Multiple imputation

[Sung]

Hi, all.

I have some questions about multiple imputation (I run MI using SPSS 17).

1. Should I have to report results based on the original dataset or imputed datasets?

2.  If there was a difference between original and imputed datasets, what do I have to use? I mean there ara rules or criteria for decision?

3. In spss 17, after MI, I run hierarchical regression as below.
----------------------------------------------------
SORT CASES  BY Imputation_.
SPLIT FILE LAYERED BY Imputation_.

REGRESSION
  /DESCRIPTIVES MEAN STDDEV CORR SIG N
  /MISSING LISTWISE
  /STATISTICS COEFF OUTS R ANOVA CHANGE
  /CRITERIA=PIN(.05) POUT(.10)
  /NOORIGIN
  /DEPENDENT T_PTSD
  /METHOD=ENTER FEScoh FESconf entage D_enrank
  /METHOD=ENTER CE TO_mimpo Cohesion Desire Undesire
  /METHOD=ENTER ELDER SLE SS
  /RESIDUALS HIST(ZRESID) .
-----------------------------------------------------
   The problems of this result were I couldn't find R, R square, adjusted R square, and F value of pooled imputation. I mean I could find these results for each imputed data, but pooled imputation data. How can I report R, R square, adjusted R square, and F value? In addition, I couldn't find beta (standardized coefficients) of pooled imputation (there were only unstandardized coefficients: B and Std. Error).

Please give me some direction. Thank you so much in advance.

Sincerely,

Sungrok

[Joost van Ginkel]

You should report the pooled results. Results of the original data are
just based on listwise deletion. Pooled results, on the other hand, are
the combined results of the separate analyses of each imputed dataset,
which is exactly what you need. Good luck!

Best regards,

Joost van Ginkel


Joost R. Van Ginkel, PhD
Leiden University
Faculty of Social and Behavioural Sciences
Data Theory Group
PO Box 9555
2300 RB Leiden
The Netherlands
Tel: [phone]
Fax: [phone]


-----Original Message-----
From: SPSSX(r) Discussion [mailto:[hidden email]] On Behalf Of
Sungrok
Sent: 05 April 2010 20:10
To: [hidden email]
Subject: Multiple imputation

Hi, all.

I have some questions about multiple imputation (I run MI using SPSS
17).

1. Should I have to report results based on the original dataset or
imputed datasets?

2.  If there was a difference between original and imputed datasets,
what do I have to use? I mean there ara rules or criteria for decision?

3. In spss 17, after MI, I run hierarchical regression as below.
----------------------------------------------------
SORT CASES  BY Imputation_.
SPLIT FILE LAYERED BY Imputation_.

REGRESSION
  /DESCRIPTIVES MEAN STDDEV CORR SIG N
  /MISSING LISTWISE
  /STATISTICS COEFF OUTS R ANOVA CHANGE
  /CRITERIA=PIN(.05) POUT(.10)
  /NOORIGIN
  /DEPENDENT T_PTSD
  /METHOD=ENTER FEScoh FESconf entage D_enrank
  /METHOD=ENTER CE TO_mimpo Cohesion Desire Undesire
  /METHOD=ENTER ELDER SLE SS
  /RESIDUALS HIST(ZRESID) .
-----------------------------------------------------
   The problems of this result were I couldn't find R, R square,
adjusted R square, and F value of pooled imputation. I mean I could find
these results for each imputed data, but pooled imputation data. How can
I report R, R square, adjusted R square, and F value? In addition, I
couldn't find beta (standardized coefficients) of pooled imputation
(there were only unstandardized coefficients: B and Std. Error).

Please give me some direction. Thank you so much in advance.

Sincerely,

Sungrok
--
View this message in context:
http://old.nabble.com/Multiple-imputation-tp28142986p28142986.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

**********************************************************************
This email and any files transmitted with it are confidential and
intended solely for the use of the individual or entity to whom they
are addressed. If you have received this email in error please notify
the system manager.
**********************************************************************

=====================
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

[Joost van Ginkel]

Dear Sungrok,

To answer your other two questions:

2) You should always report the pooled results, especially when the
results of the original data and the pooled results differ. If there are
differences between the results of the original data and the pooled
results, this means that the missingness is probably not missing
completely at random. If this assumption is violated, listwise deletion
may give biased results.

