I am pleased to announce Release 9.5 of the Real Statistics Resource Pack. The new release is now available for free download at Download Resource Pack for Excel 2010, 2013, 2016, 2019, 2021, 2024, and 365 Windows and Mac environments.
Over the next few days the website will be updated for compatibility with the new release. [This has now been done]
I want to thank everyone who made suggestions or identified errors in the website or software. Your help has improved the utility and accuracy of Real Statistics.
I also want to express my appreciation to all of you who have donated to Real Statistics. These donations help offset the costs of maintaining the website. If you are getting value from the Real Statistic website or software, I would appreciate your donation by going to Please Donate.
The primary focus of the new release is Bayesian statistics. The following is an overview of the new features in Release 9.5.
Bayes Tab
The main menu has been modified with the inclusion of a Bayes tab. All the existing and new Bayesian-oriented data analysis tools have been consolidated on this tab.
For those of you, who are using the original user interface, a new Bayes option has been added that provides access to all the Bayesian data analysis tools. In addition, a new Charts option has been added that provides access to all the charts, plots and graph tools.
For those of you who are using Xrealstats.xlam (for Windows), I have also added a new Bayes function category.
Bayesian t Tests
Added a number of worksheet functions (BayesT_TEST, BayesT0_TEST, BayesTS_TEST, BayesTX_TEST, JZS_TEST, T_STAT, T_STATP, BayesZ_TEST) that support Bayesian z and t tests for a simple sample, paired samples, and independent samples. Also added a new Bayesian T Test data analysis tool.
See Bayesian T Test Tools for more details.
Also added new worksheet functions (JZS_EFFECT, BayesT_EFFECT, BayesT0_EFFECT, JZS_SIZE, BayesT_SIZE, BayesT0_SIZE) to determine the minimum sample size and effect size for the Bayesian t test.
See Bayesian t Test Sample Size for more details.
Bayesian Signed-Ranks Tests
Added a number of worksheet functions (BayesSRT, BayesSRX, BayesSRSm, BayesSRLg, BayesSR1Sm, BayesSR1Lg, BayesSR1X, BayesSR1) that support the Bayesian Signed Ranks test. Also added a new Bayesian Non-parametric Tests data analysis tool that supports the Bayesian SR test.
See Bayesian Signed-Ranks Test Support for more details.
Bayesian Mann-Whitney Test
Added a number of worksheet functions (BayesMWU, BayesMWX, BayesMWSm, BayesMWLg, BayesMW1Sm, BayesMW1Lg, BayesMW1X, BayesMW1) that support the Bayesian Mann-Whitney test. Also added a new Bayesian Non-parametric Tests data analysis tool that supports the Bayesian MW test.
See Bayesian Mann-Whitney Test Support for more details.
Bayesian Independence Test
Added worksheet functions (BayesIndep, DFunc) that support the Bayesian version of the chi-square test of independence for contingency tables. Also added a new Bayesian Independence Test data analysis tool.
See Bayesian Independence Testing Support for more details.
Bayesian Correlation Test
Added a new BayesCorrel worksheet function that support the Bayesian version of the correlation test. Also added a new Bayesian Correlation Test data analysis tool.
See Bayesian Correlation Testing for more details.
Bayesian Kendall’s Tau Correlation Test
Added new BayesTau, BayesKendall, and Bayes1Kendall worksheet functions that support the Bayesian version of Kendall’s tau non-parametric correlation test. Also added support for this test as an option to the new Bayesian Correlation Test data analysis tool.
See Bayesian Kendall’s Tau Test for more details.
Bayesian Gamma Test
Added new BayesGamma, TABLE2RAW, and RAW2TABLE worksheet functions that support the Bayesian version of Goodman’s Gamma non-parametric test. Also added the new Bayesian Gamma Test data analysis tool.
See Bayesian Gamma Test for more details.
Bayesian Beta Distribution Characteristics
Since we often use the beta distribution in Bayesian analyses, the Real Statistics Resource Pack has now added the BayesBeta worksheet function.
See Bayesian Characterization of a Beta Distribution for more details.
Bayesian Beta Test Effect and Sample Sizes
Since we often use the beta distribution in Bayesian analyses, the Real Statistics Resource Pack has now added the BETA_SIZE and BETA_EFFECT worksheet functions. These functions are useful for Bayesian binomial hypothesis testing, as well as for Bayesian Mann-Whitney and Signed Ranks tests.
See Bayesian Beta Test Effect and Sample Sizes for more details.
New Grid Functions
The following new functions have been added: GRID_DIST, GRID_INV, GridDesc, and GridSpline.
See Bayesian Analysis using Grids for more details.
Bayesian Contrasts
The CONTRAST, CONTRAST1, and CONTRAST2 worksheet functions have been added to set up the appropriate Bayesian Signed Ranks and Mann-Whitney tests based on contrasts. These functions can also be used with the Bayesian t Tests.
See Bayesian Contrasts for more details.
New Distributions
The new release provides support for the Beta Prime distribution via the following worksheet functions: BETA2_DIST, BETA2_INV, and BETA2_HDI.
See Beta Prime Distribution and High Density Interval (HDI) for more details.
The new release also provides support for the Wakeby distribution via the following worksheet functions: WAKEBY_DIST and WAKEBY_INV.
See Wakeby Distribution for more details.
Reformatting Function
The following new worksheet function has been added:
RAW2FREQ(R1): takes a column array R1 with labels and outputs an equivalent two-column frequency table consisting of a column of unique labels and a column of corresponding frequencies. This the inverse of the existing FREQ2RAW worksheet function.
Bug Fixes and Minor Enhancements
- Fixes the Chi-square Test for Independence data analysis tool for 2 × 2 contingency tables by adding an extra column before the adjusted residuals are displayed.
- Changes how the PoissonCoeff worksheet function is implemented by replacing LN(FACT(x)) by GAMMALN(x+1). This enables larger data values to be used.
- Fixes a bug that allowed the p-value for the TRINOM_TEST function to exceed 1.
- Minor tweak to the BETA_HDI function to avoid an error in an extreme case.
Can you implement QR factoring with pivoting?
Hello Antony,
The current implementation of QR Factoring is explained at
https://real-statistics.com/linear-algebra-matrix-topics/qr-factorization/
Are you looking for a Gaussian elimination approach?
Charles
qr with pivoteo:
https://www-netlib-org.translate.goog/lapack/lug/node42.html?_x_tr_sl=en&_x_tr_tl=es&_x_tr_hl=es&_x_tr_pto=tc
Thanks for sending this to me, Antony.
I will look into it.
Charles