Free statistical software

From Infogalactic: the planetary knowledge core
Jump to: navigation, search

<templatestyles src="Module:Hatnote/styles.css"></templatestyles>

In this article, the word "free" generally means "no money expenses" (as in "free ice-cream"). Just a few of the software packages mentioned here are also "free" as in the sense of "free speech": they are not only open source but also free software in the sense that the source code of the software is freely available and can be freely modified by anyone who so desires, and even also distributed to others, as long as those re-distributed modifications remain free in exactly this same strong sense.

Lua error in package.lua at line 80: module 'strict' not found.

Free statistical software is a practical alternative to commercial packages. In general, free statistical software gives results that are the same as the results from commercial programs, and many of the packages are fairly easy to learn, using menu systems, although a few are command-driven. These packages come from a variety of sources, including governments, nongovernmental organizations (NGOs) like UNESCO, and universities, and are also developed by individuals.

Some packages are developed for specific purposes (e.g., time series analysis, factor analysis, calculators for probability distributions, etc.), while others are general packages, with a variety of statistical procedures. Others are meta-packages or statistical computing environments, which allow the user to code completely new statistical procedures. This article is a review of the general statistical packages.

Brief history of free statistical software

Some of the free software packages are from governmental or NGO organizations, such as Epi Info, from CDC[1] (Centers for Disease Control and Prevention), and IDAMS from UNESCO.[2] Some other software packages are from smaller or independent organizations or universities, such as Instat[3] or Irristat.[4] Two other packages, R,[5] and PSPP are being developed as part of the GNU Project by a large group of individuals, many of them volunteers, all over the world. These packages are notable in that it is not just open source but also free software in the same sense that material written on Wikipedia is free: others can edit, use, and redistribute at will.

A large proportion of free statistical software packages, however, are from individuals. Some of these software packages from individuals include Easyreg,[6] MicrOsiris,[7] OpenStat,[8] PSPP,[9] SOFA,[10] Zelig.[11] and DataMelt[12]

At least one package, WinIDAMS, was developed for the purposes of making key technologies available to those who could not otherwise afford them, to empower development.[13] OpenStat and Instat were developed as teaching aids.[3][8] Other packages were developed for specific purposes but can be more generally used. Examples are Irristat,[4] developed for agricultural analysis, and Epi Info,[1] developed for public health. Several of the packages, PSPP, R and Osiris don't appear to give any statements about why they were developed, other than just general use for statistical analysis.

These free software packages have been used in a number of scholarly publications. For example, OpenStat was used in a research letter to JAMA[14] and in several published studies.[15][16][17] Irristat is used in an agricultural report,[18] EasyReg is listed or used in several papers,[19][20][21] EpiInfo was also used in several papers,[22][23][24] R was used in a number of papers[25][26][27] and WinIdams was used in other papers.[28][29]

While Microsiris doesn't appear to be used in academic research, the author of the program was one of the original authors of OSIRIS,[30] which was the starting program from which WinIdams was developed.[31] The author of Microsiris also has contributed or co-contributed several components to WinIdams.[31]

Reviews of free statistical software

There are a few reviews of free statistical software. There were two reviews in journals (but not peer reviewed), one by Zhu and Kuljaca[32] and another article by Grant that included mainly a brief review of R.[33] Zhu and Kuljaca outlined some useful characteristics of software, such as ease of use, having a number of statistical procedures and ability to develop new procedures. They reviewed several programs and identified which ones, at that time, had the most functionality. At that time, several of the programs may not have had all of the desired ability for advanced statistics. Grant reviewed some of the programing features of R, and briefly mentioned the availability of other programs. One other paper reviewed statistical packages, mainly commercial, but includes R.[34] One article reviewed EasyReg and included a discussion of its accuracy.[35]

Only one review has compared the output of various packages.[36] In this review, all of the packages read either CSV files or Microsoft Excel format. All of the packages gave exactly the same results for correlation and regression. The free software packages also gave the same regression results as did excel. One of the main differences among the packages was how they handled missing data. With the example data sets used in the review, and for the package versions available in November 2006 when this review was conducted, two packages, MicrOsiris and Epi Info, could read files with blanks for missing. Two other programs, Stat4U and WinIdams need something for the missing, like -9 or -9.99. The other packages could only handle data sets with no missing values.

