PowerTOST - PowerTOSTv1.5-4

Bug fixes

• Incomplete HTML-entities in 3 man pages corrected (request of Kurt Hornik).
• Fix in power.TOST() w.r.t vectorization of CV or theta0.

Minor changes

• Example with vectorized sampleN.TOST() added to vignette ABE; vignette PA adapted to pa.NTID().
• URLs in README and man pages updated.
• Coefficients with more decimals (15) for the 10-point Gauss quadrature in function tfn(). Thanks to PharmCat for contributing them.
• Clarification of the calculations with gmodel = 1 in the man page section Details of function power.TOST.sds().

Major changes

• Functions dealing with the FDA method for NTID have now aliases without FDA in their names since the evaluation methods requested by the FDA are also required by China CDE. The aliases are power.NTID(), sampleN.NTID(), and pa.NTID(). The former functions power.NTIDFDA(), sampleN.NTIDFDA(), and pa.NTIDFDA() are deprecated and will be removed in the next release.

- R
Published by Detlew over 4 years ago

PowerTOST - PowerTOSTv1.5-3

On CRAN 2021-01-18.

Major changes

• scABEL.ad() and sampleN.scABEL.ad() adapted to deal with regulator = "GCC". Man pages, README, and RSABE-vignette updated accordingly.
• Regulator "GCC" introduced (GCC = Co-operation Council for the Arab States of the Gulf). The GCC evaluation framework for HVD / HVDP is/can be treated as a special case of ABEL, i.e., use the regulatory settings with power.scABEL() or sampleN.scABEL().

- R
Published by Detlew over 5 years ago

PowerTOST - PowerTOST v1.5-2

On CRAN 2020-10-27.

Bug fixes

• stringsAsFactors = FALSE in example of main vignette for R v<4.0.0. stringsAsFactors = TRUE (default) for a data.frame gave an error on Mac OSX oldrelease with R 3.6.3 (outdated version)

- R
Published by Detlew almost 6 years ago

PowerTOST - PowerTOST V1.5-1

On CRAN 2020-10-22

Bug fixes

• Check of arg theta0 within range theta1 ... theta2 fixed.
• Fix of the default settings of theta1, theta2 if missing in various functions.
• Added emmeans to Suggests. Otherwise NOTE on r-devel-linux-x86_64-fedora-clang. THX to Gábor Csárdi and Duncan Murdoch on r-package-devel. Will be required in R4.1.0 released next year.

Minor changes

• Added example for statistical assurance to the ABE-Vignette.
• More checks of CV and theta0 vectorized input to power.TOST(). Only one argument may be a vector.
• Unified man pages of sampleN.*: Always estimation instead of calculation. References added for Fieller’s CI.
• More examples in README.
• Changed http(s) locations of References according to R CMD check.
• Cosmetics in Vignettes. Added examples for logscale = FALSE to the ABE-Vignette.
• Changed http(s) locations of References according to R CMD check.
• Cosmetics in Vignettes. Added examples for logscale = FALSE to the ABE-Vignette.

- R
Published by Detlew almost 6 years ago

PowerTOST - PowerTOST v1.5-0

PowerTOST 1.5-0

(Maintenance release dedicated to 70 birthday of Detluuu)

On CRAN 2020-08-09.

Bug fixes

• Bug fix in scABEL.ad w.r.t. coercion
• Fix of the link to package emmeans in man pages of expected power.
• Fix in Example 1 of ABE.Rmd (not a good idea specify a variable with the same name as a function).

Major changes

• Pre-compiled RSABE vignette.

Minor changes

• Highlight clarification about total sample size in vignettes.
• Removed links to man-pages in vignettes (they work in the library but not in the public ones on CRAN).
• Moved tufte from Imports to Suggests (Duncan Murdoch).
• Harmonize default value of theta1 in pvalue.TOST in case of logscale = FALSE
• Clarification of argument CV (and theta0, theta1, theta2) in case of logscale = FALSE.
• Clarify in man-pages that all functions return the total sample size (and not subjects/sequence in crossovers and subjects/group in parallel designs -- like in some other software packages). Suggested by Amandine Schmutz.

