.52, 1215798.03, 1015004.43, 1365863.09, 995769.41,
                    1331725.36, 1271032.91, 1092103.82, 1297131.4, 1129195.28, 1372594.58, 1553717.57,

                    -39811.51, -47356.74, -49046.86, -41311.13, -79063.98, -43916.59, -16746.33, -38347.9, -84797.44, -38961.44,
                    -72036.83, -62854.78, -35259.84, -44198.39, -34262.65, -49245.82, -34977.28, -36797.35, -47534.43, -33515.13,
                    -25764.41, -29130.53, -57693.63, -51026.83, -49624.49, -36508.13, -32667.21, -37900.5,

                    -247443.87, -372942.34, -344080.78, -355586.21, -458998.84, -378086.44, -333994.18, -567024.45, -521499.8, -428915.13,
                    -512034.28, -440865.42, -347494.22, -422436.19, -444588.65, -462891.57, -518395.47, -373818.5, -398899.53, -381573.69,
                    -531449.2, -476238.48, -434296.86, -655679.94, -528999.52, -423725.95, -556977.31, -518633.95)
                  ,.Dim = c(28L, 3L)
                  ,.Dimnames = list(NULL, c("EditNetRev","EditNetAdjusted" ,"EditNetCancelled"))
                  ,.Tsp = c(2016, 2018.25, 12), class = c("mts", "ts", "matrix"))
head(dat3); nrow(dat3)



TNR_moving_average <- forecast(ma(dat3[1:28], order=3), h=8)
TNR_moving_average

# Warning message:
# In ets(object, lambda = lambda, biasadj = biasadj, allow.multiplicative.trend = allow.multiplicative.trend,  :
#          Missing values encountered. Using longest contiguous portion of time series
#        > TNR_moving_average
#        Point Forecast         Lo 80         Hi 80          Lo 95         Hi 95
#        28  1351827.24389 1246570.02118 1457084.46661 1190850.213255 1512804.27453
#        29  1351827.24389 1202841.21791 1500813.26987 1123972.779844 1579681.70794
#        30  1351827.24389 1169192.03201 1534462.45578 1072510.790913 1631143.69687
#        31  1351827.24389 1140745.29674 1562909.19105 1029005.263624 1674649.22416
#        32  1351827.24389 1115613.58783 1588040.89996  990569.631639 1713084.85615
#        33  1351827.24389 1092829.78856 1610824.69923  955724.817592 1747929.67020
#        34  1351827.24389 1071819.89899 1631834.58880  923592.964312 1780061.52348
#        35  1351827.24389 1052210.25675 1651444.23104  893602.604521 1810051.88327

Thank you for any advice or direction.


WHP



Confidentiality Notice This message is sent from Zelis. ...{{dropped:15}}

______________________________________________
[hidden email] 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.
Reply | Threaded
Open this post in threaded view
|

Re: Time-series moving average question

R help mailing list-2
My guess would be that if you inspect the output from
    ma(dat3[1:28], order=3)
you will find some NAs in it. And then forecast() doesn't like NAs.

But I can't check, because I can't find the ma() and forecast() functions. I assume they come from some package you installed; it would be helpful to say which package.

-Don

--
Don MacQueen
Lawrence Livermore National Laboratory
7000 East Ave., L-627
Livermore, CA 94550
925-423-1062
Lab cell 925-724-7509
 
 

On 6/1/18, 4:20 AM, "R-help on behalf of Bill Poling" <[hidden email] on behalf of [hidden email]> wrote:

    Good morning, I hope someone can help with these questions, or perhaps suggest one of the other R-lists?
   
    I have two questions:
   
   
      1.  Why am I getting this warning?
      2.  Why is the second example "Point Forecast" the same value, I do not see that in previous attempts with similar but different data sets as in example 1?
   
