lmom package - Resending the email

Previous Topic Next Topic
 
classic Classic list List threaded Threaded
4 messages Options
Reply | Threaded
Open this post in threaded view
|

lmom package - Resending the email

R help mailing list-2
Dear R forum
I sincerely apologize as my earlier mail with the captioned subject, since all the values got mixed up and the email is not readable. I am trying to write it again. 
My problem is I have a set of data and I am trying to fit some distributions to it. As a part of this exercise, I need to find out the parameter values of various distributions e.g. Normal distribution, Log normal distribution etc. I am using lmom package to do the same, however the parameter values obtained using lmom pacakge differ to a large extent from the parameter values obtained using say MINITAB and SPSS as given below -
_____________________________________________

amounts =  c(38572.5599129508,11426.6705314315,21974.1571641187,118530.32782443,3735.43055996748,66309.5211176106,72039.2934132668,21934.8841708626,78564.9136114375,1703.65825161293,2116.89180930203,11003.495671332,19486.3296339113,1871.35861218795,6887.53851253407,148900.978055447,7078.56497101651,79348.1239806592,20157.6241066905,1259.99802108593,3934.45912233674,3297.69946631591,56221.1154121067,13322.0705174134,45110.2498756567,31910.3686613912,3196.71168501252,32843.0140437202,14615.1499458453,13013.9915051561,116104.176753387,7229.03056392023,9833.37962177814,2882.63239493673,165457.372543821,41114.066453219,47188.1677766245,25708.5883755617,82703.7378298092,8845.04197017415,844.28834047836,35410.8486123933,19446.3808445684,17662.2398792892,11882.8497070776,4277181.17817307,30239.0371267968,45165.7512343364,22102.8513746687,5988.69296597127,51345.0146170238,1275658.35495898,15260.4892854214,8861.76578480635,37647.1638704867,4979.53544046949,7012.48134772332,3385.20612391205,1911.03114395959,66886.5036605189,2223.47536156462,814.947809578378,234.028589468841,5397.4347625133,13346.3226579065,28809.3901352898,6387.69226236731,5639.42730553242,2011100.92675507,4150.63707173462,34098.7514446498,3437.10672573502,289710.315303182,8664.66947305203,13813.3867161134,208817.521491857,169317.624400274,9966.78447705792,37811.1721605562,2263.19211279927,80434.5581206454,19057.8093104899,24664.5067589624,25136.5042354789,3582.85741610706,6683.13898432794,65423.9991390846,134848.302304064,3018.55371579808,546249.641168158,172926.689143006,3074.15064180208,1521.70624812788,59012.4248281661,21226.928522236,17572.5682970983,226.646947337851,56232.2982652019,14641.0043361533,6997.94414914865)

library(lmom)
lmom  =  samlmu(amounts)
# __________________________________________________________________
# Normal Distribution parameters
parameters_of_NOR  <- pelnor(lmom); parameters_of_NOR

      mu          sigma 115148.4    175945.8
                      Location       Scale     Minitab         115148.4     485173SPSS           115148.4     485173
# __________________________________________________________________
# Log Normal (3 Parameter) Distribution parameters
       zeta                mu               sigma 3225.798890    9.114879      2.240841
                              Location            Scale           Shape
MINITAB               9.73361             1.76298      75.51864SPSS                    9.7336                1.763          75.519           # __________________________________________________________________

Besides Genaralized extreme Value distributions, all the other distributions e.g. Gamma, Exponential (2 parameter) distributions etc give different results than MINITAB and SPSS.
Can some one guide me?

Regards
Katherine











































        [[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: lmom package - Resending the email

szehnder@uni-bonn.de
Katherine,

for a deeper understanding of differing values it makes sense to provide the list at least with an online description of the corresponding functions used in Minitab and SPSS…

Best
Simon
On 03 Dec 2014, at 10:45, Katherine Gobin via R-help <[hidden email]> wrote:

> Dear R forum
> I sincerely apologize as my earlier mail with the captioned subject, since all the values got mixed up and the email is not readable. I am trying to write it again.
> My problem is I have a set of data and I am trying to fit some distributions to it. As a part of this exercise, I need to find out the parameter values of various distributions e.g. Normal distribution, Log normal distribution etc. I am using lmom package to do the same, however the parameter values obtained using lmom pacakge differ to a large extent from the parameter values obtained using say MINITAB and SPSS as given below -
> _____________________________________________
>
> amounts =  c(38572.5599129508,11426.6705314315,21974.1571641187,118530.32782443,3735.43055996748,66309.5211176106,72039.2934132668,21934.8841708626,78564.9136114375,1703.65825161293,2116.89180930203,11003.495671332,19486.3296339113,1871.35861218795,6887.53851253407,148900.978055447,7078.56497101651,79348.1239806592,20157.6241066905,1259.99802108593,3934.45912233674,3297.69946631591,56221.1154121067,13322.0705174134,45110.2498756567,31910.3686613912,3196.71168501252,32843.0140437202,14615.1499458453,13013.9915051561,116104.176753387,7229.03056392023,9833.37962177814,2882.63239493673,165457.372543821,41114.066453219,47188.1677766245,25708.5883755617,82703.7378298092,8845.04197017415,844.28834047836,35410.8486123933,19446.3808445684,17662.2398792892,11882.8497070776,4277181.17817307,30239.0371267968,45165.7512343364,22102.8513746687,5988.69296597127,51345.0146170238,1275658.35495898,15260.4892854214,8861.76578480635,37647.1638704867,4979.53544046949,7012.48134772332,3385.20612391205,1911.03114395959,66886.5036605189,2223.47536156462,814.947809578378,234.028589468841,5397.4347625133,13346.3226579065,28809.3901352898,6387.69226236731,5639.42730553242,2011100.92675507,4150.63707173462,34098.7514446498,3437.10672573502,289710.315303182,8664.66947305203,13813.3867161134,208817.521491857,169317.624400274,9966.78447705792,37811.1721605562,2263.19211279927,80434.5581206454,19057.8093104899,24664.5067589624,25136.5042354789,3582.85741610706,6683.13898432794,65423.9991390846,134848.302304064,3018.55371579808,546249.641168158,172926.689143006,3074.15064180208,1521.70624812788,59012.4248281661,21226.928522236,17572.5682970983,226.646947337851,56232.2982652019,14641.0043361533,6997.94414914865)
>
> library(lmom)
> lmom  =  samlmu(amounts)
> # __________________________________________________________________
> # Normal Distribution parameters
> parameters_of_NOR  <- pelnor(lmom); parameters_of_NOR
>
>       mu          sigma 115148.4    175945.8
>                       Location       Scale     Minitab         115148.4     485173SPSS           115148.4     485173
> # __________________________________________________________________
> # Log Normal (3 Parameter) Distribution parameters
>        zeta                mu               sigma 3225.798890    9.114879      2.240841
>                               Location            Scale           Shape
> MINITAB               9.73361             1.76298      75.51864SPSS                    9.7336                1.763          75.519           # __________________________________________________________________
>
> Besides Genaralized extreme Value distributions, all the other distributions e.g. Gamma, Exponential (2 parameter) distributions etc give different results than MINITAB and SPSS.
> Can some one guide me?
>
> Regards
> Katherine
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
> [[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.

______________________________________________
[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: lmom package - Resending the email

Peter Dalgaard-2
lmom is based on L-moments, which are different from ordinary moments, except for the 1st one. It would be truly miraculous if it gave the same result as the ordinary method of moments or maximum likelihood.

Estimates of any distributional parameter requires that the model actually fits the data, and in your case a qqnorm(amounts) shows that they are certainly not normal. In such cases, the L-moment estimator of the std.dev. is not necessarily an estimate of the std.dev. of the actual distribution.

A lognormal distribution seems to fit the data better. However, the L-moments suggest a value for zeta (the lower bound) of 3226 which is well inside the range of the actual data. In fact there are 16 observations that are less than 3226. Maximum likelihood would never do that, but the same sort of effect is well-known for the ordinary method of moments.

In short, you need to study the theory before you appply its results.

- Peter D.


On 03 Dec 2014, at 10:57 , Simon Zehnder <[hidden email]> wrote:

> Katherine,
>
> for a deeper understanding of differing values it makes sense to provide the list at least with an online description of the corresponding functions used in Minitab and SPSS…
>
> Best
> Simon
> On 03 Dec 2014, at 10:45, Katherine Gobin via R-help <[hidden email]> wrote:
>
>> Dear R forum
>> I sincerely apologize as my earlier mail with the captioned subject, since all the values got mixed up and the email is not readable. I am trying to write it again.
>> My problem is I have a set of data and I am trying to fit some distributions to it. As a part of this exercise, I need to find out the parameter values of various distributions e.g. Normal distribution, Log normal distribution etc. I am using lmom package to do the same, however the parameter values obtained using lmom pacakge differ to a large extent from the parameter values obtained using say MINITAB and SPSS as given below -
>> _____________________________________________
>>
>> amounts =  c(38572.5599129508,11426.6705314315,21974.1571641187,118530.32782443,3735.43055996748,66309.5211176106,72039.2934132668,21934.8841708626,78564.9136114375,1703.65825161293,2116.89180930203,11003.495671332,19486.3296339113,1871.35861218795,6887.53851253407,148900.978055447,7078.56497101651,79348.1239806592,20157.6241066905,1259.99802108593,3934.45912233674,3297.69946631591,56221.1154121067,13322.0705174134,45110.2498756567,31910.3686613912,3196.71168501252,32843.0140437202,14615.1499458453,13013.9915051561,116104.176753387,7229.03056392023,9833.37962177814,2882.63239493673,165457.372543821,41114.066453219,47188.1677766245,25708.5883755617,82703.7378298092,8845.04197017415,844.28834047836,35410.8486123933,19446.3808445684,17662.2398792892,11882.8497070776,4277181.17817307,30239.0371267968,45165.7512343364,22102.8513746687,5988.69296597127,51345.0146170238,1275658.35495898,15260.4892854214,8861.76578480635,37647.1638704867,4979.53544046949,7012.48134772332,3385.20612391205,1911.03114395959,66886.5036605189,2223.47536156462,814.947809578378,234.028589468841,5397.4347625133,13346.3226579065,28809.3901352898,6387.69226236731,5639.42730553242,2011100.92675507,4150.63707173462,34098.7514446498,3437.10672573502,289710.315303182,8664.66947305203,13813.3867161134,208817.521491857,169317.624400274,9966.78447705792,37811.1721605562,2263.19211279927,80434.5581206454,19057.8093104899,24664.5067589624,25136.5042354789,3582.85741610706,6683.13898432794,65423.9991390846,134848.302304064,3018.55371579808,546249.641168158,172926.689143006,3074.15064180208,1521.70624812788,59012.4248281661,21226.928522236,17572.5682970983,226.646947337851,56232.2982652019,14641.0043361533,6997.94414914865)
>>
>> library(lmom)
>> lmom  =  samlmu(amounts)
>> # __________________________________________________________________
>> # Normal Distribution parameters
>> parameters_of_NOR  <- pelnor(lmom); parameters_of_NOR
>>
>>      mu          sigma 115148.4    175945.8
>>                      Location       Scale     Minitab         115148.4     485173SPSS           115148.4     485173
>> # __________________________________________________________________
>> # Log Normal (3 Parameter) Distribution parameters
>>       zeta                mu               sigma 3225.798890    9.114879      2.240841
>>                              Location            Scale           Shape
>> MINITAB               9.73361             1.76298      75.51864SPSS                    9.7336                1.763          75.519           # __________________________________________________________________
>>
>> Besides Genaralized extreme Value distributions, all the other distributions e.g. Gamma, Exponential (2 parameter) distributions etc give different results than MINITAB and SPSS.
>> Can some one guide me?
>>
>> Regards
>> Katherine
>>
>>
>>
>>
>>
>>
>>
>>
>>
>>
>>
>>
>>
>>
>>
>>
>>
>>
>>
>>
>>
>>
>>
>>
>>
>>
>>
>>
>>
>>
>>
>>
>>
>>
>>
>>
>>
>>
>>
>>
>>
>>
>>
>> [[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.
>
> ______________________________________________
> [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.

--
Peter Dalgaard, Professor,
Center for Statistics, Copenhagen Business School
Solbjerg Plads 3, 2000 Frederiksberg, Denmark
Phone: (+45)38153501
Email: [hidden email]  Priv: [hidden email]

______________________________________________
[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: lmom package - Resending the email

Katherine Gobin
Dear Dalgaard sir,


Thanks a lot for detailed clarification. It indeed is very enlightening and will be very useful for me in future.

And your suggestion is well taken.

Thanks again.

Regards

Katherine

--------------------------------------------
On Thu, 4/12/14, peter dalgaard <[hidden email]> wrote:

 Subject: Re: [R] lmom package - Resending the email
 To: "Simon Zehnder" <[hidden email]>

<[hidden email]>
 Date: Thursday, 4 December, 2014, 2:04 PM

 lmom is based on
 L-moments, which are different from ordinary moments, except
 for the 1st one. It would be truly miraculous if it gave the
 same result as the ordinary method of moments or maximum
 likelihood.

 Estimates of
 any distributional parameter requires that the model
 actually fits the data, and in your case a qqnorm(amounts)
 shows that they are certainly not normal. In such cases, the
 L-moment estimator of the std.dev. is not necessarily an
 estimate of the std.dev. of the actual distribution.

 A lognormal distribution seems
 to fit the data better. However, the L-moments suggest a
 value for zeta (the lower bound) of 3226 which is well
 inside the range of the actual data. In fact there are 16
 observations that are less than 3226. Maximum likelihood
 would never do that, but the same sort of effect is
 well-known for the ordinary method of moments.

 In short, you need to study
 the theory before you appply its results.

 - Peter D.