Two websites that list software also have very brief reviews of each package. These two sites are StatCon[37] and by Pezzullo.[38] These sites mainly offer a brief list of the features available in the packages. Similarly, one other web site compares the statistical procedures available on free statistical packages.[39] In this review, R had all of the procedures, OpenStat had 16, MacAnova had 15, and Microsiris had 12. The others had from 8 to 11 of the procedures.

There is also a journal specifically for statistical software,[40] although the main focus is on commercial software, R and some coding snippets.

In contrast, there are various reviews of commercial statistical software, such as a comparison between several major packages[41] and a brief review of several packages.[42]

Using free statistical software

Before using any statistical packages, it is generally a good idea to have a solid background in Statistics. Then the packages can be used to the best advantage, for example, to choose the most appropriate test, to make sure all the necessary assumptions are met, so that the appropriate conclusions can be drawn.

Once the statistical issues are understood, the next step is to decide which package to use. Most of these packages are menu driven, and can be learned in a couple of hours at most, except R, which is generally code driven and requires a much longer time to learn, and to some extent CDC's Epi Info, which also takes some time to learn.

Several of the packages also have tutorials. These tutorials help with a basic introduction and learning the basics of the programs. For example, CDC has tutorials about Epi Info[43],.[44] The CDC page also lists a video slide show tutorial from the University of Nebraska,[45] and another site has on line training classes,.[46] R has a large number of tutorials and manuals, in English and other languages[47][48][49] and a faq site.[50] A few of the packages have email discussion lists, including R[51] and PSPP.[52]/ The DataMelt has an active forum, FAQ and an online manual

Most of the packages have on line manuals, guides or help pages. These manuals or guides are useful when there are questions about specific procedures or statistical tests. Some manuals or guides are for R,[53] EasyReg,[54] OpenStat,[8] PSPP,[55] Vista,[56] WinIdams[57],,[58] Microsiris[59] and Zelig.[11] The CDC EpiInfo site itself does not have a manual, but one faculty member from Emory's School of Public Health has an introductory manual.[60] The DataMelt program is based on the book,[12] but also an extensive online manual and help system exist.[61]

Finally, there are a number of commercial packages such as SAS,[62] SPSS[63] and many others.[64] Most of the major commercial and free packages have many statistical procedures in common. The main reason to use free packages is probably the cost.

Menu driven packages

Many of the packages have some kind of opening menu that is used to get or enter the data, manipulate the data, and select the statistical analysis. Then after starting the program, generally data can be obtained, either from previously saved data sets, or importing from some other format. From this menu, data files in various formats can be imported. For example if the data is in CSV form (text with commas between values), the program recognizes the format and creates a data set from the CSV file. Finally, the program can be used to do some analysis. In this analysis menu, the variables of interest can be selected, along with other options. Then the analysis is run and results are obtained.

Command driven packages

A few programs, like WinIDAMS, need commands for many of their procedures. WinIDAMS does have an interactive menu to read in data, but then specific statistical procedures need a set of text commands. For example, the text command lines for frequencies look like this:

$COMMENT basic freqs of testing data
$RUN TABLES
$FILES
DICTIN = PD_data_idams.dic
DATAIN = PD_data_idams.dat
$SETUP
FREQUENCY TABLES
PRINT=(CDICT)
TABLES
ROWVARS=(V21) CELLS=(ROWP,FREQS)

This set of commands identifies procedure (tables), the data set and dictionary (PD_data_idams.dat and dic) and the variables. The procedures all have various options outlined in the manuals.

R can be used both in a menu-driven way and as a programming language and as an interpreter.

SCaVis is mainly a command driven package that uses scripting languages, such as Jython (Python implemented in Java), Groovy, JRuby. Java coding is also possible.

Getting data

Most packages are able to import data from excel or CSV (text with commas separating values).

One consideration is whether there are missing data. Some packages, like PSPP and MicrOsiris, can automatically deal with the missing data. So for example, say one set of data look like this:

Name Age Sex Born in US Degree
Joe 31 M Yes BA
Sam M No MS
Sally 28 F Ph.D.

