Subject: Year 2000: (was Date Format as YYMMDD?)
From: "R. Allan Reese"
Date: Wed, 15 Jan 1997 09:56:09 +0000
The year 2000 problem (aka Virginia Bottomley - that's a UK joke) -
what are various packages doing about it?
Are the "next" versions of packages going to take special steps to warn
people? Do users anticipate problems? Or are the problems so diverse
that there's no point in doing anything apart from reviewing your own
activities and looking for places to check on 1/Jan/2000 (once the hang-over
subsides).
I found that Stata doesn't allow YY dates. Its function mdy delivers a
missing value for mdy(12,1,96) etc. Demands (12,1,1996). Stern but
sensible - the Mary Poppins package.
SPSS has so many variants on dates, but I think they all get stored as a
big number internally. But the Reference Manual says that YY is assumed
to mean 19YY. So YRMODA(00,1,1) *is* 1/Jan/1900. Hence your elapsed days
calculations will run backwards.
Other packages may define YY to mean "the present century". That makes
the same problem if reading retrospective data, but if you've input data
this century and continue in 00 (2000), the accumulated data should be
alright (internally).
Dates and names are forever messy, so maybe whatever you check and plan
in the program, the most important message is to run tests and build
alerts into the data collection/management/analysis process.
PS: this is NOT an invitation for anyone to resume a "does the 21st
century start in 2000 or 2001?" debate.
R. Allan Reese Email: r.a.reese@ucc.hull.ac.uk
Head of Applications Direct voice: +44 1482 465296
Academic Services Computing Voice messages: +44 1482 465685
Hull University, Hull HU6 7RX, UK. Fax: +44 1482 466441
Subject: SAS Programming Jobs in PA/NJ/DE
From: Loren King
Date: Wed, 15 Jan 1997 09:04:46 -0800
Enjoy the flexibility of the consulting while benefiting
from the stability of working with an industry leader.
For the past 20 years we have been placing seasoned
Information Technology professionals in long-term consulting
contracts with our Fortune 500 client companies in the
Philadelphia (PA/NJ/DE) area. If you are a highly skilled
SAS Programmer who wants to apply your expertise and
develop mastery of emerging technologies while earning
compensation commensurate with your experience,
email your resume to:
balacynwyd@edpcs.com
Attention: Loren King
Detailed descriptions available below, or visit our website at:
http://www1.shore.net/~field1/edp403/jobs.htm
Code: 2239/SAS/1216
Duration: 6 Months
Position: Senior Programmer / Analyst
Duties: Assist in design and writing of the system
design specification and the development
for the new Safety Assessment Statistical System
Requires: SAS, Oracle SQL and MS Office experience
Location: Western Philadelphia Suburbs
~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
Code: 2238/SAS/1216
Duration: 7 Months
Position: Senior Programmer / Analyst
Duties: Establish criteria for data edit & review,
identify parameters in protocol, make
corrections & complete consistency checks
against Case Report Forms (CRF).
Requires: Extensive SAS, Oracle, Unix
and MS Office experience
Location: Central New Jersey
~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
Code: 2202/SAS/1216
Duration: 6 Months
Position: Data Analyst
Duties: Establish criteria for data edit & review,
identify parameters in protocol, make
corrections & complete consistency checks
against Case Report Forms (CRF).
Requires: Strong SAS PC skills
Location: Wilmington, Delaware
~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
Code: 2115/SAS/1216
Duration: 6 Months
Position: SAS Programmer
Duties: Develop Phase II & III Clinical
Trials reporting applications
Requires: SAS, VMS and Clinical Trials
Desired: Systems background experience
Location: Western Philadelphia Suburbs
~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
Code: 2080/SAS/1216
Duration: 3 Months
Position: Programmer / Analyst
Duties: Perform validation and enhancements
to existing clinical reports
Requires: Strong SAS skills
Desired: VMS experience
Location: Northwest Philadelphia suburbs
~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
Code: 2072/SAS/1216
Duration: 3 Months
Position: Programmer / Analyst
Duties: Perform enhancements to clinical reporting
applications using SAS Base and SAS
Macro on a VAX/VMS platform
Requires: SAS and Clinical Trials experience
Location: Northwest Philadelphia suburbs
~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
Code: 2046/SAS/1216
Duration: 2 Months
Position: Technical Consultant
Duties: PH CLINICAL software installation and support
Requires: VMS and Clinical Trials experience.
