Exporting and Editing Charts...

[gianlu-2]

Hello,

I have tried to export charts from SPSS to Word... the Export function in
SPSS seems to not work properly as the chart are cropped at the bottom... Is
it a bug or am I making some mistakes?

Again, I would like to arrange the charts that are saved in the SPSS viewer
in a tabular format. Is it possible to make this format automatic or should
I do it manually?

Sorry for these questions, but I am new in SPSS...

Many Thanks

Gianluca

--
Gianluca Maio
81 Mons Avenue
Maroubra NSW 2035
AUSTRALIA
Mobile:  [phone]
Skype: sephiroth76
MSN: [hidden email]

[David Gomulya]

Hi everybody,

I am trying to run a regression with a binary DV (IPO/no IPO) and some continuous independent variables. The only problem is that there are many potential unobserved heterogeneity correlated with one of the independent variables. As usual, it is impossible for me to control for all the unobservables.

Given this, I don't think I can use standard logit/probit because my results will be biased. I don't think I can use standard 2SLS like that in SPSS either because the DV is dichotomous.

I have been searching and bumped into Two Stage Probit and Nonlinear Two Stage Least Square. But, I am not so sure which one is correct, if any. I would really appreciate it if anybody could advise me the right method to use, how the method works or relevant articles.

Thank you very much! I really appreciate it.

Best regards,
David

[Ornelas, Fermin]

Running a regression line with a binary dependent variable should be out
the question given that the modeling assumptions required for OLS are
likely not met i.e. normality, independence, constant variance.

-----Original Message-----
From: SPSSX(r) Discussion [mailto:[hidden email]] On Behalf Of
David Gomulya
Sent: Sunday, September 09, 2007 10:24 PM
To: [hidden email]
Subject: Binary DV with unobserved heterogeneity

Hi everybody,

I am trying to run a regression with a binary DV (IPO/no IPO) and some
continuous independent variables. The only problem is that there are
many potential unobserved heterogeneity correlated with one of the
independent variables. As usual, it is impossible for me to control for
all the unobservables.

Given this, I don't think I can use standard logit/probit because my
results will be biased. I don't think I can use standard 2SLS like that
in SPSS either because the DV is dichotomous.

I have been searching and bumped into Two Stage Probit and Nonlinear Two
Stage Least Square. But, I am not so sure which one is correct, if any.
I would really appreciate it if anybody could advise me the right method
to use, how the method works or relevant articles.

Thank you very much! I really appreciate it.

Best regards,
David

NOTICE: This e-mail (and any attachments) may contain PRIVILEGED OR
CONFIDENTIAL information and is intended only for the use of the
specific individual(s) to whom it is addressed.  It may contain
information that is privileged and confidential under state and federal
law.  This information may be used or disclosed only in accordance with
law, and you may be subject to penalties under law for improper use or
further disclosure of the information in this e-mail and its
attachments. If you have received this e-mail in error, please
immediately notify the person named above by reply e-mail, and then
delete the original e-mail.  Thank you.

[Luca Meyer]

Hi Gianluca,

Have you tried to play with the X1LENGHT, X2LENGHT and X3LENGHT parameters
in the IGRAPH procedure?

The following is an example of histogram using the CARS.SAV sample dataset
(C:\program files\spss\cars.sav):

/*** small version ***/
IGRAPH /VIEWNAME='Histogram'
/X1 = VAR(mpg) TYPE = SCALE /Y = $count /COORDINATE = VERTICAL  
/X1LENGTH=3.0
/YLENGTH=3.0
/X2LENGTH=3.0
/CHARTLOOK='NONE'
/Histogram  SHAPE = HISTOGRAM CURVE = OFF X1INTERVAL AUTO X1START = 0.

/*** small version ***/
IGRAPH /VIEWNAME='Histogram'
/X1 = VAR(mpg) TYPE = SCALE /Y = $count /COORDINATE = VERTICAL  
/X1LENGTH=9.0
/YLENGTH=9.0
/X2LENGTH=9.0
/CHARTLOOK='NONE'
/Histogram  SHAPE = HISTOGRAM CURVE = OFF X1INTERVAL AUTO X1START = 0.

It creates 2 graphs with very different dimensions, and when you export them
as .DOC you should get one small and the other quite large.

HTH,
Luca

Mr. Luca MEYER
Market research, data analysis & more
www.lucameyer.com - Tel: [phone]


-----Messaggio originale-----
Da: SPSSX(r) Discussion [mailto:[hidden email]] Per conto di
Gianlu
Inviato: lunedì 10 settembre 2007 4.52
A: [hidden email]
Oggetto: Exporting and Editing Charts...

Hello,

I have tried to export charts from SPSS to Word... the Export function in
SPSS seems to not work properly as the chart are cropped at the bottom... Is
it a bug or am I making some mistakes?

Again, I would like to arrange the charts that are saved in the SPSS viewer
in a tabular format. Is it possible to make this format automatic or should
I do it manually?

Sorry for these questions, but I am new in SPSS...

Many Thanks

Gianluca

--
Gianluca Maio
81 Mons Avenue
Maroubra NSW 2035
AUSTRALIA
Mobile:  [phone]
Skype: sephiroth76
MSN: [hidden email]

No virus found in this incoming message.
Checked by AVG Free Edition.
Version: 7.5.485 / Virus Database: 269.13.12/997 - Release Date: 09/09/2007
10.17
 

No virus found in this outgoing message.
Checked by AVG Free Edition.
Version: 7.5.485 / Virus Database: 269.13.12/997 - Release Date: 09/09/2007
10.17
 

[James Whanger]

Binary Logistic regression is robust to both nonnormal predictors and
model misspecification related to missing variables.  It provides a means
of predicting a dichotomous outcome with a given set of independent
variables.  Samples should be relatively large so that the logistic
regression weights can be developed on part of the sample and cross-
validated on the part held out.  Sage's little green book on Logistic
Regression is a good primer on the subject, as is the chapter in Cohen et
al., 2003.

Jim