Discussion: View Thread

STATISTICA is good substitution for SAS

  • 1.  STATISTICA is good substitution for SAS

    Posted 01-23-2014 13:23
    This message has been cross posted to the following eGroups: Risk Analysis Section and Statistical Consulting Section .
    -------------------------------------------

    Hi, I recently started working for a healthcare management organization as the first statistician in the company. I'm looking for a good statistical software which could fit the need of the analysis and the budget. I'm very experienced with SAS however SAS is kind of expensive and I'm not sure if the company will allow me to buy it. When I searched for the other existing statistical packaged I found STATISTICA which said to be less expensive and capable to do most of the statistical analysis as SAS. I'm wondering if the statements 'more organizations are upgrading their analytics applications from SAS to STATISTICA' and 'SAS is a phase out application ans STATISTICA is a scaple up application' are true or not. Are there many organizations using STATISTICA now?

    Is there any one who have experience both in SAS and STATISTICA? How these two applications compare? Is STATISTICA a good replacement of SAS considering the budget issue?

    I'm grateful for any input.
    -------------------------------------------
    Shuang Wu
    -------------------------------------------


  • 2.  RE:STATISTICA is good substitution for SAS

    Posted 01-23-2014 14:19
    I used Statistica from about 1992 to 1996, because SAS did not have Windows-friendly graphics back then.  I used SAS for programming, and Statistica when I wanted to show things graphically -- and the graphics were indeed excellent.

    It was true that Statistica was far less expensive.  However, I remember it being mostly menu-driven with a lot of buttons on the screen.  (One co-worker always told me "Too many buttons" for him.)

    Before selecting Statistica as a main package, find out what its current programming and data manipulation capabilities are.  If it is mostly point and click, you will probably be disappointed.  The claims you quoted sound like marketing hype, and SAS is certainly not phasing out.  See if you can get a free trial of Statistica.

    -------------------------------------------
    Mark Martin
    Siemens Healthcare Diagnostics
    -------------------------------------------





  • 3.  RE:STATISTICA is good substitution for SAS

    Posted 01-23-2014 14:23
    You are probably not approaching this correctly. You are being paid for your time. If you are an experienced SAS user, you can do a lot of stuff really quickly in SAS. In Statistica, probably not as fast, and I doubt that Statistica has the kind of mixed model stuff SAS does. In addition, if your organization cannot afford a SAS license, how long will they be around?

    -------------------------------------------
    Paul Thompson
    Director, Methodology and Data Analysis Center
    Sanford Research/USD
    -------------------------------------------








  • 4.  RE:STATISTICA is good substitution for SAS

    Posted 01-23-2014 16:07
    Others may have tried it, I had a free download that expired, a SAS competitor and "clone" called "WPS" (world programming system) 

    http://www-304.ibm.com/partnerworld/gsd/solutiondetails.do?solution=35004&expand=true


    And for thoroughness, a list of other software packages.  Surprising to see Excel on the list of stat. packages.

    http://r4stats.com/articles/popularity/



    -------------------------------------------
    Chris Barker, Ph.D.
    Consultant and
    Adjunct Associate Professor of Biostatistics
    www,barkerstats.com

    ---
    "In composition you have all the time you want to decide what to say in 15 seconds, in improvisation you have 15 seconds."
    -Steve Lacy
    -------------------------------------------








  • 5.  RE:STATISTICA is good substitution for SAS

    Posted 01-23-2014 14:24
    I totally agree with Mark.  I would also suggest to take a look at JMP software before making up your mind.  It is a more user friendly version of SAS, made by SAS, and known to be much less expensive than SAS.

    Elena

    -------------------------------------------
    Elena Randou (Rantou)
    FDA
    -------------------------------------------








  • 6.  RE:STATISTICA is good substitution for SAS

    Posted 01-23-2014 14:36
    Can we broaden this discussion?

    Consider:

    SAS, SAS/JMP, SPSS, R, Stata, Statistica, Mathematica, MATLAB

    Is there any published comparison of these?

    I know that, in terms of cost, the order has SAS first, and R last (free), with the others in the middle.

    I have used SAS and R extensively. I have seen a lot of SPSS.  I have heard very good things about STATA.

    But it would be good to see more general comparisons. 

    Peter

    -------------------------------------------
    Peter Flom
    -------------------------------------------








  • 7.  RE:STATISTICA is good substitution for SAS

    Posted 01-23-2014 15:01
    As a Consultant in an academic setting, I get the opportunity to see most of these packages. I too have my favorites for certain tasks - I tend to think in SAS code for data manipulation, but I'll see Stata syntax for post-estimations to models.