Location: Western Philadelphia Suburbs
~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
Code: 2001/SAS/1216
Duration: 12 Months
Position: Programmer / Analyst
Requires: Strong BASE SAS background and a
working knowledge of MS Office
Desired: SAS Macro and AF are desired
Location: Northwest Philadelphia Suburbs
~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
Code: 1931/SAS/1216
Duration: 12 Months
Position: Analyst
Duties: Support the clinical reporting
teams for drug study applications
Requires: SAS, Oracle and VMS experience
Location: Northwest Philadelphia Suburbs
~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
Code: 1900/SAS/1216
Duration: 6 Months
Position: Programmer / Analyst
Duties: Work in a clinical trials environment
Requires: SAS, IBM Mainframe and JCL experience
Location: Northwest Philadelphia Suburbs
~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
Code: 1881/SAS/1216
Duration: 6 Months
Position: Statistician
Duties: Participate in the development of a Phase
Three cardiovascular clinical application
Requires: Pharmaceutical experience along with a
strong statistical analysis background
Location: Western Philadelphia Suburbs
~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
Code: 1779/SAS/1216
Duration: 6 Months
Position: Programmer / Analyst
Duties: Develop clinical applications under VAX/VMS
Requires: SAS, VAX/VMS and clinical trials experience
Location: Northwest Philadelphia suburbs
Note: Excellent chance for performance based extension.
~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
Code: 1776/SAS/1216
Duration: 6 Months
Position: Statistician
Duties: Phase 2 and 3 clinical trials applications
Requires: SAS experience
Location: Northwest Philadelphia suburbs
~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
Code: 1635/SAS/1216
Duration: 6 Months
Position: Programmer / Analyst
Duties: Load data from ASCII, Btrieve or
MS Access files into SAS files
Requires: SAS BASE & MACRO experience
Location: Wilmington, Delaware
~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
Code: 1459/SAS/1216
Duration: 6 Months
Position: Senior Programmer / Analyst
Duties: Load data from ASCII, Btrieve or
MS Access files into SAS files
Requires: Minimum of 3-4 years of SAS, clinical,
pharmaceutical or related experience
Location: Central New Jersey
~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
For the past 20 years we have been placing seasoned
Information Technology professionals in long-term
consulting contracts with our Fortune 500 client
companies in the Philadelphia (PA/NJ/DE) area. In
recognition of the value of your professional network,
EDP Contract Services will provide a cash bonus for
individuals who you refer that result in a successful placement.
~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
Please forward resume to:
Loren King, Technical Recruiting
EDP Contract Services
401 City Ave., Suite 915
Bala Cynwyd, PA 19004
610 667-8735 (fax) 610 667-2990 (voice)
e-mail: balacynwyd@edpcs.com
~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
U.S. Citizenship, Green Card, F-1 or TN eligibility required
Subject: SAS Clinical Jobs in PA/NJ/DE
From: Loren King
Date: Wed, 15 Jan 1997 09:04:19 -0800
Enjoy the flexibility of the consulting while benefiting
from the stability of working with an industry leader.
If you are a highly skilled Information Technology
professional utilizing Clinical SAS who wants to apply
your expertise and master emerging technologies while
earning compensation commensurate with your experience,
email your resume to the attention of Loren King at:
balacynwyd@edpcs.com
Detailed descriptions available below, or visit our website at:
http://www1.shore.net/~field1/edp403/jobs.htm
Code: 2276/SAS/114
Duration: 12 Months
Position: Senior Programmer / Analyst
Requires: SAS, and Clinical Trials experience
Location: Northwest Philadelphia Suburbs
~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
Code: 2183/SAS/114
Duration: 4 Months
Position: Senior Programmer / Analyst
Duties: Work on Phase IV and V Clinical Trials
Requires: SAS, Clinical Trials and VAX experience
Location: Northwest Philadelphia Suburbs
Note: Position will become permanent after 90 days
~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
Code: 1931/SAS/114
Duration: 12 Months
Position: Analyst
Duties: Support the clinical reporting
teams for drug study applications
Requires: SAS, Oracle and VMS experience
Location: Northwest Philadelphia Suburbs
~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
Code: 1880/SAS/114
Duration: 6 Months
Position: Programmer / Analyst
Duties: Participate in the development of a Phase
Three clinical trial application
Requires: SAS and VMS experience
Location: Northwest Philadelphia Suburbs
~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
Code: 1706/SAS/114
Duration: 6 Months
Position: Senior Programmer / Analyst
Duties: Participate in the development
of Clinical Trials applications
Requires: SAS, VMS and Clinical Trials experience
Location: Northwest Philadelphia suburbs
Note: Excellent chance for performance based extension.
~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
For the past 20 years we have been placing seasoned
Information Technology professionals in long-term
consulting contracts with our Fortune 500 client
companies in the Philadelphia (PA/NJ/DE) area. In
recognition of the value of your professional network,
EDP Contract Services will provide a cash bonus for
individuals who you refer that result in a successful placement.