3) SPSS does not report pooled R-squared's and standardized beta's,
probably because no rules have been defined for pooling these
statistics. Maybe you can compute R-squared by simply computing the
average R of the imputed datasets, and by squaring the result. But maybe
other people have some better suggestions?
There are, however, rules for combining the F-values (Schafer, 1997, pp.
113-114), only they are not implemented in SPSS (yet). If you want to
combine the results of the F-values, this may be done using an SPSS
macro named MI-mul.sps which can be downloaded from my personal page:

http://www.socialsciences.leiden.edu/educationandchildstudies/childandfa
milystudies/organisation/staffcfs/van-ginkel.html

I just happen to work at an improved version of this macro, namely
MI-mul2.sps, which is nearly finished now. If you wait one or two more
days, you can download it from the same link. If you can't wait that
long you can just use the old version, which is a lot less user
friendly.

Good luck!

Joost van Ginkel


Joost R. Van Ginkel, PhD
Leiden University
Faculty of Social and Behavioural Sciences
Data Theory Group
PO Box 9555
2300 RB Leiden
The Netherlands
Tel: [phone]
Fax: [phone]


-----Original Message-----
From: SPSSX(r) Discussion [mailto:[hidden email]] On Behalf Of
Sungrok
Sent: 05 April 2010 20:10
To: [hidden email]
Subject: Multiple imputation

Hi, all.

I have some questions about multiple imputation (I run MI using SPSS
17).

1. Should I have to report results based on the original dataset or
imputed datasets?

2.  If there was a difference between original and imputed datasets,
what do I have to use? I mean there ara rules or criteria for decision?

3. In spss 17, after MI, I run hierarchical regression as below.
----------------------------------------------------
SORT CASES  BY Imputation_.
SPLIT FILE LAYERED BY Imputation_.

REGRESSION
  /DESCRIPTIVES MEAN STDDEV CORR SIG N
  /MISSING LISTWISE
  /STATISTICS COEFF OUTS R ANOVA CHANGE
  /CRITERIA=PIN(.05) POUT(.10)
  /NOORIGIN
  /DEPENDENT T_PTSD
  /METHOD=ENTER FEScoh FESconf entage D_enrank
  /METHOD=ENTER CE TO_mimpo Cohesion Desire Undesire
  /METHOD=ENTER ELDER SLE SS
  /RESIDUALS HIST(ZRESID) .
-----------------------------------------------------
   The problems of this result were I couldn't find R, R square,
adjusted R square, and F value of pooled imputation. I mean I could find
these results for each imputed data, but pooled imputation data. How can
I report R, R square, adjusted R square, and F value? In addition, I
couldn't find beta (standardized coefficients) of pooled imputation
(there were only unstandardized coefficients: B and Std. Error).

Please give me some direction. Thank you so much in advance.

Sincerely,

Sungrok
--
View this message in context:
http://old.nabble.com/Multiple-imputation-tp28142986p28142986.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

**********************************************************************
This email and any files transmitted with it are confidential and
intended solely for the use of the individual or entity to whom they
are addressed. If you have received this email in error please notify
the system manager.
**********************************************************************

=====================
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

[Sung]

Dear prof. van Ginkel.

1) As you said, I calcurated r-square, betas, and t values, etc. However, sometimes these values were different from the results of pooled dataset a little bit (not serious). Is it ok?

2) I'm waiting for your MI-mul2.sps, but I can't find this file in your website.
Please let me know where can I find this file.

3) I tried to do MI-mul.sps for multiple hierarchical regression, using my dataset. I chose "Table" in output types, "Regression" in command identifiers, and "ANOVA, coefficients, descriptive statistics, and model summary" in table subtypes for selected commands. And other things followed your process. But it didn't work. I mean I can't find any result of hierarchical multiple regression. What's wrong with me?

Thank you in advance.

Sungrok.