    I can't answer your original question - SAS vs. STATISTICA. But, I'll put in my two cents:

    Cost is a consideration, but so is performance (or both the software and yourself), and ease of use. Yes - I can come up with R code to do what I'm thinking of in SAS, but it will take me longer, and take me away from other tasks - so my performance suffers. I'm much more at ease - and hence less frustrated - with SAS most of the time, so my enjoyment in my task is high.

    I also think about resources. There are a ton of SAS resources (and R as well). I might ask "does STATISTICA have similar resources?Do they have a large user base? Is there a large email forum that I fee comfortable with? Is there a user group close by that I might participate in?" The answer to those and similar questions will ultimately sway my vote for software usage.

    Good luck,
    Michael

    -------------------------------------------
    Michael Mahometa
    Consulting Manager
    UT-Austin, Div of Statistics + Scientific Computation
    -------------------------------------------








  • 8.  RE:STATISTICA is good substitution for SAS

    Posted 01-23-2014 15:12
    The issue unfortunately is the initial expense of SAS, especially if the organization has not had a statistician on board in the past, and the yearly renewal.  SAS sets it's rates for organizations very differently than most companies.  We have been hot with a $60+ K fee - annually.  It is a hard sell for someone just joining a company.

    -------------------------------------------
    Janet McDougall
    President
    McDougall Scientific Ltd
    -------------------------------------------








  • 9.  RE:STATISTICA is good substitution for SAS

    Posted 01-23-2014 14:32
    Working for a smaller healthcare organization with a limited software budget, and given your knowledge of SAS and statistics, you should strongly consider SAS/JMP for your needs.

    -------------------------------------------
    Patrick Spagon
    -------------------------------------------








  • 10.  RE:STATISTICA is good substitution for SAS

    Posted 01-23-2014 14:55
    I have used SAS for many years, and have made some use of JMP during the past two years.  While I think JMP is very good for interactive use, its scripting capability is not the equal of the SAS language.  I found that using model variable names input from a file, which is what the application required, was a stretch for JMP, whereas it would have been relatively straightforward using the SAS macro language.

    I also would suggest, in comparing packages, that you make a conservative estimate of the time required to bring yourself to the level of expertise that you have with SAS, and include that in comparing it to alternatives.

    -------------------------------------------
    Thomas Nunnikhoven
    International Paper
    -------------------------------------------








  • 11.  RE:STATISTICA is good substitution for SAS

    Posted 01-23-2014 15:06
    Unless an analysis is tied to using a specific feature of SAS, I suggest using R (it is free, and many wonderful statisticians have written code for it).

    There are many free tutorials on the internet, as well as plenty of texts on Amazon covering a wide range of topics.

    SAS has its pluses, but its price is usually not one if them.

    -------------------------------------------
    Mark Lancaster
    George Mason University
    -------------------------------------------





  • 12.  RE:STATISTICA is good substitution for SAS

    Posted 01-23-2014 14:39
    Given your budget, Is R (for free) an option for you?

    -------------------------------------------
    Chris Barker, Ph.D.
    Consultant and
    Adjunct Associate Professor of Biostatistics
    www,barkerstats.com

    ---
    "In composition you have all the time you want to decide what to say in 15 seconds, in improvisation you have 15 seconds."
    -Steve Lacy
    -------------------------------------------








  • 13.  RE:STATISTICA is good substitution for SAS

    Posted 01-23-2014 15:02

    Hi Shauang,

    SAS is the industry standard for the most part. FDA sure wants it used.  I agree with Paul and Patrick who stated that if you know SAS and are trained in SAS then SAS is the best for you to use.  I also agree with Paul in the vein that a company should invest in the product that will return the best results for them, even if it cost more.  I have SAS on my computer for clinical trial work.  Gotta have it!  It costs so much I have to depreciate the expense, but it is worth it.

    Personally though, I love STATA. It does everything and for a couple of hundred dollars more I have the entire set of documentation. 

    R is great if you need to write programs from scratch, and being open source, someone has probably written what you need already (but being open source, you can't be absolutely certain of the accuracy of the algorithms).

    SPSS is user friendly, used by many academic institutions, and we use it here quite a bit.  But try building a mixed model with it...grrrrr.  I really wish I could use STATA more, lol

    Statistica..I see it advertised in the ASA magazines a lot.  But I haven't used it.  That doesn't mean it isn't good though.