In this data set, Sam is missing age, and Sally is missing whether she was born in the USA. When some packages, like PSPP or MicrOsiris, read in or import the original data set, the packages will recognize that those values are missing, and do their calculations accordingly. MicrOsiris automatically assigns 1.5 or 1.6 billion to blanks as missing, and these values are excluded from analysis.[59]

Other packages need a 'place holder', such as '-9' where there is missing data.[65] Before the package is used to read the data, the data set has to be edited to put in place holder where there are missing data. So for example:

Name Age Sex Born in US Degree
Cole 31 M Yes BA
Sam -9 M No MS
Sally 28 F -9 Ph.D.

If the data set actually includes '-9', then when the data is being read in the program will have to be told when the -9 means missing data.

Limitations of packages

Most of the packages have limitations of some sort.

Variables in WidIDAMS are limited to 9 digits in length[58] and so have to be manipulated before analysis. Several of the programs, including Easyreg, Epidata and Instat, do not appear to handle missing data or do not handle it well.[36] While EpiInfo has many statistical procedures, correlation is not one of them. Rather correlation is found by regression.[66] This means that EpiInfo will not produce a single table showing correlations among multiple variables. According to the Zelig installation manual, use of Zelig requires that R and several of its libraries already be installed, and the installation also requires some degree of background in R.[11] One limit of MicrOsiris is in handling the output. When calculations are complete, the output pages through the results, but various menu boxes also appear over the results, and so the results cannot be accessed. The output can be saved, though, as a text file and then used.

One limitation is specific to programs that were developed by individuals. Support for these programs is limited to the time that the author has available. While the authors may, and often do, respond fairly quickly when there are few people asking questions, if too many people ask questions or the author is otherwise busy, support would correspondingly be slower.

R is both written by and used by a large number of people all over the world, and many internet-fora and other internet facilities can be used to get support from other users. While R is powerful, the learning curve can be rather steep for those not already familiar with other kinds of scientific programming.[67]