    Example1:
    dat3 <- structure(c(3539122.86, 3081383.87, 4158672.31, 4137518.78, 4123682.08, 4819375.2, 4342687.77, 5028674.58, 4472145.07, 4967277.73, 4516240.31, 4876194.63, 4816446.59,
                        4887399.37, 5478504.85, 4871385.27, 5487543.68, 5464193.69, 5252591.03, 7071416.89, 5524350.89, 6107166.69, 6530003.55, 6445929.08, 7356743.81, 6750025.03,
                        6934714.08, 6656194.35
   
                        ,-13913, -29385.31, -39633.37, -23487.13, -18202.86, -57335.49, -26061.45, -60880.07, -17589.45, -35970.08, -89133.94,
                        -84694.58, -31724.89, -29847.95, -65421.74, -34334.22, -48511.98, -30298.97, -38729.46, -29292.89, -46098.4, -65909.49,
                        -85879.23, -71845.28, -69017.07, -93161.03, -70847.29, -85106.04
   
                        ,-357694.19, -444792.75, -361349.57, -386717.55, -547422.05, -518259.22, -417613.76, -578631.46, -804516.81, -572875.52, -510487.53,
                        -666294.87, -673233.37, -556564.45, -963346.75, -639288.2, -910104.23, -773428.8, -1008078.84, -546685.3, -729932.94, -987098.23,
                        -964001.63, -986995.93, -680066.58, -728854.58, -730766.92, -753861.59)
                        ,.Dim = c(28L, 3L)
                        ,.Dimnames = list(NULL, c("OONNetRev","OONAdjusted" ,"OONCancelled"))
                        ,.Tsp = c(2016, 2018.25, 12), class = c("mts", "ts", "matrix"))
    head(dat3); nrow(dat3)
   
    TNR_moving_average <- forecast(ma(dat3[1:28], order=3), h=8)
    TNR_moving_average
   
    # Warning message:
    #   In ets(object, lambda = lambda, biasadj = biasadj, allow.multiplicative.trend = allow.multiplicative.trend,  :
    #            Missing values encountered. Using longest contiguous portion of time series
    #          > Point Forecast         Lo 80         Hi 80         Lo 95         Hi 95
    #         28  7007065.99688 6675015.72012 7339116.27365 6499238.92148 7514893.07229
    #         29  7135745.42473 6721543.41996 7549947.42950 6502278.12345 7769212.72601
    #         30  7264424.85258 6779532.18065 7749317.52450 6522845.50541 8006004.19974
    #         31  7393104.28042 6844496.10189 7941712.45896 6554080.47486 8232128.08599
    #         32  7521783.70827 6914203.11991 8129364.29663 6592569.38486 8450998.03168
    #         33  7650463.13612 6987355.72657 8313570.54567 6636327.86794 8664598.40429
    #         34  7779142.56396 7063123.29787 8495161.83005 6684085.59434 8874199.53358
    #         35  7907821.99181 7140937.69145 8674706.29217 6734973.66528 9080670.31834
   
   
   
   
    Example2:
    dat3 <- structure(c(994320.58, 811664.54, 1045259.43, 951659.48, 669458.94, 986741.09, 1023344.82, 938971.65, 897670.06, 1040074.6, 1090310.01,
                        1289821.17, 1187806.23, 971485.76, 1161147.42, 870585.04, 1021301.52, 1215798.03, 1015004.43, 1365863.09, 995769.41,
                        1331725.36, 1271032.91, 1092103.82, 1297131.4, 1129195.28, 1372594.58, 1553717.57,
   
                        -39811.51, -47356.74, -49046.86, -41311.13, -79063.98, -43916.59, -16746.33, -38347.9, -84797.44, -38961.44,
                        -72036.83, -62854.78, -35259.84, -44198.39, -34262.65, -49245.82, -34977.28, -36797.35, -47534.43, -33515.13,
                        -25764.41, -29130.53, -57693.63, -51026.83, -49624.49, -36508.13, -32667.21, -37900.5,
   