~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
Please forward resume to:
Loren King, Technical Recruiting
EDP Contract Services
401 City Ave., Suite 915
Bala Cynwyd, PA 19004
610 667-8735 (fax) 610 667-2990 (voice)
e-mail: balacynwyd@edpcs.com
~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
U.S. Citizenship, Green Card, F-1 or TN eligibility required
Subject: Re: PC & CCA
From: wpilib+@pitt.edu (Richard F Ulrich)
Date: 15 Jan 1997 15:24:50 GMT
Pablo del Monte Luna (delmonte@cibnor.mx) wrote:
: I perform, separately, principal components technique to two groups of
: climatic variables. Then, I made Canonical Correlation Analysis from
: Factor Scores of each group (accounting at least 80% of the original
: variability in any case). Is it valid?
-- More to the point, perhaps, is, "Is it useful?"
If you used ALL of the principal components from each analysis, then
the Canonical Correlation could have been run on all the inital
variables, and it would have accounted for the same variance. Is
that reasonable? "80% of the variability" is enough redundancy
that I would be cautious about a) overfitting, if there were not a
large number of cases per variable; or b) correlated error, if
your data sources are not independent.
Maybe that will help you consider what you have, but your question
was not specific enough for me to say much more.
Rich Ulrich, biostatistician wpilib+@pitt.edu
http://www.pitt.edu/~wpilib/index.html Univ. of Pittsburgh
Subject: Re: time series question
From: "David P. Reilly"
Date: Wed, 15 Jan 1997 14:51:14 -0500
David Rothman wrote:
>
> given:
>
> 1. an observed time series which is stationary according to an ADF test
> 2. can be reasonably fitted with a low order ar representation
> 3. a limited number of initial observations ( say 100), but each day
> one obs gets added and the series will grow in length until a time
> when
> the series ceases to be stationary and is then discarded (the
> stationarity
> will be tested on either the whole series, or on a sliding (100 day)
> window concept - im not sure which...yet)
>
> question:
> i need a way to estimating say the 5% tails of the underlying population
> of the Y's. looking @ the tail pts of the sample doesnt do me much
> good, nor does assuming normality of the dist and using a simple
> variance
> idea.
>
> therefore i can :
> (1) flesh out the distribution each day by simulating the ar process
> with
> estimated parameters (over a 100 day moving window) and then get
> the tail pts (id rather monte carlo it than calcing sigma directly
> for
> other reasons).
>
> or
>
> 2. bootstrap ==> given its a time series (and that its serially
> correlated),
> i guess i am forced to bootstrap by blocks. this makes it a bit more
> difficult.
>
> or
>
> 3. ???
>
> comments? any help wud be appreciated....thanks, dave
>
> ps. i actually have n time series (all with a small # of obs) and need
> to get a methodology robust enuf to generalize.
I am not sure that I fully understand your question/problem but some
comments are;
1. the ADF test is not robust to outliers and is marginal at best.
A better approach is to simultaneously identify the ARMA OR ARIMA
structure using a robust procedure ( see Masarotto ) and to then
identify pulses , seasonal pulses, level shifts and time trends via
the TIAO/TSAY approach.
2. Testing for model/parameter dynamics involves Threshold ARIMA methods
and can be quite complicated. A simple approach due to CHOW is to
test the hypothesis of a constant set of parameters.
For more , lot's more , see
the home page for AUTOBOX ....... http://darkstar.icdc.com/~autobox
for references , demos , forecasting hot links and more.
DAVE REILLY
Subject: Re: Ratios in regression
From: wpilib+@pitt.edu (Richard F Ulrich)
Date: 15 Jan 1997 22:51:04 GMT
ANNE KNOX (aknox@ca0330.caso.ca.blm.gov) wrote:
==>[reformated]
: I am using an abundance cover scale (Braun-Blanquet) and have taken the
midpoints of the percent cover classes (3, 15.5, 38, 63, 88). I was
trying to examine the effect of several independant variables : on cover.
A regression didn't work, however, since the residuals were not even close
to being normally distributed (an effect of the discrete ratios I was
told). The best advice that I have received so : far has been to either
use Spearman's rank correlation coefficient or bootstrap analysis. Is
that correct, and does anyone have any additional advice for me?
<===
I have never heard of your scale, so this is might be irrelevant -
If you have a bad effect from your 'discrete ratios', maybe you should
not be making a ratio out of whatever the two numbers are.... Just
being discrete should not have a horrible effect on residuals, insofar
as symmetry, etc., is concerned.
Rich Ulrich, wpilib+@pitt.edu
Subject: Statistician job opening - USFWS, Maryland
From: Clint_Moore@MAIL.FWS.GOV
Date: Wed, 15 Jan 1997 16:24:27 MST
(Announcement posted on TWS-L and STAT-L list servers by Clint Moore
for Graham Smith)
Our office (Office of Migratory Bird Management, U.S. Fish and Wildlife
Service, Laurel, Md.) seeks a biometrician to perform analyses in support of
migratory bird management issues--please refer to the announcement below.
Note that the position is open until 11 February 1997 and only to applicants
within the federal government. Interested parties may contact me directly, as
I do not subscribe to the list.