    Best,

    Elaine


    -------------------------------------------
    Elaine Eisenbeisz
    Owner and Principal Statistician
    Omega Statistics
    -------------------------------------------








  • 14.  RE:STATISTICA is good substitution for SAS

    Posted 01-26-2014 19:12

    "(but being open source, you can't be absolutely certain of the accuracy of the algorithms [in R])."

    This comment makes no sense to me. It is close-source software for which you can't be absolutely certain of the accuracy of the algorithms -- it's a black box that you can't peer inside. With open-source software you -- and more importantly, a wide array of experts -- can take a look at the code and find out exactly what algorithms are used and how they are implemented. And, as far as R is concerned, a great many of the packages are in fact written by leading experts in their fields.

    Another consideration that is entirely orthogonal to the open/closed-source distinction is simply the size of the user base. The more people use a piece of software, the more bugs tend to be found and fixed. So, all else being equal, favor the more widely used piece of software.

    -------------------------------------------
    Kevin Van Horn
    -------------------------------------------




  • 15.  RE:STATISTICA is good substitution for SAS

    Posted 01-23-2014 17:03

    Hi.  I've used both SAS and Statistica, along with R, Minitab, etc.  Most of my work is non-clinical (industrial processes, quality, reliability, design V&V).  Having access to SAS was great, but - as others have pointed out - it has a price tag that draws attention.

    In the recent past, SAS was (and currently is) beyond what is available in the budget.  I use Statistica for a lot of 'standard' work, to include linear models and generalized LMs, including mixed models.

    I have also had some recent success with the Statistica Visual Basic functionality (I'm not an expert with VB programming, but figured it out with their help forum) when I needed to write and automate script with sequential processing of results.  And another reason I chose Statistica was because they offer enterprise scalability at a reasonable price (as do many other packages, but not all).  I believe that Statistica has spent some effort positioning themselves as an alternative for SAS, including for clinical trials.

    Having said this, I use R more often these days.  While I like the standard tools in R, it is especially useful if I need to customize or explore beyond the boundaries offered by menu-driven packages.

    Whatever package you choose, you may want to consider taking the time to verify the functionality that you are using against some benchmark.  NIST has some useful materials (reference data sets and results) that are freely available at http://www.itl.nist.gov/div898/strd/.  And document the results.  I did this when working in an FDA-regulated environment and it came in handy several times.

    -------------------------------------------
    Clifford Long
    -------------------------------------------








  • 16.  RE:STATISTICA is good substitution for SAS

    Posted 01-24-2014 09:39
    Hello Group, one  software I have not seen mentioned is one I've used in my solo practice for over 25 years and that is NCSS [NCSS.Com].  It has a full menu of regression, ANOVA, multivariate, mixed model routines.  Plus wonderful graphics and the usual basic statistics complement.  The price is very attractive.  The output is in RTF format and thus very friendly for inserting into documents, reports etc.  I suggest taking a look and judging for yourself.  They have advertised in AMSTAT News for years.

    John Bartko

    -------------------------------------------
    John Bartko
    Consulting Biostatistician
    -------------------------------------------








  • 17.  RE:STATISTICA is good substitution for SAS

    Posted 01-24-2014 09:57
    One I haven't seen mentioned yet is Systat (apologies if I missed it).  Systat has the menu-driven interface of SPSS, if you like that, but remains closer to the command line than SPSS.  Graphics are comparable to SPSS. 

    As far as I remember it is well-priced and quite complete in the standard package, meaning it does not force you to pay extra to get essential procedures in a bunch of pricey add-on modules.  Customer support has been very good, in my experience.

    Dave

    -------------------------------------------
    David G. McBride
    Office of Epidemiology
    Missouri Department of Health and Senior Services
    -------------------------------------------








  • 18.  RE:STATISTICA is good substitution for SAS

    Posted 01-27-2014 02:22

    I've used Stata now for several years and overall I'm quite satisfied with it.  I do most data management and EDA with Stata and R or specialized packages when functionality not offered by Stat is required.  The main downside for me is the complicated pricing structure, which varies by the number of processors.

    Regards,

    Kevin Gray
    Cannon Gray LLC
    -------------------------------------------








  • 19.  RE:STATISTICA is good substitution for SAS

    Posted 01-24-2014 12:06
    I have some experience with Statistica, because I use it in the biostatistics class I teach for the Pharm/Tox department at WSU.  Although it is menu-driven, it is not an intuitive program to use. After using SAS in consulting for many years, I found Statistica a bit annoying.  As someone else pointed out, there are too many buttons!!

