Modeling with R. Three lessons in three weeks. 18 July -11 Aug
2008. Techniques include OLS, LAD, EIV, QR, and CART plus
validation. $300. Early Bird (by 5 July) discount of $75. A further
$50 discount for students, faculty, and research workers at academic
institutions. See http://statisticsonline.info/mwithR.htm

How would you test for correlation greater than 0.8? What's a
confidence interval for the 40th percentile? Take Applications of
Bootstrap, CART and Permutation Methods to find out. 18 July-8 August,
2008. $324. ($254 for students, faculty, and research workers at
academic institutions.) Plus Early Bird (before July 5th) discount of
$50. See http://statisticsonline.info/application.htm.

Can anyone explain how can I compute the standardized Canonical
Discriminant Coefficient Matrix D?

In SPSS it says:

D = inv(S11)V

where S=diag(sqrt(w11), sqrt(w22), ...)

S11 = partition containing the first q rows and columns of S
and V is a matrix of eigenvectors such that
V'*W11*V=I

Hi all!

I have a problem: I want to create a scatterplot of 3 variables (all numeric
with the same scale) and create a trend line of each variable.

How can I do this?

Hi group,

I wish to create a flag where all my variables Q1 to Q3 are equal to
3.
It is a questionnaire using a 5 point Likert scale and I wish to flag
those who just put Average to everything.

My current code is like this:

if (Q1=3 and Q2=3 and Q3 =3) flag=1.

I actually have Q1 to Q20 so instead of wrinting 'Q1 = 3 and' 20 times
can i do something like:

if (all(3,Q1 to Q20) flag=1. (similar to the any command)?

This will save alot of time as am likely to be analysing alot of this
type of data.

Many thanks in advance.

Dave L

SPSS 16 introduced Extension commands. These are user-defined syntax
that is implemented in Python or R programs. That allows you to use
the programs without knowing Python or R. Once installed, they are
automatically available in SPSS.

Here is a list of the extension commands currently available for
download from SPSS Developer Central (www.spss.com/devcentral). These
all require at least SPSS 16.0.2 and the Python Programmability Plug-
In.

For most of these, executing
command-name /HELP.
provides a full description of the syntax.

These are generally structured so that the underlying implementation
can be called directly as a Python function if you want to use them in
a BEGIN PROGRAM block, and some have extra functionality available
when used this way.

HIDECOLS and SCRIPTEX are brand new.

All,

I'm new to SPSS and very rusty in Statistics. Has anyone tried to
measure the impact of Retail Competitor locations on YR 1 Sales of a
New Company Store?

I have counts of 6 different competitors as scale variables and
grouped counts as nominal variables along with YR 1 Actual and
Proforma Sales as scale variables. I am using SPSS v. 15.0 and need to
know which statistical analysis would provide the best measurment.

Larry Gray
Vitamin Shoppe

hi,

is it possible to tell spss that the data-editor schould not move when
one loads a new textfile for example?
Of course this happens only when it is not on the full screen.

Flo

Hi, there,

I am wondering if anyone has attempted probit analysis with natural
response
estimation using SAS as well as SPSS? We find that the results are
quite different
using the two software. Is this "normal" and what the explanations
might be?

Any tips are highly appreciated.

Best,

Jinsong

I have an intel iMac running 10.5.3 and a MacBook air running same. I
stalled Graduate pk 16 + 2 patches (1 & 02). Whan I save a file .sav
or .port I cannot email that file (only working with small test files
because of the problem) as an attachment under any circumstances using
mail; as the mail package crashes 'unexpectedly quite' relaunch.
Emailing files is fundamental to my work and I need to fix this
problem. Has anyone else experienced this. I uninstalled on the
laptop and successfully re-installed (I think) but issue is the same
on that machine also. I doesn't make any difference with I use my
native package or access my mail over the internet - result is the
same. Can't send a file. Any ideas please?

I'm much more experienced with SAS and would simply create a library
for each data source and use proc sql to query multiple data sources
such as a list in MS Excel/Access (or any other ODBC compliant source)
and SQL Server.

Unfortunately, I can't seem to find a way of querying multiple sources
in a similar way using SPSS with commands like GET DATA.

Anyone know of a solution WITHOUT consolidating all the sources into
MS Access and using GET DATA?