I can't find any way to get back transformed values for a confidence interval for the geometric mean. Surely I don't need to log transform all the data and do the stats and then back transform the results?
regards, Ian Ian D. Martin, Ph.D. Tsuji Laboratory University of Waterloo Dept. of Environment & Resource Studies ===================== 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 |
Administrator
|
Surely I believe that is precisely what you need to do.
Is this somehow a problem? --
Please reply to the list and not to my personal email.
Those desiring my consulting or training services please feel free to email me. --- "Nolite dare sanctum canibus neque mittatis margaritas vestras ante porcos ne forte conculcent eas pedibus suis." Cum es damnatorum possederunt porcos iens ut salire off sanguinum cliff in abyssum?" |
Administrator
|
In reply to this post by Ian Martin-2
GET FILE='C:\Program Files\SPSS\1991 U.S. General Social Survey.sav'.
MEANS TABLES=age /CELLS GEOMETRIC . COMPUTE No_Break=1. COMPUTE L_age=LN(age). AGGREGATE OUTFILE * / BREAK No_Break / M_LAge=MEAN(L_age) /SdLAge=SD(L_Age)/ N=N. COMPUTE #Half=IDF.T(.975,N-1)*SdLAge/SQRT(N). COMPUTE LCL=EXP(M_Lage-#Half). COMPUTE UCL=EXP(M_Lage+#Half). COMPUTE GMean=EXP(M_Lage). exe.
Please reply to the list and not to my personal email.
Those desiring my consulting or training services please feel free to email me. --- "Nolite dare sanctum canibus neque mittatis margaritas vestras ante porcos ne forte conculcent eas pedibus suis." Cum es damnatorum possederunt porcos iens ut salire off sanguinum cliff in abyssum?" |
Thanks David! I'll adapt that to my data.
Still, I am puzzled that other, fairly standard SPSS procedures will give arithmetic mean ± CI, but that nothing is built in for geo mean. Perhaps this could be implemented in the future by SPSS. regards, Ian Ian D. Martin, Ph.D. Tsuji Laboratory University of Waterloo Dept. of Environment & Resource Studies On Nov 9, 2011, at 10:54 AM, David Marso wrote: > GET FILE='C:\Program Files\SPSS\1991 U.S. General Social Survey.sav'. > MEANS TABLES=age /CELLS GEOMETRIC . > COMPUTE No_Break=1. > COMPUTE L_age=LN(age). > AGGREGATE OUTFILE * / BREAK No_Break / M_LAge=MEAN(L_age) /SdLAge=SD(L_Age)/ > N=N. > COMPUTE #Half=IDF.T(.975,N-1)*SdLAge/SQRT(N). > COMPUTE LCL=EXP(M_Lage-#Half). > COMPUTE UCL=EXP(M_Lage+#Half). > COMPUTE GMean=EXP(M_Lage). > exe. > > > Ian Martin-2 wrote: >> >> I can't find any way to get back transformed values for a confidence >> interval for the geometric mean. Surely I don't need to log transform all >> the data and do the stats and then back transform the results? >> >> regards, >> Ian >> >> Ian D. Martin, Ph.D. >> >> Tsuji Laboratory >> University of Waterloo >> Dept. of Environment & Resource Studies >> >> ===================== >> To manage your subscription to SPSSX-L, send a message to >> LISTSERV@.UGA (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://spssx-discussion.1045642.n5.nabble.com/confidence-interval-for-geo-mean-tp4975675p4978107.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 |
Free forum by Nabble | Edit this page |