See also

References

  1. ↑ 1.0 1.1 Lua error in package.lua at line 80: module 'strict' not found.
  2. ↑ Lua error in package.lua at line 80: module 'strict' not found.
  3. ↑ 3.0 3.1 Lua error in package.lua at line 80: module 'strict' not found.
  4. ↑ 4.0 4.1 Lua error in package.lua at line 80: module 'strict' not found.
  5. ↑ Lua error in package.lua at line 80: module 'strict' not found.
  6. ↑ Lua error in package.lua at line 80: module 'strict' not found.
  7. ↑ Lua error in package.lua at line 80: module 'strict' not found.
  8. ↑ 8.0 8.1 8.2 Lua error in package.lua at line 80: module 'strict' not found.
  9. ↑ Lua error in package.lua at line 80: module 'strict' not found.
  10. ↑ Lua error in package.lua at line 80: module 'strict' not found.
  11. ↑ 11.0 11.1 11.2 Lua error in package.lua at line 80: module 'strict' not found.
  12. ↑ 12.0 12.1 S.V.Chekanov, Scientific Data analysis using Jython Scripting and Java. Book. 497p. (Springer-Verlag, 2010, ISBN 978-1-84996-286-5)
  13. ↑ Lua error in package.lua at line 80: module 'strict' not found.
  14. ↑ Lua error in package.lua at line 80: module 'strict' not found.
  15. ↑ Lua error in package.lua at line 80: module 'strict' not found.
  16. ↑ Lua error in package.lua at line 80: module 'strict' not found.
  17. ↑ Lua error in package.lua at line 80: module 'strict' not found.
  18. ↑ FAO Plant Production and Protection Paper No. 174, Rome, 2003, Genotype x environment interactions. Challenges and opportunities for plant breeding and cultivar recommendations, http://www.fao.org/DOCREP/005/Y4391E/y4391e00.htm
  19. ↑ Lua error in package.lua at line 80: module 'strict' not found.
  20. ↑ Lua error in package.lua at line 80: module 'strict' not found.
  21. ↑ Harumi Itoa and Darin Lee, Journal of Economics and Business, Volume 57, Issue 1, January–February 2005, Pages 75-95. Assessing the impact of the September 11 terrorist attacks on U.S. airline demand. doi 10.1016/j.jeconbus.2004.06.003. Also available here http://www.brown.edu/Departments/Economics/Papers/Papers/2003/2003-16_paper.pdf
  22. ↑ Rahav G, Gabbay R, Ornoy A, Shechtman S, Arnon J, Diav-Citrini O. Primary versus nonprimary cytomegalovirus infection during pregnancy, Israel. Emerg Infect Dis [serial on the Internet]. 2007 Nov [May 15, 2009]. Available from http://www.cdc.gov/EID/content/13/11/1791.htm
  23. ↑ Chan P-C, Huang L-M, Wu Y-C, Yang H-L, Chang I-S, Lu C-Y, et al. Tuberculosis in children and adolescents, Taiwan, 1996–2003. Emerg Infect Dis [serial on the Internet]. 2007 Sep. Available from http://www.cdc.gov/EID/content/13/9/1361.htm
  24. ↑ Lua error in package.lua at line 80: module 'strict' not found.
  25. ↑ Lua error in package.lua at line 80: module 'strict' not found.
  26. ↑ Lua error in package.lua at line 80: module 'strict' not found.
  27. ↑ Lua error in package.lua at line 80: module 'strict' not found.
  28. ↑ Lua error in package.lua at line 80: module 'strict' not found.
  29. ↑ Lua error in package.lua at line 80: module 'strict' not found.
  30. ↑ Data Sharing for Demographic Research Knowledge Base, question on OSIRIS, University of Michigan, http://dsdr-kb.psc.isr.umich.edu/answer.html?i=1076
  31. ↑ 31.0 31.1 IDAMS, Internationally Developed Data Analysis and Management Software Package. WinIDAMS Reference Manual (release 1.3) UNESCO, 2008. Preface. http://portal.unesco.org/ci/en/ev.php-URL_ID=25081&URL_DO=DO_TOPIC&URL_SECTION=-465.html
  32. ↑ "A Short Preview of Free Statistical Software Packages for Teaching Statistics to Industrial Technology Majors" Journal of Industrial Technology (Volume 21-2, April 2005), Ms. Xiaoping Zhu and Dr. Ognjen Kuljaca. http://www.nait.org/jit/current.html
  33. ↑ Felix Grant, "Free Statistics Software, Yours, Free to keep....", Scientific Computing World, Sept/Oct 2004, http://www.scientific-computing.com/scwsepoct04free_statistics.html
  34. ↑ Edward J. Wegman and Jeffrey L. Solka. 2005. Statistical Software for Today and Tomorrow. http://www.galaxy.gmu.edu/ (listed as "A Guide to Statistical Software".
  35. ↑ Lua error in package.lua at line 80: module 'strict' not found.
  36. ↑ 36.0 36.1 Shackman, Gene. 2006. "Comparing free statistical software for data sets with no missing values" and "Comparing free statistical software, Handling missing data". Both available here "Free Software" http://gsociology.icaap.org/methods/soft.html
  37. ↑ List of free statistical software, Open Source & Public Domain Packages with Source Code. StatCon 2006. http://statistiksoftware.com/free_software.html
  38. ↑ Pezzullo, Free Statistical Software, 2009. http://statpages.org/javasta2.html