[Mayara]

Dear all,
When you say that the analysis should be done on the POOLED data, does it also include the original one? Because I found it strange that SPSS keeps the original data in the output dataset from the Multiple Imputation command.
In other words, if n=5 imputations, the output dataset looks like : original data (with missing values) + 5 imputed datasets. I am using SPSS v18, and analyzing the data with SAS.
I tried to do both 1/ only imputed datasets 2/ imputed+original, but results are different. It is mainly due to the N, rather than to the missing values properly. Intuitively, I would do the analysis only on the imputed data, but as SPSS keep the original one, I am not totally sure.
Thanks for your help,
Mayara

[Bruce Weaver]

Hi Mayara.  Your wording is a bit sloppy there.  The analysis is not done on pooled data; it is done on each of the imputed data sets, and then pooled estimates of the coefficients etc are computed.  Results from analysis of the original data (with listwise deletion) are not included when the pooled estimates are computed--those results are reported so that you can compare them (via the eyeball test) with the pooled results.

Also, the presence of the special variable Imputation_ is key.  Here's a note from the Help:

* The output dataset contains the original (nonmissing) data and data for one or more imputations. Each imputation includes all of the observed data and imputed data values. The original and imputed data are stacked in the output dataset. A special variable, Imputation_, identifies whether a case represents original data (Imputation_ = 0) or imputed data (Imputation_ =1…m).


HTH.

Mayara wrote

Dear all,
When you say that the analysis should be done on the POOLED data, does it also include the original one? Because I found it strange that SPSS keeps the original data in the output dataset from the Multiple Imputation command.
In other words, if n=5 imputations, the output dataset looks like : original data (with missing values) + 5 imputed datasets. I am using SPSS v18, and analyzing the data with SAS.
I tried to do both 1/ only imputed datasets 2/ imputed+original, but results are different. It is mainly due to the N, rather than to the missing values properly. Intuitively, I would do the analysis only on the imputed data, but as SPSS keep the original one, I am not totally sure.
Thanks for your help,
Mayara

[Mayara]

Hi Bruce,
Thank you very much for your reply, very helpful.
Sorry for my English (I am a French...).
Regards,
Mayara

[Ruben Geert van den Berg]

Dear all,

I wanted to examine some data from Google Analytics and what could possibly be a better option for this than SPSS??

However, I somehow don't succeed reading the .csv data into SPSS. I already tried to change the extension to .txt and .xls but whatever I try, SPSS seems unable to read it (even though it opens fine in EXCEL). In the preview of the SPSS import wizard, I see incomprehensible signs, like a "Y" with two dots on top of it. 

In GA, I used ".csv for EXCEL", this seemed a better option to me than just ".csv".

Lines 1-9 in EXCEL are rubbish, line 10 contains (valid) variable names and the actual data start at line 11.

Can anybody please suggest how to fix this?

Thank you in advance!

Ruben

[Ruben Geert van den Berg]

Dear all,

I just discovered that I get a warning when I try to save the .xls file as an .xls file. It says something like "the file possibly contains functions that are not compatible with Unicode text". When I persist and save it anyway, I can read it into SPSS normally afterwards.

So from here, I'm off-topic since this has now become an .xls question in an SPSS mailing list. But if anybody knows how to "convert" or "adapt" a whole bunch of such nasty .csv files like this (perhaps with Python?), I'd be very grateful!

Thanks again,

Ruben

[Rick Oliver-3]

A few things to try:

Clean up the file in Excel and delete the "rubbish".
Since you're already in Excel, save the file in Excel format.
In SPSS, switch to Unicode mode before reading the Excel file.



From:        Ruben van den Berg <[hidden email]>
To:        [hidden email]
Date:        04/05/2011 02:16 PM
Subject:        Can't read .csv from Google Analytics into SPSS
Sent by:        "SPSSX(r) Discussion" <[hidden email]>

---

Dear all,

I wanted to examine some data from Google Analytics and what could possibly be a better option for this than SPSS??

However, I somehow don't succeed reading the .csv data into SPSS. I already tried to change the extension to .txt and .xls but whatever I try, SPSS seems unable to read it (even though it opens fine in EXCEL). In the preview of the SPSS import wizard, I see incomprehensible signs, like a "Y" with two dots on top of it.

In GA, I used ".csv for EXCEL", this seemed a better option to me than just ".csv".

Lines 1-9 in EXCEL are rubbish, line 10 contains (valid) variable names and the actual data start at line 11.

Can anybody please suggest how to fix this?

Thank you in advance!

Ruben

[Rick Oliver-3]

Python has a CSV module. Don't know if it or something else in Python can address your problem. But if it can be solved with list manipulation, then you can do it Python, since it brings in the whole files as a list (or a tuple, I forget which).