                        -247443.87, -372942.34, -344080.78, -355586.21, -458998.84, -378086.44, -333994.18, -567024.45, -521499.8, -428915.13,
                        -512034.28, -440865.42, -347494.22, -422436.19, -444588.65, -462891.57, -518395.47, -373818.5, -398899.53, -381573.69,
                        -531449.2, -476238.48, -434296.86, -655679.94, -528999.52, -423725.95, -556977.31, -518633.95)
                      ,.Dim = c(28L, 3L)
                      ,.Dimnames = list(NULL, c("EditNetRev","EditNetAdjusted" ,"EditNetCancelled"))
                      ,.Tsp = c(2016, 2018.25, 12), class = c("mts", "ts", "matrix"))
    head(dat3); nrow(dat3)
   
   
   
    TNR_moving_average <- forecast(ma(dat3[1:28], order=3), h=8)
    TNR_moving_average
   
    # Warning message:
    # In ets(object, lambda = lambda, biasadj = biasadj, allow.multiplicative.trend = allow.multiplicative.trend,  :
    #          Missing values encountered. Using longest contiguous portion of time series
    #        > TNR_moving_average
    #        Point Forecast         Lo 80         Hi 80          Lo 95         Hi 95
    #        28  1351827.24389 1246570.02118 1457084.46661 1190850.213255 1512804.27453
    #        29  1351827.24389 1202841.21791 1500813.26987 1123972.779844 1579681.70794
    #        30  1351827.24389 1169192.03201 1534462.45578 1072510.790913 1631143.69687
    #        31  1351827.24389 1140745.29674 1562909.19105 1029005.263624 1674649.22416
    #        32  1351827.24389 1115613.58783 1588040.89996  990569.631639 1713084.85615
    #        33  1351827.24389 1092829.78856 1610824.69923  955724.817592 1747929.67020
    #        34  1351827.24389 1071819.89899 1631834.58880  923592.964312 1780061.52348
    #        35  1351827.24389 1052210.25675 1651444.23104  893602.604521 1810051.88327
   
    Thank you for any advice or direction.
   
   
    WHP
   
   
   
    Confidentiality Notice This message is sent from Zelis. ...{{dropped:15}}
   
    ______________________________________________
    [hidden email] 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.
   

______________________________________________
[hidden email] 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.
Reply | Threaded
Open this post in threaded view
|

Re: Time-series moving average question

Bill Poling
Hello Don, thank you for your response. I appreciate your help.

I am using the forecast package, originally I found it following a forecasting example on bloggers.com

https://www.r-bloggers.com/time-series-analysis-using-r-forecast-package/

And subsequently located the complete pdf https://cran.r-project.org/web/packages/forecast/forecast.pdf

Since I created this practice data using the structure() function I am unsure why there would be NA’s as there are none apparently in the structure?

No worries though, I am going to reach out to the package author.

Cheers.

WHP

From: MacQueen, Don [mailto:[hidden email]]
Sent: Friday, June 01, 2018 11:24 AM
To: Bill Poling <[hidden email]>; r-help ([hidden email]) <[hidden email]>
Subject: Re: [R] Time-series moving average question

My guess would be that if you inspect the output from
ma(dat3[1:28], order=3)
you will find some NAs in it. And then forecast() doesn't like NAs.

But I can't check, because I can't find the ma() and forecast() functions. I assume they come from some package you installed; it would be helpful to say which package.

-Don

--
Don MacQueen
Lawrence Livermore National Laboratory
7000 East Ave., L-627
Livermore, CA 94550
925-423-1062
Lab cell 925-724-7509


______________________________________________
[hidden email]<mailto:[hidden email]> mailing list -- To UNSUBSCRIBE and more, see
https://stat.ethz.ch/mailman/listinfo/r-help<https://stat.ethz.ch/mailman/listinfo/r-help>
PLEASE do read the posting guide http://www.R-project.org/posting-guide.html<http://www.R-project.org/posting-guide.html>
and provide commented, minimal, self-contained, reproducible code.