Graham Smith
Chief, Section of Population and Habitat Assessment
(301) 497-5860
Graham_Smith@mail.fws.gov
***************************************************************************
UNITED STATES
DEPARTMENT OF INTERIOR
FISH AND WILDLIFE SERVICE
VACANCY ANNOUNCEMENT
POSITION: STATISTICIAN (BIOLOGY) ANNOUNCEMENT NUMBER: FWS9-97-11
GS-1530-09/11/12
OPENING DATE: JANUARY 21, 1997 FULL PERFORMANCE LEVEL: GS-1530-13
CLOSING DATE: FEBRUARY 11, 1997 AREA OF CONSIDERATION: GOVERNMENT-WIDE
LOCATION: ASSISTANT DIRECTOR- REFUGES AND WILDLIFE
OFFICE OF MIGRATORY BIRD MANAGEMENT
BRANCH OF SURVEYS AND ASSESSMENT
POPULATION AND HABITAT ASSESSMENT SECTION
LAUREL, MARYLAND
Applicants who wish to handcarry their applications should deliver them to
4040 N. Fairfax Drive, Room 308, Arlington, Virginia.
CONTACT TELEPHONE NUMBER: (703) 358-1743 (TTY) 358-1796
ADDRESS OF PERSONNEL OFFICE: FISH AND WILDLIFE SERVICE
1849 C STREET, N.W.
MAILSTOP: WEBB-308
WASHINGTON, DC 20240
** APPLICANTS ARE STRONGLY ENCOURAGED TO REVIEW THE INFORMATION AND SPECIFIC
INSTRUCTIONS CONTAINED IN OUR APPLICATION GUIDELINES DOCUMENT. **
Our office does not accept applications by facsimile machine or by electronic
mail.
**** QUALIFICATION REQUIREMENTS ****
SPECIALIZED EXPERIENCE: Candidates must have at least 1 year of specialized
experience at or equivalent to the next lower grade that is directly related
to the described duties and that has equipped the candidate with the
particular knowledges, skills, and abilities identified to successfully
perform the work.
**** SPECIAL INFORMATION AND INSTRUCTIONS CONCERNING CTAP PROCEDURES ****
Department of the Interior (DOI) Career Transition Assistance Plan (CTAP)
procedures apply in filling this vacancy. 5 CFR 330, Career Transition
Assistance for Surplus and Displaced Federal Employees requires the following
order of selection for this position:
a) At Bureau option, personnel actions listed in 5 CFR 330.606(b);
b) Any well-qualified SSP candidate who applies within the local commuting
area (Surplus and displaced employees will be given equal consideration);
c) At Bureau option, personnel actions not subject to RPL;
d) Qualified RPL candidates in the local commuting area;
e) At Bureau discretion, any other former displaced well-qualified DOI
employee, e.g. a well-qualified RPL candidate who applies from outside
the local commuting area;
f) Well-qualified ICTAP applicants in the local commuting area;
g) Other outside applicants (other agencies, nonstatus - only if the area of
consideration is "All Qualified Applicants".)
AN ELIGIBLE CTAP APPLICANT IS DETERMINED TO BE WELL-QUALIFIED IF HE/SHE MEETS
THE FOLLOWING: OPM QUALIFICATION STANDARDS FOR THE POSITION; ALL SELECTIVE
FACTORS, WHERE APPLICABLE; SPECIAL QUALIFYING CONDITIONS THAT OPM HAS
APPROVED FOR THE POSITION; IS PHYSICALLY QUALIFIED WITH REASONABLE
ACCOMMODATION, WHERE APPROPRIATE, TO SATISFACTORILY PERFORM THE DUTIES OF
THE POSITION UPON ENTRY; AND IS RATED BY THE ORGANIZATION AT AT LEAST THE
MIDDLE LEVEL OF A 3-LEVEL RATING SYSTEM ON ALL QUALITY RANKING FACTORS.
STATEMENT OF DUTIES:
This position is located in the Population and Habitat Assessment Section,
Branch of Surveys and Assessment, Office of Migratory Bird Management located
at Laurel, Maryland. The Section is the Office's principal organizational
unit assigned the task of assessing population status of migratory game bird
populations and recommending appropriate harvest management regulations. The
incumbent serves as a statistical staff specialist and applies statistical
theory and methods to the solution of analytical problems associated with the
management of birds. The incumbent (1) evaluates proposed management actions
to ensure that they follow from statistically valid inferences; (2) conducts
statistical analyses of survey and banding data on migratory birds; (3)
evaluates and upgrades analytical procedures of population, habitat, and
harvest surveys; (4) designs quantitative studies of special migratory bird
problems; and (5) provides other Section, Branch and Office staff with
statistical support and advice.
KNOWLEDGES, ABILITIES, SKILLS AND OTHER CHARACTERISTICS (KASOCS):
1. Knowledge of theories, principles, and methods of applied statistics.
2. Knowledge of decision sciences with emphasis on stochastic processes,
dynamic optimization and simulation modeling.
