m-estimators
Locked
 
|
can someone plz explain what m-estimators are. can i use these to smooth my data set? thx.
|
|
|
actually what im looking to do is called robust smoothing. is m-estimators robust smoothing? or if not, does anyone know how to do robust smoothing in spss? thx
|
|
|
Hi,
As I know, robust smoothing can be done in Spss with Time Series Analysis. Take a look at Trends option from Spss Command Syntax Reference. Cheers, Vlad On Fri, Feb 22, 2008 at 6:01 PM, jimjohn <[hidden email]> wrote: > actually what im looking to do is called robust smoothing. is m-estimators > robust smoothing? or if not, does anyone know how to do robust smoothing > in > spss? thx > > > > jimjohn wrote: > > > > can someone plz explain what m-estimators are. can i use these to smooth > > my data set? thx. > > > > -- > View this message in context: > http://www.nabble.com/m-estimators-tp15634443p15634463.html > Sent from the SPSSX Discussion mailing list archive at Nabble.com. > > ===================== > To manage your subscription to SPSSX-L, send a message to > [hidden email] (not to SPSSX-L), with no body text except the > command. To leave the list, send the command > SIGNOFF SPSSX-L > For a list of commands to manage subscriptions, send the command > INFO REFCARD > ===================== To manage your subscription to SPSSX-L, send a message to [hidden email] (not to SPSSX-L), with no body text except the command. To leave the list, send the command SIGNOFF SPSSX-L For a list of commands to manage subscriptions, send the command INFO REFCARD |
|
|
thx
|
|
|
In reply to this post by vlad simion
i didnt really find anything in the command syntax reference though. basically i have a time series data and the data has become very volatile with big jumps and im looking for a way to smoothe this series. but i dont want to use moving averages or exponential smoothing, instead i want to use something that will do something with the outliers such that my standard deviation is not as high. any ideas? thx.
|
|
|
hi,
you can try use a transformation (log transformation for example), or standardize your variables, but i don't think this will solve your problem if you have a time series data maybe someone else more experienced can give you some advice cheers, vlad On 2/22/08, jimjohn <[hidden email]> wrote: > > i didnt really find anything in the command syntax reference though. > basically i have a time series data and the data has become very volatile > with big jumps and im looking for a way to smoothe this series. but i dont > want to use moving averages or exponential smoothing, instead i want to > use > something that will do something with the outliers such that my standard > deviation is not as high. any ideas? thx. > > > > > > vlady wrote: > > > > Hi, > > > > As I know, robust smoothing can be done in Spss with Time Series > Analysis. > > Take a look at Trends option from Spss Command Syntax Reference. > > > > Cheers, > > Vlad > > > > On Fri, Feb 22, 2008 at 6:01 PM, jimjohn <[hidden email]> wrote: > > > >> actually what im looking to do is called robust smoothing. is > >> m-estimators > >> robust smoothing? or if not, does anyone know how to do robust > smoothing > >> in > >> spss? thx > >> > >> > >> > >> jimjohn wrote: > >> > > >> > can someone plz explain what m-estimators are. can i use these to > >> smooth > >> > my data set? thx. > >> > > >> > >> -- > >> View this message in context: > >> http://www.nabble.com/m-estimators-tp15634443p15634463.html > >> Sent from the SPSSX Discussion mailing list archive at Nabble.com. > >> > >> ===================== > >> To manage your subscription to SPSSX-L, send a message to > >> [hidden email] (not to SPSSX-L), with no body text except > the > >> command. To leave the list, send the command > >> SIGNOFF SPSSX-L > >> For a list of commands to manage subscriptions, send the command > >> INFO REFCARD > >> > > > > ===================== > > To manage your subscription to SPSSX-L, send a message to > > [hidden email] (not to SPSSX-L), with no body text except the > > command. To leave the list, send the command > > SIGNOFF SPSSX-L > > For a list of commands to manage subscriptions, send the command > > INFO REFCARD > > > > > > -- > View this message in context: > http://www.nabble.com/m-estimators-tp15634443p15641417.html > Sent from the SPSSX Discussion mailing list archive at Nabble.com. > > ===================== > To manage your subscription to SPSSX-L, send a message to > [hidden email] (not to SPSSX-L), with no body text except the > command. To leave the list, send the command > SIGNOFF SPSSX-L > For a list of commands to manage subscriptions, send the command > INFO REFCARD > ===================== To manage your subscription to SPSSX-L, send a message to [hidden email] (not to SPSSX-L), with no body text except the command. To leave the list, send the command SIGNOFF SPSSX-L For a list of commands to manage subscriptions, send the command INFO REFCARD |
|
|
In reply to this post by jimjohn
You might try the running medians choice in CREATE...
Running medians. Median of a span of series values surrounding and including the current value. The span is the number of series values used to compute the median. If the span is even, the median is computed by averaging each pair of uncentered medians. The number of cases with the system-missing value at the beginning and at the end of the series for a span of n is equal to n/2 for even span values and (n–1)/2 for odd span values. For example, if the span is 5, the number of cases with the system-missing value at the beginning and at the end of the series is 2. -----Original Message----- From: SPSSX(r) Discussion [mailto:[hidden email]] On Behalf Of jimjohn Sent: Friday, February 22, 2008 1:12 PM To: [hidden email] Subject: Re: [SPSSX-L] m-estimators i didnt really find anything in the command syntax reference though. basically i have a time series data and the data has become very volatile with big jumps and im looking for a way to smoothe this series. but i dont want to use moving averages or exponential smoothing, instead i want to use something that will do something with the outliers such that my standard deviation is not as high. any ideas? thx. vlady wrote: > > Hi, > > As I know, robust smoothing can be done in Spss with Time Series Analysis. > Take a look at Trends option from Spss Command Syntax Reference. > > Cheers, > Vlad > > On Fri, Feb 22, 2008 at 6:01 PM, jimjohn <[hidden email]> wrote: > >> actually what im looking to do is called robust smoothing. is >> m-estimators >> robust smoothing? or if not, does anyone know how to do robust smoothing >> in >> spss? thx >> >> >> >> jimjohn wrote: >> > >> > can someone plz explain what m-estimators are. can i use these to >> smooth >> > my data set? thx. >> > >> >> -- >> View this message in context: >> http://www.nabble.com/m-estimators-tp15634443p15634463.html >> Sent from the SPSSX Discussion mailing list archive at Nabble.com. >> >> ===================== >> To manage your subscription to SPSSX-L, send a message to >> [hidden email] (not to SPSSX-L), with no body text except the >> command. To leave the list, send the command >> SIGNOFF SPSSX-L >> For a list of commands to manage subscriptions, send the command >> INFO REFCARD >> > > ===================== > To manage your subscription to SPSSX-L, send a message to > [hidden email] (not to SPSSX-L), with no body text except the > command. To leave the list, send the command > SIGNOFF SPSSX-L > For a list of commands to manage subscriptions, send the command > INFO REFCARD > > -- View this message in context: http://www.nabble.com/m-estimators-tp15634443p15641417.html Sent from the SPSSX Discussion mailing list archive at Nabble.com. ===================== To manage your subscription to SPSSX-L, send a message to [hidden email] (not to SPSSX-L), with no body text except the command. To leave the list, send the command SIGNOFF SPSSX-L For a list of commands to manage subscriptions, send the command INFO REFCARD |
«
Return to SPSSX Discussion
|
1 view|%1 views
| Free forum by Nabble | Edit this page |