Regressit and Statistician Lite are both Excel add ins, and the rest are stand alone statistics programs.
G*Power is a tool to compute statistical power analyses for many different t tests, F tests, χ2 tests, z tests and some exact tests. G*Power can also be used to compute effect sizes and to display graphically the results of power analyses.
MacAnova is a free, open source, interactive statistical analysis program for Windows, Macintosh, and Linux written by Gary W. Oehlert and Christopher Bingham, both of the School of Statistics, University of Minnesota. In spite of its name, MacAnova is not just for Macintosh computers and not just for doing Analysis of Variance. MacAnova has many capabilities but its strengths are analysis of variance and related models, matrix algebra, time series analysis (time and frequency domain), and (to a lesser extent) uni- and multi-variate exploratory statistics.
Core MacAnova has a functional/command oriented interface, but an increasing number of capabilities are available through a menu/dialog/mouse type interface. Although the language and syntax are S-like (for those of you familiar with S, S-Plus or R), MacAnova is not S or R.
PSPP is a free program for statistical analysis of sampled data. It is similar to SPSS with a few exceptions. PSPP is particularly aimed at statisticians, social scientists and students requiring fast convenient analysis of sampled data. PSPP can perform several data transformation (including recoding, weighting and handling of missing values), compute descriptive statistics (frequencies, descriptive statistics), compute crosstabs and explore tables, T-tests (one sample T-test, independent samples T-test, paired samples T-test) and one-way ANOVA, bivariate correlation, linear regression, factor analysis (Principal Component Analysis and Principal Axis Factoring), Chronbach Alpha (reliability measure), ROC curve and some non-parametric tests (Chi-square and Binominal).
R is probably the most sophisticated statistics software available. The learning curve is fairly steep, but the availability of hundreds of add-on packages mean that almost anything can be accomplished. R is ‘GNU S’, a freely available language and environment for statistical computing and graphics which provides a wide variety of statistical and graphical techniques: linear and nonlinear modelling, statistical tests, time series analysis, classification, clustering, etc.
An Excel add-in that was developed in a teaching environment but is also intended for serious applied work as a complement or substitute for other linear regression software. It performs multivariate descriptive data analysis and multiple linear regression, and it offers a number of features that are designed to promote good modeling practices and high-bandwidth communication. The output for each descriptive analysis or regression model is stored on a separate worksheet within the same workbook. All chart output is presentation-quality and in native Excel format that can be edited, and all table output is intelligently formatted to show enough decimal places of precision but not too many. The descriptive analysis procedure can draw very detailed scatterplot matrices (each element of which is a separate chart that may include a regression line and center-of-mass point) and parallel time series plots of many variables, in addition to summary statistics and correlation matrices. The regression procedure makes it simple to explore variations on previously fitted models, it provides ample chart output with good support for testing model assumptions, and it offers several options for generating out-of-sample forecasts. A separate variable transformation procedure makes it easy to apply nonlinear and time transformations to variables in a systematic way. The program also includes a number of audit trail features (date/time/username stamps on all worksheets, unique model names in all table and chart titles, and an additional worksheet with side-by-side comparisons of models) that help to organize and authenticate the results of fitting many models to the same data.
Years of experience teaching undergraduates and postgraduates struggling to analyse experimental statistics on computer has showed us how programs should work with people not despite them. We want people to analyse data with ease through friendly software that augments the way we need to work.
- t-test (1 sample)
- t-test for two samples (within and between subjects)
- Univariate ANOVA (within and between subjects)
- Linear regression
- Sign test
- Chi square
- Mann-Whitney U
- Wilcoxon sign-ranks
- Wilcoxon rank-sums
Statistical software for fast and easy interpretation of experimental data in science and R&D in a technical environment. This statistical package helps with analysis and prevents making false assumptions. In short it makes statistics faster and easier, suitable for less experience users but advanced enough for more demanding users.
Develve has no deep hidden menus, everything is directly accessible and the results are directly visible, to improve the productivity. For instance the result graphs are easily scrollable and with a click on a graph a bigger version will pop up. When comparing different datasets it is directly indicated if the difference in average and variation is significant and if the sample size is big enough to prevent false assumptions. For a Design of Experiments Develve helps to create a test matrix. When a factor is not in balance Develve will detect this.