    Bottom line, go with something that you will be comfortable using.

    -------------------------------------------
    Beverly Grunden
    Statistical Consultant
    Wright State University
    -------------------------------------------








  • 20.  RE:STATISTICA is good substitution for SAS

    Posted 01-24-2014 12:33
    Well, since no one else has mentioned it, I will.  I have been using JMP (from SAS Institute) for over two years now and am well pleased with it.  Very versatile: very broad coverage of statistical analyses integrated with excellent graphics, combined with very good data handling capabilities.  Can do various simulations, too.

    Single user license lists at $1470, about half that for academic institutions.  JMP Pro way more expensive...

    -------------------------------------------
    Wayne Fischer
    Statistician
    University of Texas Medical Branch
    -------------------------------------------








  • 21.  RE:STATISTICA is good substitution for SAS

    Posted 03-12-2014 13:59
    Some thoughts on choosing a stat package (in no special order).

    A lot depends on what kind of work you are doing.

    There is a prevailing idea that FDA requires use of SAS, even though that would be an illegal requirement. However, it can be easier to go along to get along.

    If you are in a field where clean data is supplied, then then it makes less difference which package you use.  If data is generated by people it can very messy and dealing with the mess is an important consideration.

    Be sure that comparisons are based on current capabilities.  For example, in the early 80s, default SAS would take about twice the machine resources to read a 1.5 million record file and do a single procedure as would default SPSS. Today machines resources are not as much of a consideration as they were then.
    SAS would only run on IBM hardware.  Today SAS runs on many platforms.  I do not recall where but sometime in the last week I saw a claim on a discussion list that SPSS does not do mixed models.  It does for many years. Likewise a few months ago I saw a statement on a discussion list that SPSS does not do general linear models, generalized linear models, or complex samples. Historically each of those statements were true at one time, but not for many years.

    For packages that have modules, it is not necessary for every user to have access to all of the modules all of the time.  

    Many packages can write files in the format for other packages.

    Beware of slanted views. I have heard people say that SPSS had to be useless because the very idea of social science is nonsense. I've heard "SAS is only for ag experiments".

    Some packages can interface easily with other resources such as python or R. E.g., SPSS can call R. That way all the data prep can be done in SPSS and if one wants something less common one can use are without dealing with its data handling.  

    If the users and QA reviewers are strong readers of English, then readability of syntax is a big advantage.

    If tasks are diverse, then similarity between procedure syntax is an advantage.  That is less of a consideration if you just do one narrow type of statistics.

    If you have large amounts of data, then a package that hold  all data in RAM is a disadvantage.

    In some disciplines it is not unusual for 95% of the labor hours using a package, in those circumstances human factors aspects are extremely important.

    Ease of extensive labeling helps non-statisticians or beginners interpret results.

    It can be useful for developing syntax to be able to distinguish whether (a) the value of a variable is missing because the system cannot follow your instructions, e.g, input does not match the format specified or the instructions call for unreasonable operations like square root of a negative number OR
    (b) is missing for a known reason like this case was not selected for a sample vs refused to respond at all vs skipped this item, etc.  In some fields, it is good practice to be sure that data contains no missing values for reasons that are not specified.  I have found this very useful in developing syntax.



    Packages that are strictly point and click can be great for small projects like small exercises. However they do not have the audit trail necessary for projects where quality review or maintainability are important.  However, a GUI that can <paste> syntax can be useful for producing early drafts of syntax.  In my experience, YMMV, cleaning, prepping, and analysis is an iterative process like any other writing. {I have even gone back an rephrased part of this post.}  Whether you call it "an audit trail", "due diligence", "careful communication", or "CYA" availability of syntax is a major consideration.


    When I have clients who want to distribute data for public use, I suggest that they have at least 1 seat that has SPSS which carries the most metadata in its system files (value labels for valid and missing values, level of measurement, variable labels etc. ) . Then completely fill in the variables view which shows the metadata. Then it is simple to "save as" SPSS, SAS, flat file, csv, etc.  DISPLAY DICTIONARY provides documentation that can be used in conjunction packages that hold less metadata in their system files.

    In my experience , YMMV, purchase cost is only a small part of total cost of ownership.  Money and calendar time costs for time to write syntax, clean and prep the data, ease of QA review, create a solid audit trail vastly outweigh purchase cost as part of the long term total cost of operation.

