help: export ALLview MIXED generalized linear models
Locked
help: export ALLview MIXED generalized linear models
 
|
Exploring repeated measures using MIXED > generalized linear model Comparing out put with that obtain from MIXED linear and from GEE They are all different! But never mind that OUTPUT form MIXED > generalized linear model Is in something called the “model viewer” looks pretty But am totally unable to copy or export form the viewer in tab separated text. I can get PICTURES of al the output, separately for each item which is a pain BUT I cannot get Tables at all, not even 1 by 1 Not serious for linear, but VERY serious for ordinal and logistic where I really DO need the repeated measures. GEE is absolutely fine, thank you SPSS, but of curse give chi-squares rather than F-ratio Pleae, please help with exporting form model viewer in MIXED > generalized linear model Here is the code *Generalized Linear Mixed Models. GENLINMIXED /DATA_STRUCTURE SUBJECTS=Participant REPEATED_MEASURES=Judgement*Timecat COVARIANCE_TYPE=DIAGONAL /FIELDS TARGET=Accuracy TRIALS=NONE OFFSET=NONE /TARGET_OPTIONS DISTRIBUTION=NORMAL LINK=IDENTITY /FIXED EFFECTS=Mood Judgement Timecat Mood*Judgement Mood*Timecat Judgement*Timecat Mood*Judgement*Timecat USE_INTERCEPT=TRUE /BUILD_OPTIONS TARGET_CATEGORY_ORDER=ASCENDING INPUTS_CATEGORY_ORDER=ASCENDING MAX_ITERATIONS=100 CONFIDENCE_LEVEL=95 DF_METHOD=SATTERTHWAITE COVB=MODEL /EMMEANS TABLES=Mood CONTRAST=NONE /EMMEANS TABLES=Judgement CONTRAST=NONE /EMMEANS TABLES=Timecat CONTRAST=NONE /EMMEANS TABLES=Mood*Judgement CONTRAST=NONE /EMMEANS TABLES=Mood*Timecat CONTRAST=NONE /EMMEANS TABLES=Judgement*Timecat CONTRAST=NONE /EMMEANS TABLES=Mood*Judgement*Timecat CONTRAST=NONE /EMMEANS_OPTIONS SCALE=TRANSFORMED PADJUST=LSD. Many thanks Diana Emeritus Professor Diana Kornbrot email: d.e.kornbrot@... web: http://dianakornbrot.wordpress.com/ Work Department of Psychology School of Life and Medical Sciences University of Hertfordshire College Lane, Hatfield, Hertfordshire AL10 9AB, UK voice: +44 (0) 170 728 4626 Home 19 Elmhurst Avenue London N2 0LT, UK voice: +44 (0) 208 444 2081 mobile: +44 (0) 740 318 1612 |
Re: help: export ALLview MIXED generalized linear models
|
|
For GENLINMIXED, you can go to Edit >
Options.... Output tab to request pivot table output instead of Model Viewer
output. I believe that was added in v20.
Alex From: "Kornbrot, Diana" <[hidden email]> To: [hidden email], Date: 05/06/2013 10:11 AM Subject: help: export ALLview MIXED generalized linear models Sent by: "SPSSX(r) Discussion" <[hidden email]> HELP Exploring repeated measures using MIXED > generalized linear model Comparing out put with that obtain from MIXED linear and from GEE They are all different! But never mind that OUTPUT form MIXED > generalized linear model Is in something called the “model viewer” looks pretty But am totally unable to copy or export form the viewer in tab separated text. I can get PICTURES of al the output, separately for each item which is a pain BUT I cannot get Tables at all, not even 1 by 1 Not serious for linear, but VERY serious for ordinal and logistic where I really DO need the repeated measures. GEE is absolutely fine, thank you SPSS, but of curse give chi-squares rather than F-ratio Pleae, please help with exporting form model viewer in MIXED > generalized linear model Here is the code *Generalized Linear Mixed Models. GENLINMIXED /DATA_STRUCTURE SUBJECTS=Participant REPEATED_MEASURES=Judgement*Timecat COVARIANCE_TYPE=DIAGONAL /FIELDS TARGET=Accuracy TRIALS=NONE OFFSET=NONE /TARGET_OPTIONS DISTRIBUTION=NORMAL LINK=IDENTITY /FIXED EFFECTS=Mood Judgement Timecat Mood*Judgement Mood*Timecat Judgement*Timecat Mood*Judgement*Timecat USE_INTERCEPT=TRUE /BUILD_OPTIONS TARGET_CATEGORY_ORDER=ASCENDING INPUTS_CATEGORY_ORDER=ASCENDING MAX_ITERATIONS=100 CONFIDENCE_LEVEL=95 DF_METHOD=SATTERTHWAITE COVB=MODEL /EMMEANS TABLES=Mood CONTRAST=NONE /EMMEANS TABLES=Judgement CONTRAST=NONE /EMMEANS TABLES=Timecat CONTRAST=NONE /EMMEANS TABLES=Mood*Judgement CONTRAST=NONE /EMMEANS TABLES=Mood*Timecat CONTRAST=NONE /EMMEANS TABLES=Judgement*Timecat CONTRAST=NONE /EMMEANS TABLES=Mood*Judgement*Timecat CONTRAST=NONE /EMMEANS_OPTIONS SCALE=TRANSFORMED PADJUST=LSD. Many thanks Diana Emeritus Professor Diana Kornbrot email: d.e.kornbrot@... web: http://dianakornbrot.wordpress.com/ Work Department of Psychology School of Life and Medical Sciences University of Hertfordshire College Lane, Hatfield, Hertfordshire AL10 9AB, UK voice: +44 (0) 170 728 4626 Home 19 Elmhurst Avenue London N2 0LT, UK voice: +44 (0) 208 444 2081 mobile: +44 (0) 740 318 1612 |
Re: help: export ALLview MIXED generalized linear models
|
|
I just found this; it’s not obvious. In 20 it’s controlled on the Viewer tab and once there you have to go down the little picture list on the left hand side to find the model viewer icon, which you can then change to hidden. Why would this ever be set to be the default? While you’re at it, I guess you might consider hiding the tree viewer also. Where is this used? Gene Maguin From: SPSSX(r) Discussion [mailto:[hidden email]] On Behalf Of Alex Reutter For GENLINMIXED, you can go to Edit > Options.... Output tab to request pivot table output instead of Model Viewer output. I believe that was added in v20.