3. Knowledge of the quantitative methods associated with the study and
management of wildlife populations.
4. Knowledge of survey design and sampling theory and methods.
5. Ability to communicate effectively and work well with others.
6. Knowledge of data warehousing and skill in the use of a statistical
software package.
** DISPLACED EMPLOYEES REQUESTING SPECIAL CONSIDERATION UNDER THE ICTAP **
If you are a displaced Federal employee you may be entitled to receive
special selection priority under the ICTAP. To receive this priority
consideration you must:
1. Be a displaced Federal employee. You MUST submit a copy of the appropriate
documentation showing your priority consideration status with your
application package. The following categories of candidates are
considered displaced employees:
A. Current or former career or career-conditional (tenure group I or II)
competitive service employees who:
(1) received a specific RIF separation notice (include a copy of your
RIF notice or your Standard Form 50 stating you were separated by
RIF); or
(2) were separated because of a compensable injury, whose compensation
has been terminated, and whose former agency certifies that it is
unable to place them; or
(3) retired with a disability and whose disability annuity has been or
is being terminated; or
(4) upon receipt of a RIF separation notice retired on the effective
date of the RIF; or
(5) retired under the discontinued service retirement option; or
(6) were separated because you declined a transfer of function or
directed reassignment to another commuting area.
OR
B. A former Military Reserve or National Guard Technician who is receiving
a special Office of Personnel Management (OPM) disability retirement
annuity under section 8337(h) or 8456 of title 5 United States Code.
Include a copy of your eligibility letter from the National Guard or
Military Reserve.
2. Be applying for a position at or below the grade level of the position
from which you have been separated. The position must not have a greater
promotion potential than the position from which you were separated.
3. Have a current (or last) performance rating of record of at least fully
successful, results achieved, or equivalent. A copy of this performance
rating MUST be submitted with your application package. (This requirement
does not apply to candidates who are eligible due to compensable injury or
disability retirement).
4. Occupy or be displaced from a position in the same local commuting area as
the position for which you are requesting priority consideration.
5. File your application by the vacancy announcement closing date and meet
all the application criteria (eg., submit all required documentation,
etc.)
6. Be rated well-qualified for the position. An eligible ICTAP applicant is
determined to be well-qualified if he/she meets the following: OPM
qualification standards for the position; is physically qualified with
reasonable accommodation, where appropriate, to satisfactorily perform the
duties of the position upon entry; and is rated by the organization at at
least the middle level of a 3-level rating system on all quality ranking
factors.
Subject: Re: Statistical Routines for Visual Basic
From: Clay Helberg
Date: Wed, 15 Jan 1997 09:33:28 -0600
Tim Dierauf wrote:
>
> Greetings Group,
>
> I am working with a company that is attempting to trend compressor
> degradation with software using linear regression and Windows-95. The
> application is written in visual basic. I would like to get them to use
> some more robust diagnostics such as deleted residuals and/or Cook's
> Distances along with an F-test to determine model strength.
> I can write these routines for them, but would rather use a commercial
> debugged package. Does anybody know if there are any packages available
> in DLL or Visual Basic callable forms that provide statistical
> distributions such as the Normal, F, and Student-t? Better yet,
> regression analysis and diagnostics?
>
> Thanks in advance,
> Tim
(Disclaimer: I work for SPSS, so my opinions may be biased....)
Tim--
I agree with you that a commercial package is the way to go--by the time
you write your own code for the thing, the time you've spent on it will
have cost the company far more than the cost of the commercial package.
As for interfacing with VB, consider SPSS 7.5 for Windows. It provides
OLE object links to most of the SPSS's features, and allows you to open
SPSS data files, manipulate them, call statistical procedures, generate
graphs and plots, and access the results, all from your VB (or C++, or
Powerbuilder, or whatever) application. We will soon be releasing a book
for developers filled with examples of VB, C++ and Powerbuilder code for
building custom applications which access the procedures and features in
SPSS.
For more information, see .
--Clay
--
Clay Helberg | Internet: helberg@execpc.com
Publications Dept. | WWW: http://www.execpc.com/~helberg/
SPSS, Inc. | Speaking only for myself....
Subject: SmallWaters Newsletter
From: "SMALLWATERS CORP>"
Date: Wed, 15 Jan 1997 16:44:37 -0600
SmallWaters Newsletter
January 15, 1996
This E-mail newsletter contains certain news about Amos, SmallWaters
Corporation and upcoming SEM workshops.
1. Telephone area code change
--------------------------
SmallWaters' telephone area code has changed from 312 to 773,
effective immediately. Our new numbers are
voice: USA-(773)-667-8635
fax: USA-(773)-955-6252
"Please make a note of it."
2. Free Amos 3.6 student version
-----------------------------
New: The Amos 3.6 student version is located on the
SmallWaters web page from where it can be downloaded.