From:        Ruben van den Berg <[hidden email]>
To:        [hidden email]
Date:        04/05/2011 02:31 PM
Subject:        Update: Can't read .csv from Google Analytics into SPSS
Sent by:        "SPSSX(r) Discussion" <[hidden email]>

---

Dear all,

I just discovered that I get a warning when I try to save the .xls file as an .xls file. It says something like "the file possibly contains functions that are not compatible with Unicode text". When I persist and save it anyway, I can read it into SPSS normally afterwards.

So from here, I'm off-topic since this has now become an .xls question in an SPSS mailing list. But if anybody knows how to "convert" or "adapt" a whole bunch of such nasty .csv files like this (perhaps with Python?), I'd be very grateful!

Thanks again,

Ruben

[Ruben Geert van den Berg]

Thanks a lot, Rick!

The rubbish is not really a problem, I can drop it by specifying a cell range.

I tried switching Unicode on (set unicode on.) and just using syntax instead of the wizard, generating

>Error.  Command name: GET DATA 

>(2054) The file is not in a recognized Excel file format. 

>* File: "C:\Documents and Settings\Ruben\Bureaublad\NetSociety_SPSS\Analytics_www.netsociety.nl_20100405-20110404 (1).xls" 

>Execution of this command stops. 

DATASET NAME DataSet2 WINDOW=FRONT.

So the problem is the encoding of the xls file you think? Do you have a clue what the encoding could be and what it should be? Because if I know that, I could perhaps try and bother the python forum with the rest of my troubles...

Best,

Ruben

---

Date: Tue, 5 Apr 2011 14:30:45 -0500
From: [hidden email]
Subject: Re: Can't read .csv from Google Analytics into SPSS
To: [hidden email]

A few things to try:

Clean up the file in Excel and delete the "rubbish".
Since you're already in Excel, save the file in Excel format.
In SPSS, switch to Unicode mode before reading the Excel file.



From:        Ruben van den Berg <[hidden email]>
To:        [hidden email]
Date:        04/05/2011 02:16 PM
Subject:        Can't read .csv from Google Analytics into SPSS
Sent by:        "SPSSX(r) Discussion" <[hidden email]>

---

Dear all,

I wanted to examine some data from Google Analytics and what could possibly be a better option for this than SPSS??

However, I somehow don't succeed reading the .csv data into SPSS. I already tried to change the extension to .txt and .xls but whatever I try, SPSS seems unable to read it (even though it opens fine in EXCEL). In the preview of the SPSS import wizard, I see incomprehensible signs, like a "Y" with two dots on top of it.

In GA, I used ".csv for EXCEL", this seemed a better option to me than just ".csv".

Lines 1-9 in EXCEL are rubbish, line 10 contains (valid) variable names and the actual data start at line 11.

Can anybody please suggest how to fix this?

Thank you in advance!

Ruben

[Jon K Peck]

My guess is that the original csv is in Unicode utf-8 format - and it is not an xls file, so you would read it with the text wizard or DATA LIST.  See what it looks like if you open it in Notepad.  The file might have a BOM (byte order mark) at the start indicating the encoding.  You can manipulate this with the Encoding dropdown control on the Open dialog in Notepad.  DATA LIST supports an ENCODING subcommand, which you might need to set to UTF8.



Jon Peck
Senior Software Engineer, IBM
[hidden email]
312-651-3435



From:        Ruben van den Berg <[hidden email]>
To:        [hidden email]
Date:        04/05/2011 03:01 PM
Subject:        Re: [SPSSX-L] Can't read .csv from Google Analytics into SPSS
Sent by:        "SPSSX(r) Discussion" <[hidden email]>

---

Thanks a lot, Rick!

The rubbish is not really a problem, I can drop it by specifying a cell range.

I tried switching Unicode on (set unicode on.) and just using syntax instead of the wizard, generating

>Error.  Command name: GET DATA
>(2054) The file is not in a recognized Excel file format.
>* File: "C:\Documents and Settings\Ruben\Bureaublad\NetSociety_SPSS\Analytics_www.netsociety.nl_20100405-20110404 (1).xls"
>Execution of this command stops.
DATASET NAME DataSet2 WINDOW=FRONT.

So the problem is the encoding of the xls file you think? Do you have a clue what the encoding could be and what it should be? Because if I know that, I could perhaps try and bother the python forum with the rest of my troubles...