- Sample counting n
- Cp Cpk % out of tolerance
- Compare with
- Variation F-test
- Variation Levene test
- Anderson Darling normality test
- Correlation test
- Multiple linear Regression
- Sample size calculations
- Box-Cox transformation
- Generate distribution
- Proportion calculation
- One way Anova
- Kruskal-Wallis Test
Design of experiments (DOE)
- Up to 12 levels
- 10 repetitions
- Open standard orthogonal arrays and full factorial arrays
- Anova DOE
- Confirmation run
- Including response graphs
- Calculate the doe on one Column out of the result array or all the columns
SOFA is a user-friendly statistics, analysis, & reporting program. It is free, with an emphasis on ease of use, learn as you go, and beautiful output. SOFA lets you display results in an attractive format ready to share. And SOFA will help you learn as you go. Many statistics programs make you import data from a database before you can use it. Not SOFA. You can connect directly to your database, and all its tables. Just give SOFA the login details. You can even edit data from within SOFA, or apply a simple data filter to focus on the subset of a table you are interested in. SOFA currently supports:
Microsoft SQL Server
What if your project has data in more than one database? No problem. SOFA lets you work with any tables wherever they may be and whichever (supported) database type they are stored in.
Spreadsheet Friendly Output – SOFA tabular output is already in a form that can be directly opened in MS Excel or pasted into OpenOffice Calc.
- SOFA can import data from Excel spreadsheets into its built-in SQLite database.
- ODS spreadsheets can be imported from both Open Office Calc and Gnumeric.
- Data in CSV or tab-separated format can be imported into SOFA Statistics.
- Data can be imported from on-line Google Docs Spreadsheets.
- All imported data can be viewed and edited within SOFA.
Exporting – SOFA can export data into an Excel spreadsheet format (readable by open source spreadsheets as well).
Data Entry Friendly – You can now add data directly to SOFA Statistics by configuring new tables in the built-in SQLite database and adding data directly to them. It is also possible to redesign and delete tables.
Easy Data Recoding – It is easy to recode your data using a simple form – e.g. if your data contains age but you need to analyse by age group you can recode MIN TO 19 as 1 with a label of “Under 20”, 20 TO 39 as 2 with a label of “20-39” etc.
Output You Can Share Easily – Tabular output is in HTML, which means you can put it directly on your intranet or website, or put it in a spreadsheet.
SOFA has a wide range of attractive, high quality charts including:
- simple bar charts (freq or means)
- clustered bar charts (freq or means)
- pie charts
- single and multiple line charts (freq or means)
- area charts (freq or means)
- box and whisker plots
It is also possible to create chart series. There is even some eye candy.
SOFA will make it easy to conduct and report on the use of:
- Row and column percentages, with the ability to nest variables e.g look at Ethnicity and Gender vs Age
- Lower Quartile
- Upper Quartile
- Standard Deviation
- N items
- Pearson’s Chi-Square with Contingency Tables
- Independent samples t-test
- Paired samples t-test
- One-way ANOVA
- Mann Whitney U
- Wilcoxon Signed Ranks
- Kruskal Wallis H
- Pearson’s Correlation
- Spearman’s Correlation
Learn As You Go
A central goal of SOFA Statistics is to make Statistics Open For All. Secondary school students, for example, should be able to use SOFA to learn more about statistics. And other users will also benefit from the educational orientation of the program.
The Statistical Lab is an explorative and interactive tool designed both to support education in statistics and provide a tool for the simulation and solution of statistical problems. The graphical user interface is designed to make complex statistical relations easy to understand. It connects and displays data frames, frequency tables, random numbers or matrixes in a user-friendly statistical worksheet allowing users to run calculations, conduct analyses and perform multiple simulations and manipulations.
Statistician is a comprehensive yet simple to use add-in for Microsoft Excel 2007 or later. The software performs high quality statistical analysis based on series of easy to use forms, activated via the Excel ribbon. The program is available in two versions – Statistician Lite (Free), and Statistician Standard ($US195) which includes many additional statistical models and functions.
Statistician works in a unique way when compared to other Excel based statistical analysis software. Most importantly, it allows the user to store a data set and perform multiple analyses on it, a method used by all high end statistical software, but lacking in many other Excel add-ins which require the user to reselect data over and over again when they return to the spreadsheet.