|
Re: help: export ALLview MIXED generalized linear models
|
|
Hi Gene,
Doing that on the Viewer tab will simply hide the Model Viewer output by default, not produce pivot table output in its place. Go to the Output tab and look at the Output Display group. Alex From: "Maguin, Eugene" <[hidden email]> To: [hidden email], Date: 05/06/2013 12:57 PM Subject: Re: help: export ALLview MIXED generalized linear models Sent by: "SPSSX(r) Discussion" <[hidden email]> I just found this; it’s not obvious. In 20 it’s controlled on the Viewer tab and once there you have to go down the little picture list on the left hand side to find the model viewer icon, which you can then change to hidden. Why would this ever be set to be the default? While you’re at it, I guess you might consider hiding the tree viewer also. Where is this used? Gene Maguin From: SPSSX(r) Discussion [[hidden email]] On Behalf Of Alex Reutter Sent: Monday, May 06, 2013 11:24 AM To: [hidden email] Subject: Re: help: export ALLview MIXED generalized linear models For GENLINMIXED, you can go to Edit > Options.... Output tab to request pivot table output instead of Model Viewer output. I believe that was added in v20. Alex From: "Kornbrot, Diana" <d.e.kornbrot@...> To: [hidden email], Date: 05/06/2013 10:11 AM Subject: help: export ALLview MIXED generalized linear models Sent by: "SPSSX(r) Discussion" <[hidden email]> HELP Exploring repeated measures using MIXED > generalized linear model Comparing out put with that obtain from MIXED linear and from GEE They are all different! But never mind that OUTPUT form MIXED > generalized linear model Is in something called the “model viewer” looks pretty But am totally unable to copy or export form the viewer in tab separated text. I can get PICTURES of al the output, separately for each item which is a pain BUT I cannot get Tables at all, not even 1 by 1 Not serious for linear, but VERY serious for ordinal and logistic where I really DO need the repeated measures. GEE is absolutely fine, thank you SPSS, but of curse give chi-squares rather than F-ratio Pleae, please help with exporting form model viewer in MIXED > generalized linear model Here is the code *Generalized Linear Mixed Models. GENLINMIXED /DATA_STRUCTURE SUBJECTS=Participant REPEATED_MEASURES=Judgement*Timecat COVARIANCE_TYPE=DIAGONAL /FIELDS TARGET=Accuracy TRIALS=NONE OFFSET=NONE /TARGET_OPTIONS DISTRIBUTION=NORMAL LINK=IDENTITY /FIXED EFFECTS=Mood Judgement Timecat Mood*Judgement Mood*Timecat Judgement*Timecat Mood*Judgement*Timecat USE_INTERCEPT=TRUE /BUILD_OPTIONS TARGET_CATEGORY_ORDER=ASCENDING INPUTS_CATEGORY_ORDER=ASCENDING MAX_ITERATIONS=100 CONFIDENCE_LEVEL=95 DF_METHOD=SATTERTHWAITE COVB=MODEL /EMMEANS TABLES=Mood CONTRAST=NONE /EMMEANS TABLES=Judgement CONTRAST=NONE /EMMEANS TABLES=Timecat CONTRAST=NONE /EMMEANS TABLES=Mood*Judgement CONTRAST=NONE /EMMEANS TABLES=Mood*Timecat CONTRAST=NONE /EMMEANS TABLES=Judgement*Timecat CONTRAST=NONE /EMMEANS TABLES=Mood*Judgement*Timecat CONTRAST=NONE /EMMEANS_OPTIONS SCALE=TRANSFORMED PADJUST=LSD. Many thanks Diana Emeritus Professor Diana Kornbrot email: d.e.kornbrot@... web: http://dianakornbrot.wordpress.com/ Work Department of Psychology School of Life and Medical Sciences University of Hertfordshire College Lane, Hatfield, Hertfordshire AL10 9AB, UK voice: +44 (0) 170 728 4626 Home 19 Elmhurst Avenue London N2 0LT, UK voice: +44 (0) 208 444 2081 mobile: +44 (0) 740 318 1612 |
Re: help: export ALLview MIXED generalized linear models
|
|
In reply to this post by Maguin, Eugene
So, on 20 this model viewer business only affects, as far as I know, genlinmixed and nonparametric tests command. And, it can’t be turned off. That doesn’t matter (too) much for nonpar but for genlinmixed it does and quite a lot. I had made up some data a while back and ran it. Of course, no tables. But even if i export the output as an rtf, there are no tables. Where are the tables? Gene Maguin From: Jon K Peck [mailto:[hidden email]] No. That list is just for visibility. It has nothing to do with whether MV output is produced.
|
Re: help: export ALLview MIXED generalized linear models
|
|
In reply to this post by Kornbrot, Diana
I am not sure what you are doing, but if
you double click the MV object, go to the panel you want to copy, set the
view to "table", and do right-click Copy Object, the result should
paste into Excel or similar as (formatted) text. Depending on the
type of target, you might need to use Paste Special. In a simple
text editor it should appear as unformatted text.