It is available at no charge, and users are permitted
to copy and share it freely.
The Amos 3.6 student version runs all 21 examples of the
Amos Users' Guide. The program is identical to the full
commercial version except that there are some restrictions
on the size of the model (up to eight observed variables
and 54 free parameters). A 23-page tutorial (postscript
file) and full online help make it easy to get started.
For specific information, point your web browser to
http://www.smallwaters.com/amos/student.html
Installation instructions for the usual Windows system
dialects, i.e., Windows 3.1x, Windows 95, Windows NT 3.51
and 4.0x, and IBM OS/2 Warp 3 (with WIN-OS/2) are also
on the web page.
3. Free Amos path diagram viewer
-----------------------------
Last summer, a discussion thread on SEMNET called for
tools that would make it easier to exchange path diagrams
via E-mail. In response to these suggestions, Jim Arbuckle
designed the Amos 3.6 student version so that it would
read and print *ANY* Amos path diagram (*.amw) file, no
matter how many variables it contained.
With the diagram viewer, Amos path diagrams produced
elsewhere can be viewed and printed locally in publication
quality. The appearance of the path diagram can be edited,
i.e., objects can be moved and resized, typefaces changed
etc. However, if the diagram has more than 8 observed
variables, the model structure can no longer be changed,
neither can the parameter or variable labels.
With the Amos path diagram viewer, *.amw files can now be
delivered as mail attachments or web objects. The recipient
of the diagrams no longer has to purchase an Amos license
to merely see the diagram. Instead, he/she can simply
download and install the free Amos student version.
Note: The Amos student version can be configured as a
helper application or "plugin" for web browsers and mail
viewers (specify that the browser should launch the application
"amosgraf.exe" to read files with "amw" extensions). I have
tested Amos as a plugin to Netscape 2.02 and it works
pretty smoothly.
4. Upcoming SEM workshops in Heidelberg and Chicago
------------------------------------------------
March 1-7: Three separate SEM workshops given in
Heidelberg (Germany) by
o Karl Joereskog and Fan Yang
o James L. Arbuckle and Werner Wothke
o Peter M. Bentler
March 24-28: Four SEM workshops given in Chicago
by
o Ralph Mueller
o Werner Wothke
o Jamal Abedi
o James R. Campbell and John Keeves
Costs for these workshops are very affordable (in the $15-120
reange). Specifics can be found at
http://www.smallwaters.com/courses
5. New Amos site licensing
-----------------------
An Amos site licensing option is now available for
universities and other organizations. Pricing details are
given on
http://www.smallwaters.com/sales
6. Help wanted
-----------
SmallWaters is looking for a full-time MARKETING and SALES
assistant. If you know of qualified persons in the Chicago
area who are looking for for a new position, please point
them to the announcement on
http://www.smallwaters.com/humres
Yours very truly,
Werner Wothke
***************************************************************
* *
* SmallWaters Corporation voice: USA-773.667.8635 *
* 1507 E. 53rd Street, # 452 fax: USA-773.955.6252 *
* Chicago, IL 60615 Email: wewo@smallwaters.com *
* *
* Web page --- http://www.smallwaters.com *
***************************************************************
Subject: Re: Year 2000: (was Date Format as YYMMDD?)
From: David Marso
Date: Wed, 15 Jan 1997 18:42:05 -0600
Alan Reese Wrote (in part):
"SPSS has so many variants on dates, but I think they all get stored as
a
big number internally. But the Reference Manual says that YY is assumed
to mean 19YY. So YRMODA(00,1,1) *is* 1/Jan/1900. Hence your elapsed
days
calculations will run backwards."
They are all stored (except for YRMODA) as seconds since midnight Oct
14,1582.
YRMODA is stored as Days since this same date (not arbitrary) the
beginning of
the Gregorian Calender . A simple solution is USE 4 digit year values
or protect
your code with something like the following (In this case all 2 digit
years less
than 20 will be treated as 20YY instead of 19YY . I provide a
demonstration of
the approach:
Regards, David Marso
SPSS Technical Support Representative
DATA LIST / M D Y 1-6 DATE 8-17 (ADATE) YR4 19-22.
begin data
010100 01/01/2000 2000
end data .
list.
COMPUTE YRMODAA=YRMODA(Y,M,D).
COMPUTE YRMODAB=YRMODA((Y+(Y<20))*2000,M,D).
COMPUTE YRMODA4=YRMODA(YR4,M,D).
*Better *:.
COMPUTE DATEVARA=DATE.MDY(M,D,Y).
COMPUTE DATEVARB=DATE.MDY(M,D,+(Y<20)*2000).
COMPUTE DATEVAR4=DATE.MDY(M,D,YR4).
COMPUTE CHECKA=YRMODAA*86400.
COMPUTE CHECKB=YRMODAB*86400.