Confidentiality Notice This message is sent from Zelis. This transmission may contain information which is privileged and confidential and is intended for the personal and confidential use of the named recipient only. Such information may be protected by applicable State and Federal laws from this disclosure or unauthorized use. If the reader of this message is not the intended recipient, or the employee or agent responsible for delivering the message to the intended recipient, you are hereby notified that any disclosure, review, discussion, copying, or taking any action in reliance on the contents of this transmission is strictly prohibited. If you have received this transmission in error, please contact the sender immediately. Zelis, 2018.

        [[alternative HTML version deleted]]

______________________________________________
[hidden email] 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.
Reply | Threaded
Open this post in threaded view
|

Re: Time-series moving average question

R help mailing list-2
You are right that there are no NAs in the practice data. But there are NAs in the moving average data.

To see this, break your work into two separate steps, like this:

  tnr.ma <- ma(dat3[1:28], order=3)
  TNR_moving_average <- forecast(tnr.ma, h=8)

I think you will find that the warning comes from the second step.

Print tnr.ma and you will see some NAs.

-Don

--
Don MacQueen
Lawrence Livermore National Laboratory
7000 East Ave., L-627
Livermore, CA 94550
925-423-1062
Lab cell 925-724-7509
 


From: Bill Poling <[hidden email]>
Date: Friday, June 1, 2018 at 8:58 AM
To: "MacQueen, Don" <[hidden email]>, array R-help <[hidden email]>
Subject: RE: [R] Time-series moving average question

Hello Don, thank you for your response. I appreciate your help.
 
I am using the forecast package, originally I found it following a forecasting example on bloggers.com
 
https://www.r-bloggers.com/time-series-analysis-using-r-forecast-package/
 
And subsequently located the complete pdf https://cran.r-project.org/web/packages/forecast/forecast.pdf
 
Since I created this practice data using the structure() function I am unsure why there would be NA’s as there are none apparently in the structure?
 
No worries though, I am going to reach out to the package author.
 
Cheers.
 
WHP
 
From: MacQueen, Don [mailto:[hidden email]]
Sent: Friday, June 01, 2018 11:24 AM
To: Bill Poling <[hidden email]>; r-help ([hidden email]) <[hidden email]>
Subject: Re: [R] Time-series moving average question
 
My guess would be that if you inspect the output from
ma(dat3[1:28], order=3)
you will find some NAs in it. And then forecast() doesn't like NAs.

But I can't check, because I can't find the ma() and forecast() functions. I assume they come from some package you installed; it would be helpful to say which package.

-Don

--
Don MacQueen
Lawrence Livermore National Laboratory
7000 East Ave., L-627
Livermore, CA 94550
925-423-1062
Lab cell 925-724-7509


______________________________________________
mailto:[hidden email] 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.



Confidentiality Notice This message is sent from Zelis. This transmission may contain information which is privileged and confidential and is intended for the personal and confidential use of the named recipient only. Such information may be protected by applicable State and Federal laws from this disclosure or unauthorized use. If the reader of this message is not the intended recipient, or the employee or agent responsible for delivering the message to the intended recipient, you are hereby notified that any disclosure, review, discussion, copying, or taking any action in reliance on the contents of this transmission is strictly prohibited. If you have received this transmission in error, please contact the sender immediately. Zelis, 2018.

______________________________________________
[hidden email] 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.
Reply | Threaded
Open this post in threaded view
|

Re: Time-series moving average question

Bill Poling
Hi Don, wow, you are so right. I picked that piece up from the bloggers tutorial and since I am R naive yet, I thought it was all one step

moving_average = forecast(ma(tdat[1:31], order=2), h=5)

Truly, I usually print and check at every step I can, as painful as it is sometimes.
Great lesson for this novice usR.

So the first and last values are NA in each case? Do you know why? Should I replace the NA with a value, say the average of the others?

Also, I have 5 series of data I am working with using this script and of course each gave me that warning, but only the one series had the same 8 Point Forecast values, is that coincidental you think?

Terrific of you to help, I really appreciate it.

WHP


From: MacQueen, Don [mailto:[hidden email]]
Sent: Friday, June 01, 2018 12:54 PM
To: Bill Poling <[hidden email]>; r-help ([hidden email]) <[hidden email]>
Subject: Re: [R] Time-series moving average question

You are right that there are no NAs in the practice data. But there are NAs in the moving average data.