Jon Peck (no "h") aka Kim Senior Software Engineer, IBM [hidden email] phone: 720-342-5621 From: "Kornbrot, Diana" <[hidden email]> To: [hidden email], Date: 05/06/2013 09:13 AM Subject: [SPSSX-L] help: export ALLview MIXED generalized linear models Sent by: "SPSSX(r) Discussion" <[hidden email]> HELP Exploring repeated measures using MIXED > generalized linear model Comparing out put with that obtain from MIXED linear and from GEE They are all different! But never mind that OUTPUT form MIXED > generalized linear model Is in something called the “model viewer” looks pretty But am totally unable to copy or export form the viewer in tab separated text. I can get PICTURES of al the output, separately for each item which is a pain BUT I cannot get Tables at all, not even 1 by 1 Not serious for linear, but VERY serious for ordinal and logistic where I really DO need the repeated measures. GEE is absolutely fine, thank you SPSS, but of curse give chi-squares rather than F-ratio Pleae, please help with exporting form model viewer in MIXED > generalized linear model Here is the code *Generalized Linear Mixed Models. GENLINMIXED /DATA_STRUCTURE SUBJECTS=Participant REPEATED_MEASURES=Judgement*Timecat COVARIANCE_TYPE=DIAGONAL /FIELDS TARGET=Accuracy TRIALS=NONE OFFSET=NONE /TARGET_OPTIONS DISTRIBUTION=NORMAL LINK=IDENTITY /FIXED EFFECTS=Mood Judgement Timecat Mood*Judgement Mood*Timecat Judgement*Timecat Mood*Judgement*Timecat USE_INTERCEPT=TRUE /BUILD_OPTIONS TARGET_CATEGORY_ORDER=ASCENDING INPUTS_CATEGORY_ORDER=ASCENDING MAX_ITERATIONS=100 CONFIDENCE_LEVEL=95 DF_METHOD=SATTERTHWAITE COVB=MODEL /EMMEANS TABLES=Mood CONTRAST=NONE /EMMEANS TABLES=Judgement CONTRAST=NONE /EMMEANS TABLES=Timecat CONTRAST=NONE /EMMEANS TABLES=Mood*Judgement CONTRAST=NONE /EMMEANS TABLES=Mood*Timecat CONTRAST=NONE /EMMEANS TABLES=Judgement*Timecat CONTRAST=NONE /EMMEANS TABLES=Mood*Judgement*Timecat CONTRAST=NONE /EMMEANS_OPTIONS SCALE=TRANSFORMED PADJUST=LSD. Many thanks Diana Emeritus Professor Diana Kornbrot email: d.e.kornbrot@... web: http://dianakornbrot.wordpress.com/ Work Department of Psychology School of Life and Medical Sciences University of Hertfordshire College Lane, Hatfield, Hertfordshire AL10 9AB, UK voice: +44 (0) 170 728 4626 Home 19 Elmhurst Avenue London N2 0LT, UK voice: +44 (0) 208 444 2081 mobile: +44 (0) 740 318 1612 |
|
|
In reply to this post by Alex Reutter
Oh, a short moment of joy quickly quashed! I have just recently been moved from v19 to 20, and I was excited to read Alex’s comment that the Model Viewer output
could be turned off. Alas, in v20 I don’t have an ‘Output’ tab in the Options window – just the original ‘Output Labels’ tab. The broader ‘Output’ section that Alex refers to appear to have only been introduced in v21. Kylie. From: SPSSX(r) Discussion [mailto:[hidden email]]
On Behalf Of Alex Reutter Hi Gene,
|
Re: help: export ALLview MIXED generalized linear models
Administrator
|
I was raised on the overrated platitude "if you don't have something good to say, don't say anything at all... yada yada yada..." Hence, I have nothing much to say about the MVM.
Who was tripping on what when this silliness was spawned?
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?" |
Re: help: export ALLview MIXED generalized linear models
|
. . and as my old boss, the late Dr Mark Abrams, used to say, "If it's worth saying, you can say it in percentages."
John F Hall (Mr) [Retired academic survey researcher] Email: [hidden email] Website: www.surveyresearch.weebly.com Start page: www.surveyresearch.weebly.com/spss-without-tears.html -----Original Message----- From: SPSSX(r) Discussion [mailto:[hidden email]] On Behalf Of David Marso Sent: 07 May 2013 06:07 To: [hidden email] Subject: Re: help: export ALLview MIXED generalized linear models I was raised on the overrated platitude "if you don't have something good to say, don't say anything at all... yada yada yada..." Hence, I have nothing much to say about the MVM. Who was tripping on what when this silliness was spawned? Kylie Lange-3 wrote > Oh, a short moment of joy quickly quashed! I have just recently been > moved from v19 to 20, and I was excited to read Alex’s comment that > the Model Viewer output could be turned off. Alas, in v20 I don’t have an ‘Output’ > tab in the Options window – just the original ‘Output Labels’ tab. The > broader ‘Output’ section that Alex refers to appear to have only been > introduced in v21. > > Kylie. > > > From: SPSSX(r) Discussion [mailto: > SPSSX-L@.UGA > ] On Behalf Of Alex Reutter > Sent: Tuesday, 7 May 2013 3:59 AM > To: > SPSSX-L@.UGA > Subject: Re: help: export ALLview MIXED generalized linear models > > Hi Gene, > > Doing that on the Viewer tab will simply hide the Model Viewer output > by default, not produce pivot table output in its place. Go to the > Output tab and look at the Output Display group. > > Alex > > > > > From: "Maguin, Eugene" < > emaguin@ > <mailto: > emaguin@ > >> > To: > SPSSX-L@.uga > <mailto: > SPSSX-L@.uga > >, > Date: 05/06/2013 12:57 PM > Subject: Re: help: export ALLview MIXED generalized linear models > Sent by: "SPSSX(r) Discussion" < > SPSSX-L@.uga > <mailto: > SPSSX-L@.uga > >> > ________________________________ > > > > I just found this; it’s not obvious. In 20 it’s controlled on the > Viewer tab and once there you have to go down the little picture list > on the left hand side to find the model viewer icon, which you can > then change to hidden. Why would this ever be set to be the default? > > While you’re at it, I guess you might consider hiding the tree viewer > also. Where is this used? > > Gene Maguin > > > > From: SPSSX(r) Discussion [mailto: > SPSSX-L@.UGA > ] On Behalf Of Alex Reutter > Sent: Monday, May 06, 2013 11:24 AM > To: > SPSSX-L@.UGA > <mailto: > SPSSX-L@.UGA > > > Subject: Re: help: export ALLview MIXED generalized linear models > > For GENLINMIXED, you can go to Edit > Options.... Output tab to > request pivot table output instead of Model Viewer output. I believe > that was added in v20. > > Alex > > > > From: "Kornbrot, Diana" < > d.e.kornbrot@.ac > <mailto: > d.e.kornbrot@.ac > >> > To: > SPSSX-L@.uga > <mailto: > SPSSX-L@.uga > >, > Date: 05/06/2013 10:11 AM > Subject: help: export ALLview MIXED generalized linear models > Sent by: "SPSSX(r) Discussion" < > SPSSX-L@.uga > <mailto: > SPSSX-L@.uga > >> > ________________________________ > > > > > HELP > Exploring repeated measures using MIXED > generalized linear model > Comparing out put with that obtain from MIXED linear and from GEE They > are all different! But never mind that OUTPUT form MIXED > generalized > linear model Is in something called the “model viewer” looks pretty > But am totally unable to copy or export form the viewer in tab > separated text. > I can get PICTURES of al the output, separately for each item which is > a pain BUT I cannot get Tables at all, not even 1 by 1 Not serious for > linear, but VERY serious for ordinal and logistic where I really DO > need the repeated measures. > > GEE is absolutely fine, thank you SPSS, but of curse give chi-squares > rather than F-ratio > > Pleae, please help with exporting form model viewer in MIXED > > generalized linear model Here is the code *Generalized Linear Mixed > Models. > GENLINMIXED > /DATA_STRUCTURE SUBJECTS=Participant > REPEATED_MEASURES=Judgement*Timecat > COVARIANCE_TYPE=DIAGONAL > /FIELDS TARGET=Accuracy TRIALS=NONE OFFSET=NONE /TARGET_OPTIONS > DISTRIBUTION=NORMAL LINK=IDENTITY /FIXED EFFECTS=Mood Judgement > Timecat Mood*Judgement Mood*Timecat Judgement*Timecat > Mood*Judgement*Timecat USE_INTERCEPT=TRUE /BUILD_OPTIONS > TARGET_CATEGORY_ORDER=ASCENDING INPUTS_CATEGORY_ORDER=ASCENDING > MAX_ITERATIONS=100 CONFIDENCE_LEVEL=95 DF_METHOD=SATTERTHWAITE > COVB=MODEL /EMMEANS TABLES=Mood CONTRAST=NONE /EMMEANS > TABLES=Judgement CONTRAST=NONE /EMMEANS TABLES=Timecat CONTRAST=NONE > /EMMEANS TABLES=Mood*Judgement CONTRAST=NONE /EMMEANS > TABLES=Mood*Timecat CONTRAST=NONE /EMMEANS TABLES=Judgement*Timecat > CONTRAST=NONE /EMMEANS TABLES=Mood*Judgement*Timecat CONTRAST=NONE > /EMMEANS_OPTIONS SCALE=TRANSFORMED PADJUST=LSD. > Many thanks > > Diana > > Emeritus Professor Diana Kornbrot > email: > d.e.kornbrot@.ac > web: http://dianakornbrot.wordpress.com/ > Work > Department of Psychology > School of Life and Medical Sciences > University of Hertfordshire > College Lane, Hatfield, Hertfordshire AL10 9AB, UK > voice: +44 (0) 170 728 4626 > Home > 19 Elmhurst Avenue > London N2 0LT, UK > voice: +44 (0) 208 444 2081 > mobile: +44 (0) 740 318 1612 ----- 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?" -- View this message in context: http://spssx-discussion.1045642.n5.nabble.com/help-export-ALLview-MIXED-generalized-linear-models-tp5720008p5720017.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 |
Re: help: export ALLview MIXED generalized linear models
|
|
In reply to this post by Jon K Peck
From this point of view MIXED LINEAR is great, everything one needs can be easily specified in dialogues, well done that SPSS team, BUT MIXED GENERALIZED LINEAR is a disaster. Cannot specify an outfile for anything at all. Cannot specify contrasts. Insisting on specifying the models by SELECT & DRAG separately for each main effect and each interaction, as opposed to the simple SELECT, FACTORIAL, arrow key in the nice friendly MIXED LINEAR,and GEE. The output from MIXED GENERALIZED LINEAR is also a disaster. This is true whether one uses syntax or dialogues This is because output is ONLY in the model viewer. The model viewer cannot be exported as a whole, as Jon Peck points out, for each SEPARATE panel you may: “go to the panel you want to copy, set the view to "table", and do right-click Copy Object, the result should paste into Excel or similar as (formatted) text. Depending on the type of target, you might need to use Paste Special. In a simple text editor it should appear as unformatted text.” The “right click” bit is far from obvious, took me a long time to find it. Why not just include with copy view under edit menu. Anyway copy object got it completely wrong for the model effects, see below. SPSS needs some better quality controlNote also that the graphs are not editable, as they are in normal SPSS output, so you have to make sure you choose a publishable template in the template. The default won’t be publishable in most journals YES. It is all possible. For my 3 factor model, all those actions would be required separately for: information criteria, model effects, parameter estimates, 8 means tables, a covariate matrix, a mere TWELVE items. Thanks a bunch SPSS. What I think of the SPSS team responsible for input/output to MIXED GENERALIZED LINEAR may be imagined, but not put into a group email. Does SPSS 21 deal with any of these problems? Best Diana Results of copy object, see how top has been omitted and 1 line has become 2. SPSS shold be ashamed I’d like an apology ofr all the wasted time! attribute superColumn rowName superRow V5 df2 Corrected Model ▼ 49 Sig Mood*Judgement .019 F Mood*Judgement*Timecat 2.030 df1 Judgement 1 df2 Mood*Judgement 31 df2 Judgement 31 df2 Judgement*Timecat 34 df2 Mood*Timecat 32 F Corrected Model ▼ 3.429 df2 Timecat 32 df1 Judgement*Timecat 4 F Mood 0.513 df1 Mood*Judgement 1 Sig Judgement .217 df2 Mood 27 F Mood*Timecat 1.500 F Timecat 2.901 df1 Mood*Judgement*Timecat 4 Sig Timecat .037 df1 Timecat 4 Sig Mood*Timecat .226 F Judgement*Timecat 0.494 Sig Mood .480 Sig Mood*Judgement*Timecat .112 F Judgement 1.587 df2 Mood*Judgement*Timecat 34 Sig Judgement*Timecat .740 F Mood*Judgement 6.118 df1 Mood 1 df1 Corrected Model ▼ 19 Sig Corrected Model ▼ .000 df1 Mood*Timecat 4 On 06/05/2013 22:52, "Jon K Peck" <peck@...> wrote: I am not sure what you are doing, but if you double click the MV object, go to the panel you want to copy, set the view to "table", and do right-click Copy Object, the result should paste into Excel or similar as (formatted) text. Depending on the type of target, you might need to use Paste Special. In a simple text editor it should appear as unformatted text. Emeritus Professor Diana Kornbrot email: d.e.kornbrot@... web: http://dianakornbrot.wordpress.com/ Work Department of Psychology School of Life and Medical Sciences University of Hertfordshire College Lane, Hatfield, Hertfordshire AL10 9AB, UK voice: +44 (0) 170 728 4626 Home 19 Elmhurst Avenue London N2 0LT, UK voice: +44 (0) 208 444 2081 mobile: +44 (0) 740 318 1612 |
Re: help: export ALLview MIXED generalized linear models
|
Administrator
|
"Thanks a bunch SPSS. What I think of the SPSS team responsible for input/output to MIXED GENERALIZED LINEAR may be imagined, but not put into a group email."