COMPUTE CHECKC=YRMODA4*86400.
FORMATS DATEVARA DATEVARB DATEVAR4 CHECKA CHECKB CHECKC (ADATE).
LIST.
M D Y DATE YR4 YRMODAA YRMODAB YRMODA4 DATEVARA
DATEVARB DATEVAR4 CHECKA CHECKB CHECKC
1 1 0 01/01/2000 2000 115861.0 152385.0 152385.0 01/01/1900
01/01/2000 01/01/2000 01/01/1900 01/01/2000 01/01/2000
Number of cases read: 1 Number of cases listed: 1
Subject: Re: Power for repeated measures designs
From: wpilib+@pitt.edu (Richard F Ulrich)
Date: 15 Jan 1997 22:59:24 GMT
Bruce L. Lambert, Ph.D. (lambertb@uic.edu) wrote:
: Hi everyone,
: I am planning some memory experiments that will use repeated measures
: (a.k.a., within subjects) designs. However, I do not know how to estimate
: sample sizes for these designs. Cohen's text has no index entry for
: "repeated measures" or "within subjects" and the chapter on ANOVA does
: not give much guidance on the issue as far as I can tell. Most published
: studies I've read in reviewing the short-term memory literature use quite
: small sample sizes (< 40), but each participant produces many dozens,
: even hundreds of data points, due to repeated trials. Can someone give me
: pointers in this area?
As someone else suggested, you easiest answer might be do reduce your
consideration to a paired t-test; if you can.
To actually set up your pre-suppositions for any intricate repeated
measures design, I think you need some good, expert, hands-on advice,
and/or a good set of pilot data. (The conventions of the way SS and
effect sizes are described in Repeated Measures are different from
what you might expect from looking at other ANOVA...)
Rich Ulrich, biostatistician wpilib+@pitt.edu
http://www.pitt.edu/~wpilib/index.html Univ. of Pittsburgh
Subject: SRCOS Research Conference (Response Surface Methods = main topic)
From: wparr@utk.edu (Bill Parr)
Date: Wed, 15 Jan 1997 21:09:08 -0500
Some of you commented that many folks don't have WWW access, even though
they have USENET access, so:
Here's the material which appears on the WWW page on the June 19 - 21
Gatlinburg SRCOS meeting.
Sorry about the repeated mailing for some of you.
Bill Parr
========================
Brief fact sheet on the SRCOS meeting June
19 - 21, 1997
Last updated 1/14/97
This meeting will have a strong emphasis on Response Surface Methods, with
an impressive array of distinguished speakers (see below) alreay assembled.
There will be an opportunity for poster sessions for those interested.
Ph.D. students are especially encouraged to attend.
For the best and most up-to-date information on this conference, visit and
bookmark the conference home page
at:
http://funnelweb.utcc.utk.edu/~wparr/srcos.html
Direct all inquiries to Bill Parr (wparr@utk.edu, 423-974-1631) or Gina
Keeling (gkeeling@utk.edu, 423-974-2558)
Dates: June 19 - 21, 1997. Most people will drive/fly in Wednesday
afternoon or night June 18, and depart sometime Sunday June 22. Ground
transportation from the airport to Gatlinburg takes about 70 minutes. Cost
is about $50 each way by cab (on average).
BLOCK THIS ON YOUR CALENDAR NOW, AND PUT IT IN YOUR BUDGET!!!
Airport: The local airport (for other than private planes) is McGhee -
Tyson, in Knoxvile, Tennessee.
Hotel: Park Vista, Gatlinburg, Tennessee, $70.00 per night. The hotel is
nestled in beautiful Gatlinburg, Tennessee, with easy access to the
National Park, to shopping for art and antiques, and to the Pigeon Forge
outlet malls.
We have reserved a block of 60 rooms.
Children under 18 stay for free. Hotel rooms come with one king-size or two
double beds. Rollaway beds can be rented for $10.00 per night. Cribs are
free. You must indicate your preference when making your reservations.
Complimentary coffee and doughnuts are served in the lobby each morning.
For meeting paticipants, coffee, juice, pastries, bagels and muffins will
be served during the morning sessions. Coffee, sodas and snacks will be
served during the afternoon sessions. You are on your own for meals other
than the banquet Friday night. The restaurant serves a breakfast buffet, or
you can eat breakfast and lunch from the menu (neither is included in the
room price).
Check out time is 11:00 a.m., check-in time is 4:00 p.m.
Cancellations must be made 72 hours prior to the arrival date to qualify
for a refund.
Contact phone number for the Park Vista: 1-800-227-5622 or 1-423-436-9211
Tentative program plan (subject to change) -
Last updated 1/14/97
June 18 (Wednesday)
6:00 p.m. - 7:00 p.m. Reception in Garden View C & D at the Park Vista
All the sessions below will be in the Tennessee Ballroom.