To see this, break your work into two separate steps, like this:

tnr.ma<http://tnr.ma> <- ma(dat3[1:28], order=3)
TNR_moving_average <- forecast(tnr.ma<http://tnr.ma>, h=8)

I think you will find that the warning comes from the second step.

Print tnr.ma<http://tnr.ma> and you will see some NAs.

-Don

--
Don MacQueen
Lawrence Livermore National Laboratory
7000 East Ave., L-627
Livermore, CA 94550
925-423-1062
Lab cell 925-724-7509



From: Bill Poling <[hidden email]<mailto:[hidden email]>>
Date: Friday, June 1, 2018 at 8:58 AM
To: "MacQueen, Don" <[hidden email]<mailto:[hidden email]>>, array R-help <[hidden email]<mailto:[hidden email]>>
Subject: RE: [R] Time-series moving average question

Hello Don, thank you for your response. I appreciate your help.

I am using the forecast package, originally I found it following a forecasting example on bloggers.com<http://bloggers.com>

https://www.r-bloggers.com/time-series-analysis-using-r-forecast-package/<https://www.r-bloggers.com/time-series-analysis-using-r-forecast-package/>

And subsequently located the complete pdf https://cran.r-project.org/web/packages/forecast/forecast.pdf<https://cran.r-project.org/web/packages/forecast/forecast.pdf>

Since I created this practice data using the structure() function I am unsure why there would be NA’s as there are none apparently in the structure?

No worries though, I am going to reach out to the package author.

Cheers.

WHP

From: MacQueen, Don [mailto:[hidden email]]
Sent: Friday, June 01, 2018 11:24 AM
To: Bill Poling <[hidden email]<mailto:[hidden email]>>; r-help ([hidden email]<mailto:[hidden email]>) <[hidden email]<mailto:[hidden email]>>
Subject: Re: [R] Time-series moving average question

My guess would be that if you inspect the output from
ma(dat3[1:28], order=3)
you will find some NAs in it. And then forecast() doesn't like NAs.

But I can't check, because I can't find the ma() and forecast() functions. I assume they come from some package you installed; it would be helpful to say which package.

-Don

--
Don MacQueen
Lawrence Livermore National Laboratory
7000 East Ave., L-627
Livermore, CA 94550
925-423-1062
Lab cell 925-724-7509


______________________________________________
mailto:[hidden email] mailing list -- To UNSUBSCRIBE and more, see
https://stat.ethz.ch/mailman/listinfo/r-help<https://stat.ethz.ch/mailman/listinfo/r-help>
PLEASE do read the posting guide http://www.R-project.org/posting-guide.html<http://www.R-project.org/posting-guide.html>
and provide commented, minimal, self-contained, reproducible code.



Confidentiality Notice This message is sent from Zelis. This transmission may contain information which is privileged and confidential and is intended for the personal and confidential use of the named recipient only. Such information may be protected by applicable State and Federal laws from this disclosure or unauthorized use. If the reader of this message is not the intended recipient, or the employee or agent responsible for delivering the message to the intended recipient, you are hereby notified that any disclosure, review, discussion, copying, or taking any action in reliance on the contents of this transmission is strictly prohibited. If you have received this transmission in error, please contact the sender immediately. Zelis, 2018.

Confidentiality Notice This message is sent from Zelis. This transmission may contain information which is privileged and confidential and is intended for the personal and confidential use of the named recipient only. Such information may be protected by applicable State and Federal laws from this disclosure or unauthorized use. If the reader of this message is not the intended recipient, or the employee or agent responsible for delivering the message to the intended recipient, you are hereby notified that any disclosure, review, discussion, copying, or taking any action in reliance on the contents of this transmission is strictly prohibited. If you have received this transmission in error, please contact the sender immediately. Zelis, 2018.