My suspicions are that something really nasty got into the water supply on Wacker Drive and all the designers drank the resulting Koolaid. I often wonder if anyone there (other than Jon) actually uses the software? I could attempt to summarize my view of the MVM, bit I am drastically attempting to curtail my use of profanity on this list. --
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?" |
Re: help: export ALLview MIXED generalized linear models
|
|
Wait a minute, David. You worked for spss and you have said you were present/involved in software decisions. You saw the process. The people who sat around that table were your counterparts, my counterparts. Any of us could have been them. However they got here to this idea and the decision to go forward, they (plural) believed this was good idea. And, I'll bet, they believed this should be wave of the future for ALL statistics procedure reporting. So, I think it would be interesting to know the true line of thinking underlying this decision.
Gene Maguin -----Original Message----- From: SPSSX(r) Discussion [mailto:[hidden email]] On Behalf Of David Marso Sent: Tuesday, May 07, 2013 7:47 AM To: [hidden email] Subject: Re: help: export ALLview MIXED generalized linear models "Thanks a bunch SPSS. What I think of the SPSS team responsible for input/output to MIXED GENERALIZED LINEAR may be imagined, but not put into a group email." My suspicions are that something really nasty got into the water supply on Wacker Drive and all the designers drank the resulting Koolaid. I often wonder if anyone there (other than Jon) actually uses the software? I could attempt to summarize my view of the MVM, bit I am drastically attempting to curtail my use of profanity on this list. -- Kornbrot, Diana wrote > I try to do everything using dialogues, as I need to present to and > teach students and colleagues who NEVER want to know anything about > syntax, not ever. > From this point of view MIXED LINEAR is great, everything one needs > can be easily specified in dialogues, well done that SPSS team, BUT > MIXED GENERALIZED LINEAR is a disaster. Cannot specify an outfile for > anything at all. Cannot specify contrasts. > Insisting on specifying the models by SELECT & DRAG separately for > each main effect and each interaction, as opposed to the simple > SELECT, FACTORIAL, arrow key in the nice friendly MIXED LINEAR,and GEE. > > The output from MIXED GENERALIZED LINEAR is also a disaster. This is > true whether one uses syntax or dialogues This is because output is > ONLY in the model viewer. > The model viewer cannot be exported as a whole, as Jon Peck points > out, for each SEPARATE panel you may: “go to the panel you want to > copy, set the view to "table", and do right-click Copy Object, the > result should paste into Excel or similar as (formatted) text. > Depending on the type of target, you might need to use Paste Special. > In a simple text editor it should appear as unformatted text.” The > “right click” bit is far from obvious, took me a long time to find it. > Why not just include with copy view under edit menu. Anyway copy > object got it completely wrong for the model effects, see below. SPSS > needs some better quality controlNote also that the graphs are not > editable, as they are in normal SPSS output, so you have to make sure you choose a publishable template in the template. > The default won’t be publishable in most journals YES. It is all > possible. For my 3 factor model, all those actions would be required > separately for: information criteria, model effects, parameter > estimates, 8 means tables, a covariate matrix, a mere TWELVE items. > > Thanks a bunch SPSS. What I think of the SPSS team responsible for > input/output to MIXED GENERALIZED LINEAR may be imagined, but not put > into a group email. > > Does SPSS 21 deal with any of these problems? > Best > > Diana > > Results of copy object, see how top has been omitted and 1 line has > become 2. SPSS shold be ashamed I’d like an apology ofr all the wasted > time! > > attribute superColumn rowName superRow V5 > df2 Corrected Model ▼ 49 > Sig Mood*Judgement .019 > F Mood*Judgement*Timecat 2.030 > df1 Judgement 1 > df2 Mood*Judgement 31 > df2 Judgement 31 > df2 Judgement*Timecat 34 > df2 Mood*Timecat 32 > F Corrected Model ▼ 3.429 > df2 Timecat 32 > df1 Judgement*Timecat 4 > F Mood 0.513 > df1 Mood*Judgement 1 > Sig Judgement .217 > df2 Mood 27 > F Mood*Timecat 1.500 > F Timecat 2.901 > df1 Mood*Judgement*Timecat 4 > Sig Timecat .037 > df1 Timecat 4 > Sig Mood*Timecat .226 > F Judgement*Timecat 0.494 > Sig Mood .480 > Sig Mood*Judgement*Timecat .112 > F Judgement 1.587 > df2 Mood*Judgement*Timecat 34 > Sig Judgement*Timecat .740 > F Mood*Judgement 6.118 > df1 Mood 1 > df1 Corrected Model ▼ 19 > Sig Corrected Model ▼ .000 > df1 Mood*Timecat 4 > > > > On 06/05/2013 22:52, "Jon K Peck" < > peck@.ibm > > wrote: > > I am not sure what you are doing, but if you double click the MV > object, go to the panel you want to copy, set the view to "table", and > do right-click Copy Object, the result should paste into Excel or > similar as > (formatted) text. Depending on the type of target, you might need to > use Paste Special. In a simple text editor it should appear as > unformatted text. > > > Jon Peck (no "h") aka Kim > Senior Software Engineer, IBM > peck@.ibm > phone: 720-342-5621 > > > > > From: "Kornbrot, Diana" < > d.e.kornbrot@.ac > > > To: > SPSSX-L@.uga > , > Date: 05/06/2013 09:13 AM > Subject: [SPSSX-L] help: export ALLview MIXED generalized linear > models > Sent by: "SPSSX(r) Discussion" < > SPSSX-L@.uga > > > ________________________________ > > > > HELP > Exploring repeated measures using MIXED > generalized linear model > Comparing out put with that obtain from MIXED linear and from GEE They > are all different! But never mind that OUTPUT form MIXED > generalized > linear model Is in something called the “model viewer” looks pretty > But am totally unable to copy or export form the viewer in tab > separated text. > I can get PICTURES of al the output, separately for each item which is > a pain BUT I cannot get Tables at all, not even 1 by 1 Not serious for > linear, but VERY serious for ordinal and logistic where I really DO > need the repeated measures. > > GEE is absolutely fine, thank you SPSS, but of curse give chi-squares > rather than F-ratio > > Pleae, please help with exporting form model viewer in MIXED > > generalized linear model Here is the code *Generalized Linear Mixed > Models. > GENLINMIXED > /DATA_STRUCTURE SUBJECTS=Participant > REPEATED_MEASURES=Judgement*Timecat > COVARIANCE_TYPE=DIAGONAL > /FIELDS TARGET=Accuracy TRIALS=NONE OFFSET=NONE > /TARGET_OPTIONS DISTRIBUTION=NORMAL LINK=IDENTITY > /FIXED EFFECTS=Mood Judgement Timecat Mood*Judgement Mood*Timecat > Judgement*Timecat Mood*Judgement*Timecat USE_INTERCEPT=TRUE > /BUILD_OPTIONS TARGET_CATEGORY_ORDER=ASCENDING > INPUTS_CATEGORY_ORDER=ASCENDING MAX_ITERATIONS=100 CONFIDENCE_LEVEL=95 > DF_METHOD=SATTERTHWAITE COVB=MODEL > /EMMEANS TABLES=Mood CONTRAST=NONE > /EMMEANS TABLES=Judgement CONTRAST=NONE > /EMMEANS TABLES=Timecat CONTRAST=NONE > /EMMEANS TABLES=Mood*Judgement CONTRAST=NONE > /EMMEANS TABLES=Mood*Timecat CONTRAST=NONE > /EMMEANS TABLES=Judgement*Timecat CONTRAST=NONE > /EMMEANS TABLES=Mood*Judgement*Timecat CONTRAST=NONE > /EMMEANS_OPTIONS SCALE=TRANSFORMED PADJUST=LSD. > Many thanks > > Diana > > ________________________________ > Emeritus Professor Diana Kornbrot > email: > d.e.kornbrot@.ac > < > d.e.kornbrot@.ac > > > web: http://dianakornbrot.wordpress.com/ > <http://dianakornbrot.wordpress.com/> > Work > Department of Psychology > School of Life and Medical Sciences > University of Hertfordshire > College Lane, Hatfield, Hertfordshire AL10 9AB, UK > voice: +44 (0) 170 728 4626 > Home > 19 Elmhurst Avenue > London N2 0LT, UK > voice: +44 (0) 208 444 2081 > mobile: +44 (0) 740 318 1612 > > > > > ________________________________ > Emeritus Professor Diana Kornbrot > email: > d.e.kornbrot@.ac > web: http://dianakornbrot.wordpress.com/ > Work > Department of Psychology > School of Life and Medical Sciences > University of Hertfordshire > College Lane, Hatfield, Hertfordshire AL10 9AB, UK > voice: +44 (0) 170 728 4626 > Home > 19 Elmhurst Avenue > London N2 0LT, UK > voice: +44 (0) 208 444 2081 > mobile: +44 (0) 740 318 1612 ----- 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?" -- View this message in context: http://spssx-discussion.1045642.n5.nabble.com/help-export-ALLview-MIXED-generalized-linear-models-tp5720008p5720024.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 |
Re: help: export ALLview MIXED generalized linear models
|
|
Dave worked there a long time ago when SPSS was a different company with a different process. I worked there a not so long time ago (retired 6 years ago) but can't really speak to current directions.