  39. ↑ Andrea Corsini. 2009. Free Statistics. Free statistical software comparisons. http://en.freestatistics.info/comp.php
  40. ↑ Journal of Statistical Software, http://www.jstatsoft.org/
  41. ↑ Lua error in package.lua at line 80: module 'strict' not found. Summarized in Hom, Willard. 2006. Choosing Between SAS, Stata, and SPSS. http://www.cccco.edu/SystemOffice/Divisions/TechResearchInfo/ResearchandPlanning/AbstractsofResearch/ResearchMethods/tabid/302/Default.aspx
  42. ↑ Wass, John. No date. Comparative Statistical Software Review. Tabulations and musings from your editor's biased perspective. Scientific Computing. http://www.scientificcomputing.com/comparative-statistical-software.aspx
  43. ↑ Epi Info™ Community Health Assessment Tutorial. The Epi Info™ Community Health Assessment Tutorial was produced by the collaborative efforts of the Centers for Disease Control and Prevention (CDC), the Assessment Initiative (AI), and the New York State Department of Health (NYSDOH). http://www.cdc.gov/epiinfo/communityhealth.htm
  44. ↑ Cholera Outbreak in Rwenshama: Using Epi Info for Windows in an Outbreak Investigation. Coordinating Office for Global Health - DGPHCD, http://www.cdc.gov/cogh/dgphcd/training/softwaretraining.htm
  45. ↑ Introduction to EPI2000. GPVEC Great Plains Veterinary Educational Center. University of Nebraska - Lincoln. http://gpvec.unl.edu/videos/epi-stats.asp
  46. ↑ The North Carolina Center for Public Health Preparedness Training Website http://nccphp.sph.unc.edu/training/index.html
  47. ↑ Contributed Documentation. PSPP has a particularly easy to follow tutorial, and a rich set of statistical analyses, including T-test, Oneway and Factorial Anova, Linear and Logistic regression and Principal components analysis. It also has provision for it to be very easy to import data from many other different file formats. http://cran.r-project.org/other-docs.html.
  48. ↑ William Revelle, Using R for psychological research: A simple guide to an elegant package, 2008, http://personality-project.org/r/
  49. ↑ Dong-Yun Kim, MAT 356 R Tutorial, Spring 2004. http://www.math.ilstu.edu/dhkim/Rstuff/Rtutor.html
  50. ↑ R FAQ. Frequently Asked Questions on R. Version 2.8.2009-03-18. ISBN 3-900051-08-9 http://lib.stat.cmu.edu/R/CRAN/doc/FAQ/R-FAQ.html
  51. ↑ R-help -- Main R Mailing List: Primary help. https://stat.ethz.ch/mailman/listinfo/r-help
  52. ↑ Pspp-users -- PSPP user discussion, http://lists.gnu.org/mailman/listinfo/pspp-users
  53. ↑ R Development Core Team. An Introduction to R. Version 2.8.1 (2008-12-22). ISBN 3-900051-12-7. http://cran.r-project.org/doc/manuals/R-intro.html
  54. ↑ Herman J. Bierens. EasyReg International: Guided tours. No Date Given. http://econ.la.psu.edu/~hbierens/ERITOURS.HTM
  55. ↑ Documentation, No Date Given. PSPP. https://www.gnu.org/software/pspp/documentation.html
  56. ↑ Forrest W. Young, 1996. ViSta User's Guide. http://forrest.psych.unc.edu/research/
  57. ↑ P.S. Nagpaul. 1999. Guide to Advanced Data Analysis using IDAMS Software. http://www.unesco.org/webworld/idams/advguide/TOC.htm
  58. ↑ 58.0 58.1 Unesco. 2008. WinIDAMS 1.3 Reference Manual - Table of Contents. http://www.unesco.org/webworld/portal/idams/html/english/TOC.htm
  59. ↑ 59.0 59.1 Van Eck, Richard, Microsiris, Statistical and Data Management Software System. Version 9.1, 2006. Van Eck Computer Consulting. http://www.microsiris.com/MicrOsiris.htm
  60. ↑ Kevin M. Sullivan. Mar 3 2008. Introduction to Epi Info (Version 3.4.1) Analyze Data Module. http://www.sph.emory.edu/~cdckms/
  61. ↑ S.Chekanov. The DataMelt manual http://jwork.org/dmelt/wikidoc/
  62. ↑ http://www.sas.com/
  63. ↑ http://www.spss.com/
  64. ↑ Statistics.com list of commercial software http://www.statistics.com/resources/software/commercial/fulllist.php3
  65. ↑ Unesco, How to work with WinIDAMS. Section on Missing data values. http://www.unesco.org/webworld/idams/selfteaching/eng/emissing-data.htm
  66. ↑ CDC. Epi Info Training Session. Using Epi Info in an Outbreak Investigation. Advanced Analysis and Mapping. http://www.cdc.gov/cogh/dgphcd/training/softwaretraining.htm
  67. ↑ Gillian Raab, Susan Purdon, Kathy Buckner and Iona Waterston. The R Package. Napier University (Edinburgh) and the National Centre for Social Research (London). http://www2.napier.ac.uk/depts/fhls/peas/rpackage.asp

This article incorporates material from the Citizendium article "Free statistical software", which is licensed under the Creative Commons Attribution-ShareAlike 3.0 Unported License but not under the GFDL.

External links to pages that list and describe free statistical software packages

Retrieved from "https://infogalactic.com/w/index.php?title=Free_statistical_software&oldid=721528631"