        [[alternative HTML version deleted]]

______________________________________________
[hidden email] 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.
Reply | Threaded
Open this post in threaded view
|

Re: Time-series moving average question

R help mailing list-2
For your first question, you’re doing moving averages of 3 points (I assume that’s what order=3 does). For any given time point of your input data, that would be one before, one at, and one after the given time point. Do all of  your input times have both one before and one after?

Don’t know about your same 8 point forecast values question, not without running it myself, but I would say that if the data really is different, yet the forecasts are the same, it would have to be coincidental. But a priori this seems unlikely, so I’d inspect your script very carefully for mistakes.

-Don

--
Don MacQueen
Lawrence Livermore National Laboratory
7000 East Ave., L-627
Livermore, CA 94550
925-423-1062
Lab cell 925-724-7509



From: Bill Poling <[hidden email]>
Date: Friday, June 1, 2018 at 10:43 AM
To: "MacQueen, Don" <[hidden email]>, array R-help <[hidden email]>
Subject: RE: [R] Time-series moving average question

Hi Don, wow, you are so right. I picked that piece up from the bloggers tutorial and since I am R naive yet, I thought it was all one step

moving_average = forecast(ma(tdat[1:31], order=2), h=5)

Truly, I usually print and check at every step I can, as painful as it is sometimes.
Great lesson for this novice usR.

So the first and last values are NA in each case? Do you know why? Should I replace the NA with a value, say the average of the others?

Also, I have 5 series of data I am working with using this script and of course each gave me that warning, but only the one series had the same 8 Point Forecast values, is that coincidental you think?

Terrific of you to help, I really appreciate it.

WHP


From: MacQueen, Don [mailto:[hidden email]]
Sent: Friday, June 01, 2018 12:54 PM
To: Bill Poling <[hidden email]>; r-help ([hidden email]) <[hidden email]>
Subject: Re: [R] Time-series moving average question

You are right that there are no NAs in the practice data. But there are NAs in the moving average data.

To see this, break your work into two separate steps, like this:

tnr.ma<http://tnr.ma> <- ma(dat3[1:28], order=3)
TNR_moving_average <- forecast(tnr.ma<http://tnr.ma>, h=8)

I think you will find that the warning comes from the second step.

Print tnr.ma<http://tnr.ma> and you will see some NAs.

-Don

--
Don MacQueen
Lawrence Livermore National Laboratory
7000 East Ave., L-627
Livermore, CA 94550
925-423-1062
Lab cell 925-724-7509



From: Bill Poling <[hidden email]<mailto:[hidden email]>>
Date: Friday, June 1, 2018 at 8:58 AM
To: "MacQueen, Don" <[hidden email]<mailto:[hidden email]>>, array R-help <[hidden email]<mailto:[hidden email]>>
Subject: RE: [R] Time-series moving average question

Hello Don, thank you for your response. I appreciate your help.

I am using the forecast package, originally I found it following a forecasting example on bloggers.com<http://bloggers.com>

https://www.r-bloggers.com/time-series-analysis-using-r-forecast-package/

And subsequently located the complete pdf https://cran.r-project.org/web/packages/forecast/forecast.pdf

Since I created this practice data using the structure() function I am unsure why there would be NA’s as there are none apparently in the structure?

No worries though, I am going to reach out to the package author.

Cheers.

WHP

From: MacQueen, Don [mailto:[hidden email]]
Sent: Friday, June 01, 2018 11:24 AM
To: Bill Poling <[hidden email]<mailto:[hidden email]>>; r-help ([hidden email]<mailto:[hidden email]>) <[hidden email]<mailto:[hidden email]>>
Subject: Re: [R] Time-series moving average question

My guess would be that if you inspect the output from
ma(dat3[1:28], order=3)
you will find some NAs in it. And then forecast() doesn't like NAs.

But I can't check, because I can't find the ma() and forecast() functions. I assume they come from some package you installed; it would be helpful to say which package.

-Don

--
Don MacQueen
Lawrence Livermore National Laboratory
7000 East Ave., L-627
Livermore, CA 94550
925-423-1062
Lab cell 925-724-7509


______________________________________________
mailto:[hidden email] 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.