Who knows, the decision-making process may be very different when you're a small cog in a big enterprise now compared to a small company then trying to keep up the competition, maintain its loyal user base, and move into enterprise computing. -----Original Message----- From: SPSSX(r) Discussion [mailto:[hidden email]] On Behalf Of Maguin, Eugene Sent: Tuesday, May 07, 2013 6:56 AM To: [hidden email] Subject: Re: help: export ALLview MIXED generalized linear models Wait a minute, David. You worked for spss and you have said you were present/involved in software decisions. You saw the process. The people who sat around that table were your counterparts, my counterparts. Any of us could have been them. However they got here to this idea and the decision to go forward, they (plural) believed this was good idea. And, I'll bet, they believed this should be wave of the future for ALL statistics procedure reporting. So, I think it would be interesting to know the true line of thinking underlying this decision. Gene Maguin -----Original Message----- From: SPSSX(r) Discussion [mailto:[hidden email]] On Behalf Of David Marso Sent: Tuesday, May 07, 2013 7:47 AM To: [hidden email] Subject: Re: help: export ALLview MIXED generalized linear models "Thanks a bunch SPSS. What I think of the SPSS team responsible for input/output to MIXED GENERALIZED LINEAR may be imagined, but not put into a group email." My suspicions are that something really nasty got into the water supply on Wacker Drive and all the designers drank the resulting Koolaid. I often wonder if anyone there (other than Jon) actually uses the software? I could attempt to summarize my view of the MVM, bit I am drastically attempting to curtail my use of profanity on this list. -- Kornbrot, Diana wrote > I try to do everything using dialogues, as I need to present to and > teach students and colleagues who NEVER want to know anything about > syntax, not ever. > From this point of view MIXED LINEAR is great, everything one needs > can be easily specified in dialogues, well done that SPSS team, BUT > MIXED GENERALIZED LINEAR is a disaster. Cannot specify an outfile for > anything at all. Cannot specify contrasts. > Insisting on specifying the models by SELECT & DRAG separately for > each main effect and each interaction, as opposed to the simple > SELECT, FACTORIAL, arrow key in the nice friendly MIXED LINEAR,and GEE. > > The output from MIXED GENERALIZED LINEAR is also a disaster. This is > true whether one uses syntax or dialogues This is because output is > ONLY in the model viewer. > The model viewer cannot be exported as a whole, as Jon Peck points > out, for each SEPARATE panel you may: “go to the panel you want to > copy, set the view to "table", and do right-click Copy Object, the > result should paste into Excel or similar as (formatted) text. > Depending on the type of target, you might need to use Paste Special. > In a simple text editor it should appear as unformatted text.” The > “right click” bit is far from obvious, took me a long time to find it. > Why not just include with copy view under edit menu. Anyway copy > object got it completely wrong for the model effects, see below. SPSS > needs some better quality controlNote also that the graphs are not > editable, as they are in normal SPSS output, so you have to make sure you choose a publishable template in the template. > The default won’t be publishable in most journals YES. It is all > possible. For my 3 factor model, all those actions would be required > separately for: information criteria, model effects, parameter > estimates, 8 means tables, a covariate matrix, a mere TWELVE items. > > Thanks a bunch SPSS. What I think of the SPSS team responsible for > input/output to MIXED GENERALIZED LINEAR may be imagined, but not put > into a group email. > > Does SPSS 21 deal with any of these problems? > Best > > Diana > > Results of copy object, see how top has been omitted and 1 line has > become 2. SPSS shold be ashamed I’d like an apology ofr all the wasted > time! > > attribute superColumn rowName superRow V5 > df2 Corrected Model ▼ 49 > Sig Mood*Judgement .019 > F Mood*Judgement*Timecat 2.030 > df1 Judgement 1 > df2 Mood*Judgement 31 > df2 Judgement 31 > df2 Judgement*Timecat 34 > df2 Mood*Timecat 32 > F Corrected Model ▼ 3.429 > df2 Timecat 32 > df1 Judgement*Timecat 4 > F Mood 0.513 > df1 Mood*Judgement 1 > Sig Judgement .217 > df2 Mood 27 > F Mood*Timecat 1.500 > F Timecat 2.901 > df1 Mood*Judgement*Timecat 4 > Sig Timecat .037 > df1 Timecat 4 > Sig Mood*Timecat .226 > F Judgement*Timecat 0.494 > Sig Mood .480 > Sig Mood*Judgement*Timecat .112 > F Judgement 1.587 > df2 Mood*Judgement*Timecat 34 > Sig Judgement*Timecat .740 > F Mood*Judgement 6.118 > df1 Mood 1 > df1 Corrected Model ▼ 19 > Sig Corrected Model ▼ .000 > df1 Mood*Timecat 4 > > > > On 06/05/2013 22:52, "Jon K Peck" < > peck@.ibm > > wrote: > > I am not sure what you are doing, but if you double click the MV > object, go to the panel you want to copy, set the view to "table", and > do right-click Copy Object, the result should paste into Excel or > similar as > (formatted) text. Depending on the type of target, you might need to > use Paste Special. In a simple text editor it should appear as > unformatted text. > > > Jon Peck (no "h") aka Kim > Senior Software Engineer, IBM > peck@.ibm > phone: 720-342-5621 > > > > > From: "Kornbrot, Diana" < > d.e.kornbrot@.ac > > > To: > SPSSX-L@.uga > , > Date: 05/06/2013 09:13 AM > Subject: [SPSSX-L] help: export ALLview MIXED generalized linear > models > Sent by: "SPSSX(r) Discussion" < > SPSSX-L@.uga > > > ________________________________ > > > > HELP > Exploring repeated measures using MIXED > generalized linear model > Comparing out put with that obtain from MIXED linear and from GEE They > are all different! But never mind that OUTPUT form MIXED > generalized > linear model Is in something called the “model viewer” looks pretty > But am totally unable to copy or export form the viewer in tab > separated text. > I can get PICTURES of al the output, separately for each item which is > a pain BUT I cannot get Tables at all, not even 1 by 1 Not serious for > linear, but VERY serious for ordinal and logistic where I really DO > need the repeated measures. > > GEE is absolutely fine, thank you SPSS, but of curse give chi-squares > rather than F-ratio > > Pleae, please help with exporting form model viewer in MIXED > > generalized linear model Here is the code *Generalized Linear Mixed > Models. > GENLINMIXED > /DATA_STRUCTURE SUBJECTS=Participant > REPEATED_MEASURES=Judgement*Timecat > COVARIANCE_TYPE=DIAGONAL > /FIELDS TARGET=Accuracy TRIALS=NONE OFFSET=NONE > /TARGET_OPTIONS DISTRIBUTION=NORMAL LINK=IDENTITY > /FIXED EFFECTS=Mood Judgement Timecat Mood*Judgement Mood*Timecat > Judgement*Timecat Mood*Judgement*Timecat USE_INTERCEPT=TRUE > /BUILD_OPTIONS TARGET_CATEGORY_ORDER=ASCENDING > INPUTS_CATEGORY_ORDER=ASCENDING MAX_ITERATIONS=100 CONFIDENCE_LEVEL=95 > DF_METHOD=SATTERTHWAITE COVB=MODEL > /EMMEANS TABLES=Mood CONTRAST=NONE > /EMMEANS TABLES=Judgement CONTRAST=NONE > /EMMEANS TABLES=Timecat CONTRAST=NONE > /EMMEANS TABLES=Mood*Judgement CONTRAST=NONE > /EMMEANS TABLES=Mood*Timecat CONTRAST=NONE > /EMMEANS TABLES=Judgement*Timecat CONTRAST=NONE > /EMMEANS TABLES=Mood*Judgement*Timecat CONTRAST=NONE > /EMMEANS_OPTIONS SCALE=TRANSFORMED PADJUST=LSD. > Many thanks > > Diana > > ________________________________ > Emeritus Professor Diana Kornbrot > email: > d.e.kornbrot@.ac > < > d.e.kornbrot@.ac > > > web: http://dianakornbrot.wordpress.com/ > <http://dianakornbrot.wordpress.com/> > Work > Department of Psychology > School of Life and Medical Sciences > University of Hertfordshire > College Lane, Hatfield, Hertfordshire AL10 9AB, UK > voice: +44 (0) 170 728 4626 > Home > 19 Elmhurst Avenue > London N2 0LT, UK > voice: +44 (0) 208 444 2081 > mobile: +44 (0) 740 318 1612 > > > > > ________________________________ > Emeritus Professor Diana Kornbrot > email: > d.e.kornbrot@.ac > web: http://dianakornbrot.wordpress.com/ > Work > Department of Psychology > School of Life and Medical Sciences > University of Hertfordshire > College Lane, Hatfield, Hertfordshire AL10 9AB, UK > voice: +44 (0) 170 728 4626 > Home > 19 Elmhurst Avenue > London N2 0LT, UK > voice: +44 (0) 208 444 2081 > mobile: +44 (0) 740 318 1612 ----- 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?" -- View this message in context: http://spssx-discussion.1045642.n5.nabble.com/help-export-ALLview-MIXED-generalized-linear-models-tp5720008p5720024.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 ===================== 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 |
Re: help: export ALLview MIXED generalized linear models
|
|
In reply to this post by Jon K Peck
Ok, I got it to work, Jon. Thank you. You can pretty much guess what I think of this. That said, the thing that would have improved it would be the ability to copy to a word file in a directly usable table (pivot table type) structure. As it is now, the pasted structure has to be taken apart and restructured to recreate a standard scientific table structure. Gene Maguin From: SPSSX(r) Discussion [mailto:[hidden email]] On Behalf Of Jon K Peck I am not sure what you are doing, but if you double click the MV object, go to the panel you want to copy, set the view to "table", and do right-click Copy Object, the result should paste into Excel or similar as (formatted) text. Depending on the type of target, you might need to use Paste Special. In a simple text editor it should appear as unformatted text.
Emeritus Professor Diana Kornbrot |
Re: help: export ALLview MIXED generalized linear models
|
Administrator
|
In reply to this post by ViAnn Beadle
I bailed in late 2001 after 11 years -micro-mis-managerial faux pas- (1990-2001), so can hardly speak to what/how decisions are made in the current organization. I suspect after the IBM acquisition/defection the place/culture/process would be hardly recognizable.
Viann: "small company then trying to keep up the competition..." "move into enterprise computing.." --> medium sized company then trying to BUY up the competition...(BMDP, Systat, Jandel, several others which I would like to forget). move into marketing research shops (real stats real easy... yawn).
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?" |
Re: help: export ALLview MIXED generalized linear models
|
|
In reply to this post by Maguin, Eugene
Thank you for your reply. It’s interesting to know that another group of folks who use similar statistical procedures think about the output in what seems to be a very different way. Gene Maguin From: Jon K Peck [mailto:[hidden email]] As I have tried to say on this list and elsewhere, I am not a fan of the Model Viewer. But it did not arise from hallucinating, ignorant, lazy brains as has been alleged, and it is not the future of statistical reporting in the Statistics product. As has begun to be evident, the few MV procedures are beginning to offer a choice of traditional pivot table output and MV output. V21 offers a choice set in preferences for the type of output, although it only affects GENLINMIXED in that release. Retrofitting is a lot of work.
|
Re: help: export ALLview MIXED generalized linear models
|
|
In reply to this post by David Marso
My conclusions BAD news: version 20 MIXED generalized linear models is not fit for purposeof exporting, although quite nice fro exploration GOOD news, continuous, aprox normal: MIXED linear gives most of what’s needed. Effect sizes and graphs easily obtianed form exports to EXCEL GOOD news, non-linear: GENERALIZED LINEAR MODELS, GENERALIZED ESTIMATING EQUATIONS [GEE] gives all key descriptive and inferential [chi-square, CLS] stuff one needs. Still think excellent statistics team let down by input/output time. Like Jon, I am no fan of the module viewer. Interaction makes available options that cannot be scripted, and so cannot be saved in a template Good to learn its not the SPSS way forward Form the software engineering point of view, it appears that SPSS does not have a good module library. So for example, syntax for covariance or utfile in different procedures has different options than can be scripted. That’s puzzling and suggests that there is more than 1 covariance subroutine floating around. Same goes for some of the input procedures. Clearly, MIXED calls different input routines for assigning variables to roles in the 2 sub-modules. All that suggests very poor software management at the very top. Anyway, that’s my 2 cents Best Diana On 07/05/2013 14:31, "David Marso" <david.marso@...> wrote: I bailed in late 2001 after 11 years -micro-mis-managerial faux pas- Emeritus Professor Diana Kornbrot email: d.e.kornbrot@... web: http://dianakornbrot.wordpress.com/ Work Department of Psychology School of Life and Medical Sciences University of Hertfordshire College Lane, Hatfield, Hertfordshire AL10 9AB, UK voice: +44 (0) 170 728 4626 Home 19 Elmhurst Avenue London N2 0LT, UK voice: +44 (0) 208 444 2081 mobile: +44 (0) 740 318 1612 |
| Free forum by Nabble | Edit this page |