Best,

Ruben

---

Date: Tue, 5 Apr 2011 14:30:45 -0500
From: [hidden email]
Subject: Re: Can't read .csv from Google Analytics into SPSS
To: [hidden email]

A few things to try:

Clean up the file in Excel and delete the "rubbish".
Since you're already in Excel, save the file in Excel format.
In SPSS, switch to Unicode mode before reading the Excel file.



From:        Ruben van den Berg <[hidden email]>
To:        [hidden email]
Date:        04/05/2011 02:16 PM
Subject:        Can't read .csv from Google Analytics into SPSS
Sent by:        "SPSSX(r) Discussion" <[hidden email]>

---

Dear all,

I wanted to examine some data from Google Analytics and what could possibly be a better option for this than SPSS??

However, I somehow don't succeed reading the .csv data into SPSS. I already tried to change the extension to .txt and .xls but whatever I try, SPSS seems unable to read it (even though it opens fine in EXCEL). In the preview of the SPSS import wizard, I see incomprehensible signs, like a "Y" with two dots on top of it.

In GA, I used ".csv for EXCEL", this seemed a better option to me than just ".csv".

Lines 1-9 in EXCEL are rubbish, line 10 contains (valid) variable names and the actual data start at line 11.

Can anybody please suggest how to fix this?

Thank you in advance!

Ruben

[Albert-Jan Roskam]

So you want to convert a csv file from one csv dialect into another? Yep, the Python csv module can do that. It's a built-in module; no need to download anything. Then you might still be faced with the encoding issue. I find such issues alwasy a bit obscure and difficult. There is no fail safe way to know whether the file is in unicode or not, and what byte order it has (although a b.o.m., if present, helps). Something like this:

 

import csv, contextlib

f_in = open("d:/my_nasty_csv.csv", "rb")

f_out = open("d:/my_slick_and_neat_csv.csv", "wb")

with contextlib.nested(f_in ,  f_out) as (infile, outfile):

  writer = csv.writer(outfile)

  for line in csv.reader(infile):

     writer.writerow([unicode(item).encode("utf-8") for item in line])

 

You can also catch the encoding error (if it occurs) and print on which line it occurs to find out what character is the culprit.

 

Cheers!!
Albert-Jan

~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
All right, but apart from the sanitation, the medicine, education, wine, public order, irrigation, roads, a fresh water system, and public health, what have the Romans ever done for us?
~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~

---

From: Rick Oliver <[hidden email]>
To: [hidden email]
Sent: Tue, April 5, 2011 9:40:48 PM
Subject: Re: [SPSSX-L] Update: Can't read .csv from Google Analytics into SPSS

Python has a CSV module. Don't know if it or something else in Python can address your problem. But if it can be solved with list manipulation, then you can do it Python, since it brings in the whole files as a list (or a tuple, I forget which).



From:        Ruben van den Berg <[hidden email]>
To:        [hidden email]
Date:        04/05/2011 02:31 PM
Subject:        Update: Can't read .csv from Google Analytics into SPSS
Sent by:        "SPSSX(r) Discussion" <[hidden email]>

---

Dear all,

I just discovered that I get a warning when I try to save the .xls file as an .xls file. It says something like "the file possibly contains functions that are not compatible with Unicode text". When I persist and save it anyway, I can read it into SPSS normally afterwards.

So from here, I'm off-topic since this has now become an .xls question in an SPSS mailing list. But if anybody knows how to "convert" or "adapt" a whole bunch of such nasty .csv files like this (perhaps with Python?), I'd be very grateful!

Thanks again,

Ruben

[lisettehuyzer]

Dear Ruben,

Hope you are still active on this Forum.
I have the same problem you had and I'm on the quest for answers. Were you able to solve it?

Hope to hear from you!

Best regards,

Lisette Huyzer

[Ruben Geert van den Berg]

Dear Lisette,

Yes, I did. I also wrote a bunch of syntax that tackles some issues I typically walk into when I do so (converting the impossible date/currency formats into proper numeric variables). I'll be more than happy to share it with you and anybody else who's interested. Perhaps we can even make a little tutorial on this. Please let me know what you want to accomplish (you can send me a private message if you prefer that) and I'll figure out how to do it with some of the GA data I've access to.