Confidentiality Notice This message is sent from Zelis. This transmission may contain information which is privileged and confidential and is intended for the personal and confidential use of the named recipient only. Such information may be protected by applicable State and Federal laws from this disclosure or unauthorized use. If the reader of this message is not the intended recipient, or the employee or agent responsible for delivering the message to the intended recipient, you are hereby notified that any disclosure, review, discussion, copying, or taking any action in reliance on the contents of this transmission is strictly prohibited. If you have received this transmission in error, please contact the sender immediately. Zelis, 2018.

Confidentiality Notice This message is sent from Zelis. This transmission may contain information which is privileged and confidential and is intended for the personal and confidential use of the named recipient only. Such information may be protected by applicable State and Federal laws from this disclosure or unauthorized use. If the reader of this message is not the intended recipient, or the employee or agent responsible for delivering the message to the intended recipient, you are hereby notified that any disclosure, review, discussion, copying, or taking any action in reliance on the contents of this transmission is strictly prohibited. If you have received this transmission in error, please contact the sender immediately. Zelis, 2018.

        [[alternative HTML version deleted]]

______________________________________________
[hidden email] 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.
Reply | Threaded
Open this post in threaded view
|

Re: Time-series moving average question

Bill Poling
Good morning Don, thank you for your support. I will give this all more investigation and submit my findings when finalized.

Cheers and thanks again for your help Sir.

WHP



From: MacQueen, Don [mailto:[hidden email]]
Sent: Friday, June 01, 2018 5:03 PM
To: Bill Poling <[hidden email]>; r-help ([hidden email]) <[hidden email]>
Subject: Re: [R] Time-series moving average question

For your first question, you’re doing moving averages of 3 points (I assume that’s what order=3 does). For any given time point of your input data, that would be one before, one at, and one after the given time point. Do all of  your input times have both one before and one after?

Don’t know about your same 8 point forecast values question, not without running it myself, but I would say that if the data really is different, yet the forecasts are the same, it would have to be coincidental. But a priori this seems unlikely, so I’d inspect your script very carefully for mistakes.

-Don

--
Don MacQueen
Lawrence Livermore National Laboratory
7000 East Ave., L-627
Livermore, CA 94550
925-423-1062
Lab cell 925-724-7509



From: Bill Poling <[hidden email]<mailto:[hidden email]>>
Date: Friday, June 1, 2018 at 10:43 AM
To: "MacQueen, Don" <[hidden email]<mailto:[hidden email]>>, array R-help <[hidden email]<mailto:[hidden email]>>
Subject: RE: [R] Time-series moving average question

Hi Don, wow, you are so right. I picked that piece up from the bloggers tutorial and since I am R naive yet, I thought it was all one step

moving_average = forecast(ma(tdat[1:31], order=2), h=5)

Truly, I usually print and check at every step I can, as painful as it is sometimes.
Great lesson for this novice usR.

So the first and last values are NA in each case? Do you know why? Should I replace the NA with a value, say the average of the others?

Also, I have 5 series of data I am working with using this script and of course each gave me that warning, but only the one series had the same 8 Point Forecast values, is that coincidental you think?

Terrific of you to help, I really appreciate it.

WHP


From: MacQueen, Don [mailto:[hidden email]]
Sent: Friday, June 01, 2018 12:54 PM
To: Bill Poling <[hidden email]<mailto:[hidden email]>>; r-help ([hidden email]<mailto:[hidden email]>) <[hidden email]<mailto:[hidden email]>>
Subject: Re: [R] Time-series moving average question

You are right that there are no NAs in the practice data. But there are NAs in the moving average data.

To see this, break your work into two separate steps, like this:

tnr.ma<http://tnr.ma> <- ma(dat3[1:28], order=3)
TNR_moving_average <- forecast(tnr.ma<http://tnr.ma>, h=8)

I think you will find that the warning comes from the second step.

Print tnr.ma<http://tnr.ma> and you will see some NAs.