June 19, Session 1 (Morning, 9 - 12)
Keynote speaker: Ray Myers, Virginia Tech (Chair for Keynote session: David
Sylwester, University of Tennessee)
Session organizer: Geoff Vining, University of Florida
Christine Anderson-Cook - Virginia Tech
Richard Lynch - Harris Semiconductor - A Case study using RSM to
improve quality of a semiconductor process
Geoff Vining, University of Florida
June 19, Session 2 (Night, 7 p.m.- 9:30 p.m.):
Statistical Education
Session Organizer - Richard Scheaffer, University of Florida
Richard Scheaffer - University of Florida
Madhuri Mulekar - University of South Alabama
June 20, Session 1 (Morning, 9 - 12)
Keynote speaker: John Cornell, University of Florida (Chair for keynote:
Darryl Downing, Oak Ridge)
Session organizer: Andre Khuri, University of Florida (on multi-response
problem)
Andre' Khuri, Univ. of Florida
James W. Neil, Kansas State Univ.
Warren E. Stewart, Univ. of Wisconsin-Madison
June 20, Session 2, (Afternoon, 2 - 5)
Session on Neural Networks and Linear Models
Session Organizer: Todd Ogden, University of South Carolina
Matt Rotelli, Eli Lilly & Company
Other speakers TBD
6:30 - 8:30 p.m. Mountain Hoedown Banquet - Outside on the lawn, or, in the
event of rain, in Garden View C, D, and E
June 21, Session 1 (Morning, 9 - 12)
Keynote speaker: G.E.P. Box (Chair for keynote: Joanne Wendelberger, Los
Alamos)
Session organizer: Dennis Lin, Penn State University (Chair: Greg Piepel,
Battelle Laboratories)
Max Morris, Oak Ridge
Robert Mee, University of Tennessee
Kwang-Jae Kim, Pennsylvania State University
June 21, Session 2 (afternoon, 1 - 4:00)
Session on Information Theoretic Modeling
Session Organizer: Hamparsum Bozdogan, University of Tennessee
Session Chair: Refik Soyer, George Washington University
Hamparsum Bozdogan, University of Tennessee - "A New Informational
Complexity Criterion for Model Selection: The General THeory and Its
Appications"
Chen Xi, Pfizer, Inc. - "Model Selection in nonlinear Regression
Analysis"
Peter M. Bearse & Hamparsum Bozdogan, University of Tennessee -
"Selecting the Model Order, Lag Length, and the Best Predictors in Vector
Autoregressive (VAR) Models using the Informational Complexity Criterion"
Discussant: Refik Soyer, George Washington University
Registration information can be found at
http://funnelweb.utcc.utk.edu/~wparr/srcos.html
or by calling Gina Keeling at 423-974-2558.
==================================================================
William C. Parr Phone: 423-974-1631, Fax: 423-974-2490
Email: wparr@utk.edu
mailto:wparr@utk.edu
World Wide Web: http://funnelweb.utcc.utk.edu/~wparr/
"And the ship's wise men
will remind you once again
That the whole wide world is watchin'." Bob Dylan
==================================================================
--
William C. Parr
wparr@utk.edu
URL: http://funnelweb.utcc.utk.edu/~wparr/
Phone: 423-974-1631 Fax: 423-974-2490
Subject: Re: Year 2000: (was Date Format as YYMMDD?)
From: John Whittington
Date: Thu, 16 Jan 1997 02:29:00 +0000
On Wed, 15 Jan 1997, "R. Allan Reese" wrote (in
part):
>The year 2000 problem (aka Virginia Bottomley - that's a UK joke) -
>what are various packages doing about it?
As for 'packages', I use SAS most of the time and that has been addressing
the problem for some time. There has always been a user-settable option to
define 'year cutoff' when it comes to interpretting YY dates (e.g. if one
sets this cutoff as 1930, then '31' is interpreted as 1931, but 29 is
interpreted as 2029) and we are assured that all current releases of SAS can
cope with dates up to around the year 20,000! Furthermore, the very wide
range of 'informats' available in SAS permit the correct reading in of dates
in virtually any non-ambiguous format.
The more serious problem, however, relates to operating systems,
particularly for PCs. I gather that most versions of MS-DOS out there and,
worse, very many BIOSs will crash whilst everyone else is having celebratory
drinks, and simply will not work with a year of '00' - and I suspect the
same is true of many other operating systems. One hopes and imagines that
any new software released from now on will be addressing the problem - but
there is probably going to be mayhem for those who, at midnight on 31
December 1999, have software dating from much earlier than the mid 90s.
Regards,
John
-----------------------------------------------------------
Dr John Whittington, Voice: +44 1296 730225
Mediscience Services Fax: +44 1296 738893
Twyford Manor, Twyford, E-mail: johnw@mag-net.co.uk
Buckingham MK18 4EL, UK CompuServe: 100517,3677
-----------------------------------------------------------