Best,

Ruben

> Date: Wed, 7 Dec 2011 06:03:02 -0800

> From: [hidden email]
> Subject: Re: Can't read .csv from Google Analytics into SPSS
> To: [hidden email]
>
> Dear Ruben,
>
> Hope you are still active on this Forum.
> I have the same problem you had and I'm on the quest for answers. Were you
> able to solve it?
>
> Hope to hear from you!
>
> Best regards,
>
> Lisette Huyzer
>
> --
> View this message in context: http://spssx-discussion.1045642.n5.nabble.com/Multiple-imputation-tp1075737p5055730.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

[Albert-Jan Roskam]

Hoi Ruben,

 

I'd be interested to know more about it, although I never use Google data.

 

Cheers!!
Albert-Jan

~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
All right, but apart from the sanitation, the medicine, education, wine, public order, irrigation, roads, a fresh water system, and public health, what have the Romans ever done for us?
~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~

From: Ruben van den Berg <[hidden email]>
To: [hidden email]
Sent: Thursday, December 8, 2011 9:24 AM
Subject: Re: [SPSSX-L] Can't read .csv from Google Analytics into SPSS

Dear Lisette,

Yes, I did. I also wrote a bunch of syntax that tackles some issues I typically walk into when I do so (converting the impossible date/currency formats into proper numeric variables). I'll be more than happy to share it with you and anybody else who's interested. Perhaps we can even make a little tutorial on this. Please let me know what you want to accomplish (you can send me a private message if you prefer that) and I'll figure out how to do it with some of the GA data I've access to.

Best,

Ruben

> Date: Wed, 7 Dec 2011 06:03:02 -0800

> From: [hidden email]
> Subject: Re: Can't read .csv from Google Analytics into SPSS
> To: [hidden email]
>
> Dear Ruben,
>
> Hope you are still active on this Forum.
> I have the same problem you had and I'm on the quest for answers. Were you
> able to solve it?
>
> Hope to hear from you!
>
> Best regards,
>
> Lisette Huyzer
>
> --
> View this message in context: http://spssx-discussion.1045642.n5.nabble.com/Multiple-imputation-tp1075737p5055730.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

[Matthew Fuller-Tyszkiewicz]

Hi,

I'm away on leave until Tuesday 13th December. I will not have access to my email account while away, and willl endeavour to return your emails shortly after my return.

Cheers,
Matt.

[lisettehuyzer]

Hi Ruben, Albert-Jan,

I'm very sorry for the late reply. Hope you're still willing to help :)

Currently, I am executing multiple A|B tests on different web sites. In order to get better insights into the data, an additional tracking script has been added to the traditional GWO tracking code. As a result, I now get data about my experiments in the custom variables section. The results of the experiment will be based upon conversion rates and e-commerce data, so important statistics are:

• # of conversions
• # of visits
• e-Commerce data ( €/transaction/conversion)
• Time on site
• pages/visit
• returning vs new visitors
• custom variable (variable 1; two options)
• traffic sources

At this point, I have found that is hard (or even impossible) to export individual visitor data as it is against Googles policies. Thusfar, I have not found a way yet to export all data at once, I've only managed to export one level of a report at a time. Did you manage to export all data at once? 

By the way, I guess both Albert-Jan and Ruben are Dutch, is it okay if we proceed in Dutch? 

Best regards,

Lisette Huijzer

---

Date: Fri, 9 Dec 2011 02:00:59 -0800
From: [hidden email]
To: [hidden email]
Subject: Re: Can't read .csv from Google Analytics into SPSS

Hoi Ruben,

 

I'd be interested to know more about it, although I never use Google data.

 

Cheers!!
Albert-Jan

~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
All right, but apart from the sanitation, the medicine, education, wine, public order, irrigation, roads, a fresh water system, and public health, what have the Romans ever done for us?
~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~

From: Ruben van den Berg <[hidden email]>
To: [hidden email]
Sent: Thursday, December 8, 2011 9:24 AM
Subject: Re: [SPSSX-L] Can't read .csv from Google Analytics into SPSS

Dear Lisette,

Yes, I did. I also wrote a bunch of syntax that tackles some issues I typically walk into when I do so (converting the impossible date/currency formats into proper numeric variables). I'll be more than happy to share it with you and anybody else who's interested. Perhaps we can even make a little tutorial on this. Please let me know what you want to accomplish (you can send me a private message if you prefer that) and I'll figure out how to do it with some of the GA data I've access to.