-Don

--
Don MacQueen
Lawrence Livermore National Laboratory
7000 East Ave., L-627
Livermore, CA 94550
925-423-1062
Lab cell 925-724-7509



From: Bill Poling <[hidden email]<mailto:[hidden email]>>
Date: Friday, June 1, 2018 at 8:58 AM
To: "MacQueen, Don" <[hidden email]<mailto:[hidden email]>>, array R-help <[hidden email]<mailto:[hidden email]>>
Subject: RE: [R] Time-series moving average question

Hello Don, thank you for your response. I appreciate your help.

I am using the forecast package, originally I found it following a forecasting example on bloggers.com<http://bloggers.com>

https://www.r-bloggers.com/time-series-analysis-using-r-forecast-package/<https://www.r-bloggers.com/time-series-analysis-using-r-forecast-package/>

And subsequently located the complete pdf https://cran.r-project.org/web/packages/forecast/forecast.pdf<https://cran.r-project.org/web/packages/forecast/forecast.pdf>

Since I created this practice data using the structure() function I am unsure why there would be NA’s as there are none apparently in the structure?

No worries though, I am going to reach out to the package author.

Cheers.

WHP

From: MacQueen, Don [mailto:[hidden email]]
Sent: Friday, June 01, 2018 11:24 AM
To: Bill Poling <[hidden email]<mailto:[hidden email]>>; r-help ([hidden email]<mailto:[hidden email]>) <[hidden email]<mailto:[hidden email]>>
Subject: Re: [R] Time-series moving average question

My guess would be that if you inspect the output from
ma(dat3[1:28], order=3)
you will find some NAs in it. And then forecast() doesn't like NAs.

But I can't check, because I can't find the ma() and forecast() functions. I assume they come from some package you installed; it would be helpful to say which package.

-Don

--
Don MacQueen
Lawrence Livermore National Laboratory
7000 East Ave., L-627
Livermore, CA 94550
925-423-1062
Lab cell 925-724-7509


______________________________________________
mailto:[hidden email] mailing list -- To UNSUBSCRIBE and more, see
https://stat.ethz.ch/mailman/listinfo/r-help<https://stat.ethz.ch/mailman/listinfo/r-help>
PLEASE do read the posting guide http://www.R-project.org/posting-guide.html<http://www.R-project.org/posting-guide.html>
and provide commented, minimal, self-contained, reproducible code.



Confidentiality Notice This message is sent from Zelis. This transmission may contain information which is privileged and confidential and is intended for the personal and confidential use of the named recipient only. Such information may be protected by applicable State and Federal laws from this disclosure or unauthorized use. If the reader of this message is not the intended recipient, or the employee or agent responsible for delivering the message to the intended recipient, you are hereby notified that any disclosure, review, discussion, copying, or taking any action in reliance on the contents of this transmission is strictly prohibited. If you have received this transmission in error, please contact the sender immediately. Zelis, 2018.

Confidentiality Notice This message is sent from Zelis. This transmission may contain information which is privileged and confidential and is intended for the personal and confidential use of the named recipient only. Such information may be protected by applicable State and Federal laws from this disclosure or unauthorized use. If the reader of this message is not the intended recipient, or the employee or agent responsible for delivering the message to the intended recipient, you are hereby notified that any disclosure, review, discussion, copying, or taking any action in reliance on the contents of this transmission is strictly prohibited. If you have received this transmission in error, please contact the sender immediately. Zelis, 2018.

Confidentiality Notice This message is sent from Zelis. This transmission may contain information which is privileged and confidential and is intended for the personal and confidential use of the named recipient only. Such information may be protected by applicable State and Federal laws from this disclosure or unauthorized use. If the reader of this message is not the intended recipient, or the employee or agent responsible for delivering the message to the intended recipient, you are hereby notified that any disclosure, review, discussion, copying, or taking any action in reliance on the contents of this transmission is strictly prohibited. If you have received this transmission in error, please contact the sender immediately. Zelis, 2018.

        [[alternative HTML version deleted]]

______________________________________________
[hidden email] 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.