    There are strong reasons not to use EXCEL for actual statistics. See the links below.  I do use it for small spreadsheet tasks for which it was designed.  It can be useful as a data entry tool put the data together.


    The following  is from one of my soapbox posts, apologies to those of you who are tired of my making this point.

    Using spreadsheets for stat can be like using a hammer to drive a screw.

    IF I RECALL CORRECTLY any accounting system that uses computer spreadsheets cannot pass ISO certification. I believe this is at least partly due to the difficulties in tracing exactly what was done.

    I do use Excel Pro or tables in WordPerfect several times a week.
    Sometimes it is practical to enter data via a spreadsheet and then read it into a stat package e.g., SPSS, for checking double entry and quality checks. [This is because spread sheets are usually available, but it not cost effective to provide  stat package to every person who will do data entry.]

    For an overview of the issues:
    A video can be found at
    http://www.spss.com/events/event.cfm?E_ID=2921&Country=US

    A pdf can be found by clicking
    <The Risks of Using Spreadsheets in Data Analysis>


    For more technical review see.

    http://www.pages.drexel.edu/~bdm25/excel-intro.pdf

    http://www.pages.drexel.edu/~bdm25/excel2007.pdf

    http://www.pages.drexel.edu/~bdm25/excel-rng.pdf

    an instructional link is
    http://www.umass.edu/statdata/software/handouts/excel.html.



    -------------------------------------------
    Arthur Kendall
    Social Research Consultants
    -------------------------------------------








  • 22.  RE:STATISTICA is good substitution for SAS

    Posted 01-24-2014 13:12
    I have never used Statistica. A key question about it:

    Can you record or journal the analysis? By that I mean can you create a record of the analysis which allows you to repeat the analysis again without pressing buttons?

    If you cannot do that, it is not a professional tool. If you cannot record the analysis for later auditing, then it should not be used.

    Can an experienced Statistica user answer that question?

    -------------------------------------------
    Paul Thompson
    Director, Methodology and Data Analysis Center
    Sanford Research/USD
    -------------------------------------------








  • 23.  RE:STATISTICA is good substitution for SAS

    Posted 01-24-2014 14:13

    Hi Paul,

    Statistica has an option to make the script available.  This can be either what they call the 'model syntax', or it can be available through VB code.  I always included the model syntax in my reports so that the analysis could be duplicated if/when needed (or to show behind-the-scenes options that might be chosen).  And there are tools to automatically add it to a report (written to Word, an integrated Statistica report, etc.).

    Cliff


    -------------------------------------------
    Clifford Long
    Director of Quality Engineering
    ACCO Brands Corporation
    -------------------------------------------








  • 24.  RE:STATISTICA is good substitution for SAS

    Posted 01-24-2014 17:54
    I used SAS at the corporation where I worked before retiring, but cannot afford it as a part-time sole proprietor consultant.  I evaluated Statistica for use by laboratory personnel before retiring, and acquired enough knowledge to continue using it.  I have used it routinely for several years now.  It does include automatic generation of editable Visual Basic programs for repeating or extending analyses.  Statistica graphics are excellent  There are add-ons, at a price, for such things as neural network code generation, but the basic package is sufficient for most purposes.  There may not be enough flexibility for formatting output, but I confess to being purely self-taught.  As for "too many buttons", I think any full-function system involves a learning curve.
     

    -------------------------------------------
    Archie Swindell
    -------------------------------------------








  • 25.  RE:STATISTICA is good substitution for SAS

    Posted 01-24-2014 19:10
    When I can't get an institution to buy/ lease stat software for me I use the R suite of programs. Cutting edge & you can't beat the price--it's freeware.

    -------------------------------------------
    W. Vogt
    Professor
    -------------------------------------------





  • 26.  RE:STATISTICA is good substitution for SAS

    Posted 01-26-2014 22:27
    Many good packages have been mentioned.  I would argue that many of us function better with more than one package taking advantage of the strengths of certain packages and avoiding the weaknesses when we have more than one package to choose from.  I would certainly recommend R either as a primary or secondary package.

    Because you know SAS, I suggest consideration the latest edition of the book "R for SAS and SPSS Users" even if you can swing getting SAS.  (Even the first edition was excellent.)

    -------------------------------------------
    James Baldwin
    Station Statistician
    US Forest Service
    -------------------------------------------