 On 03 Dec 2014, at 10:57 ,
 Simon Zehnder <[hidden email]>
 wrote:

 > Katherine,
 >
 > for a deeper
 understanding of differing values it makes sense to provide
 the list at least with an online description of the
 corresponding functions used in Minitab and SPSS…
 >
 > Best
 > Simon
 > On 03 Dec 2014,
 at 10:45, Katherine Gobin via R-help <[hidden email]>
 wrote:
 >
 >> Dear R
 forum
 >> I sincerely apologize as my
 earlier mail with the captioned subject, since all the
 values got mixed up and the email is not readable. I am
 trying to write it again.
 >> My
 problem is I have a set of data and I am trying to fit some
 distributions to it. As a part of this exercise, I need to
 find out the parameter values of various distributions e.g.
 Normal distribution, Log normal distribution etc. I am using
 lmom package to do the same, however the parameter values
 obtained using lmom pacakge differ to a large extent from
 the parameter values obtained using say MINITAB and SPSS as
 given below -
 >>
 _____________________________________________
 >>
 >> amounts = 
 c(38572.5599129508,11426.6705314315,21974.1571641187,118530.32782443,3735.43055996748,66309.5211176106,72039.2934132668,21934.8841708626,78564.9136114375,1703.65825161293,2116.89180930203,11003.495671332,19486.3296339113,1871.35861218795,6887.53851253407,148900.978055447,7078.56497101651,79348.1239806592,20157.6241066905,1259.99802108593,3934.45912233674,3297.69946631591,56221.1154121067,13322.0705174134,45110.2498756567,31910.3686613912,3196.71168501252,32843.0140437202,14615.1499458453,13013.9915051561,116104.176753387,7229.03056392023,9833.37962177814,2882.63239493673,165457.372543821,41114.066453219,47188.1677766245,25708.5883755617,82703.7378298092,8845.04197017415,844.28834047836,35410.8486123933,19446.3808445684,17662.2398792892,11882.8497070776,4277181.17817307,30239.0371267968,45165.7512343364,22102.8513746687,5988.69296597127,51345.0146170238,1275658.35495898,15260.4892854214,8861.76578480635,37647.1638704867,4979.53544046949,7012.48134772332
,3385.20612391205,1911.03114395959,66886.5036605189,2223.47536156462,814.947809578378,234.028589468841,5397.4347625133,13346.3226579065,28809.3901352898,6387.69226236731,5639.42730553242,2011100.92675507,4150.63707173462,34098.7514446498,3437.10672573502,289710.315303182,8664.66947305203,13813.3867161134,208817.521491857,169317.624400274,9966.78447705792,37811.1721605562,2263.19211279927,80434.5581206454,19057.8093104899,24664.5067589624,25136.5042354789,3582.85741610706,6683.13898432794,65423.9991390846,134848.302304064,3018.55371579808,546249.641168158,172926.689143006,3074.15064180208,1521.70624812788,59012.4248281661,21226.928522236,17572.5682970983,226.646947337851,56232.2982652019,14641.0043361533,6997.94414914865)
 >>
 >>
 library(lmom)
 >> lmom  = 
 samlmu(amounts)
 >> #
 __________________________________________________________________
 >> # Normal Distribution parameters
 >> parameters_of_NOR  <-
 pelnor(lmom); parameters_of_NOR
 >>
 >>      mu          sigma
 115148.4    175945.8
 >>       
               Location       Scale 
    Minitab         115148.4 
    485173SPSS           115148.4 
    485173
 >> #
 __________________________________________________________________
 >> # Log Normal (3 Parameter)
 Distribution parameters
 >>   
    zeta                mu         
      sigma 3225.798890    9.114879     
 2.240841
 >>                 
             Location            Scale       
    Shape
 >> MINITAB     
          9.73361         
    1.76298      75.51864SPSS           
         9.7336                1.763       
   75.519           #
 __________________________________________________________________
 >>
 >> Besides
 Genaralized extreme Value distributions, all the other
 distributions e.g. Gamma, Exponential (2 parameter)
 distributions etc give different results than MINITAB and
 SPSS.
 >> Can some one guide me?
 >>
 >> Regards
 >> Katherine
 >>
 >>
 >>
 >>
 >>
 >>
 >>
 >>
 >>
 >>
 >>
 >>
 >>
 >>
 >>
 >>
 >>
 >>
 >>
 >>
 >>
 >>
 >>
 >>
 >>
 >>
 >>
 >>
 >>
 >>
 >>
 >>
 >>
 >>
 >>
 >>
 >>
 >>
 >>
 >>
 >>
 >>
 >>
 >>     [[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.
 >
 >
 ______________________________________________
 > [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.

 --
 Peter Dalgaard,
 Professor,
 Center for Statistics, Copenhagen
 Business School
 Solbjerg Plads 3, 2000
 Frederiksberg, Denmark
 Phone:
 (+45)38153501
 Email: [hidden email]  Priv:
 [hidden email]

______________________________________________
[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.