Best,

Ruben

> Date: Wed, 7 Dec 2011 06:03:02 -0800

> From: [hidden email]
> Subject: Re: Can't read .csv from Google Analytics into SPSS
> To: [hidden email]
>
> Dear Ruben,
>
> Hope you are still active on this Forum.
> I have the same problem you had and I'm on the quest for answers. Were you
> able to solve it?
>
> Hope to hear from you!
>
> Best regards,
>
> Lisette Huyzer
>
> --
> View this message in context: http://spssx-discussion.1045642.n5.nabble.com/Multiple-imputation-tp1075737p5055730.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

---

If you reply to this email, your message will be added to the discussion below:

http://spssx-discussion.1045642.n5.nabble.com/Multiple-imputation-tp1075737p5061261.html

To unsubscribe from Multiple imputation, click here.
NAML

[Ruben Geert van den Berg]

Dear Lisette,

I think this last post is completely off-topic for an SPSS list. I'll be more than happy to discuss this with you off-line but then you'll have to respond a bit faster ;-)

Best,

Ruben

---

Date: Mon, 19 Dec 2011 03:40:23 -0800
From: [hidden email]
Subject: Re: Can't read .csv from Google Analytics into SPSS
To: [hidden email]

Hi Ruben, Albert-Jan,

I'm very sorry for the late reply. Hope you're still willing to help :)

Currently, I am executing multiple A|B tests on different web sites. In order to get better insights into the data, an additional tracking script has been added to the traditional GWO tracking code. As a result, I now get data about my experiments in the custom variables section. The results of the experiment will be based upon conversion rates and e-commerce data, so important statistics are:

• # of conversions
• # of visits
• e-Commerce data ( €/transaction/conversion)
• Time on site
• pages/visit
• returning vs new visitors
• custom variable (variable 1; two options)
• traffic sources

At this point, I have found that is hard (or even impossible) to export individual visitor data as it is against Googles policies. Thusfar, I have not found a way yet to export all data at once, I've only managed to export one level of a report at a time. Did you manage to export all data at once? 

By the way, I guess both Albert-Jan and Ruben are Dutch, is it okay if we proceed in Dutch? 

Best regards,

Lisette Huijzer

---

Date: Fri, 9 Dec 2011 02:00:59 -0800
From: [hidden email]
To: [hidden email]
Subject: Re: Can't read .csv from Google Analytics into SPSS

Hoi Ruben,

 

I'd be interested to know more about it, although I never use Google data.

 

Cheers!!
Albert-Jan

~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
All right, but apart from the sanitation, the medicine, education, wine, public order, irrigation, roads, a fresh water system, and public health, what have the Romans ever done for us?
~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~

From: Ruben van den Berg <[hidden email]>
To: [hidden email]
Sent: Thursday, December 8, 2011 9:24 AM
Subject: Re: [SPSSX-L] Can't read .csv from Google Analytics into SPSS

Dear Lisette,

Yes, I did. I also wrote a bunch of syntax that tackles some issues I typically walk into when I do so (converting the impossible date/currency formats into proper numeric variables). I'll be more than happy to share it with you and anybody else who's interested. Perhaps we can even make a little tutorial on this. Please let me know what you want to accomplish (you can send me a private message if you prefer that) and I'll figure out how to do it with some of the GA data I've access to.

Best,

Ruben

> Date: Wed, 7 Dec 2011 06:03:02 -0800

> From: [hidden email]
> Subject: Re: Can't read .csv from Google Analytics into SPSS
> To: [hidden email]
>
> Dear Ruben,
>
> Hope you are still active on this Forum.
> I have the same problem you had and I'm on the quest for answers. Were you
> able to solve it?
>
> Hope to hear from you!
>
> Best regards,
>
> Lisette Huyzer
>
> --
> View this message in context: http://spssx-discussion.1045642.n5.nabble.com/Multiple-imputation-tp1075737p5055730.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

---

If you reply to this email, your message will be added to the discussion below:

http://spssx-discussion.1045642.n5.nabble.com/Multiple-imputation-tp1075737p5061261.html

To unsubscribe from Multiple imputation, click here.
NAML

---

View this message in context: RE: Can't read .csv from Google Analytics into SPSS
Sent from the SPSSX Discussion mailing list archive at Nabble.com.