- R
Published by Detlew almost 6 years ago

PowerTOST -

PowerTOST 1.4-9

Submitted to CRAN 2019-12-16. (xmas gift)

Bug fixes

• Fix in power.dp() w.r.t. setting argument CVb if missing in case of design="IBD".
• Fix in scABEL.ad(): reg$name instead of regulator.
• CV in 4th panel of pwrA_S3methods.R to the same precison like in the others.
• Fix in power.TOST.sds() for gmodel=1, case of gmodel=3 with data of the largest group (group by treatment interaction significant at p=0.1)

Major changes

• (Pre-compiled) vignettes.

Minor changes

• Imports package tufte for nice quotes in Rmarkdown.
• Slightly enhanced man pages of power.dp() and sampleN.dp() w.r.t. the value of CVb in case of design="IBD".
• Cosmetics in output of sampleN.noninf based on margin.
• Reworked minimum sample sizes in pa.scABE.R() according to guidances. Generally 12 (as before) but 24 for the FDA. Also 24 for the EMA if 2x2x3 design (Q&A document). Changed N to n in the S3-methods in conformity with other functions.

- R
Published by Detlew over 6 years ago

PowerTOST - PowerTOST v1.4-8

Bug fixes

• scABEL.ad(), sampleN.scABEL.ad(): CVwT was not given in output if CVwas a vector.
• In scABEL.ad.R regulatorwas NULL. Corrected to reg$name.
• Smaller font in 4^th screen of pwrA_S3methods.R of pa.NTID() (more lines required). Plain font instead of bold in main.
• Broken FDA URL in many man pages corrected.
• In expsampleN.noninf() wrt operator && with vector arguments (new check in R 3.6.0).
• CI.RatioF() fixed. Thanks to Michael (mittyri).

Major changes

• New function sampleN.RSABE2L.sdsims() for sample size estimation via subject simulations for the ‘exact’ method of Tóthfalusi & Endrényi “Algorithms for evaluating reference scaled average bioequivalence: power, bias, and consumer risk”.
• New function sampleN.scABEL.sdsims() for sample size estimation for ABEL via subject simulations. Useful in case of assumed heteroscedasticity in the partial replicate design (TRT|RTR|RRT).
• NEWS.md instead of NEWS.
• README.md (knitted from README.Rmd).
• Function power.TOST.sds() to simulate subject data & evaluate via models with group effect implemented.
• Unified Code base for the scaled ABE functions.

Minor changes

• LaTeX-builder on CRAN laments about UTF-8 charcters in man-pages. No problem rendering the PDF-manual locally! Replaced all UTF-8 characters by \enc{foo}{bar}.
• In power.scABEL(): If nsims not given, defaults to 1e5 (like before). If theta0 equals one of the expanded limits, deafault s to 1e6. Man-page updated.
• Output of sampleN.TOST(): Same name of replicate designs like in the scaled functions.
• In power.scABEL() name of scaled component "p(BE-ABEL)" instead of "p(BE-wABEL)".
• Updated test_ABEL.R in inst/tests to support subject simulations.
• power.scABEL(): More informative warning about heteroscedasticity in the partial replicate design (use of power.scABEL.sdsims() suggested).
• Add/subtract .Machine$double.eps if rho is -1 or +1 given in power_type1_2TOST.R (similar to sampleN_2TOST_sim.R). Removed warning in the latter function. Less confusing for users and the example in the man-page looks nicer.
• Man pages reworked.

- R
Published by Detlew almost 7 years ago

PowerTOST - PowerTOST v1.4-7

• Bug corrected in functions using expected power
• Function type1error.2TOST() no longer available since it suffers from insufficient precision to obtain the type 1 error (TIE) via simulations. Due to the intersection-union principle the TIE is always upper bounded to alpha by theory.
• Function power.2TOST() now based on simulations to obtain the power of 2 TOSTs (statistical flaw in 4-dimensional t-distribution approach).
• sampleN.2TOST and man page adapted according to this change.
• regulator="FDA" implemented in scABEL.ad().
• New function power.RSABE2L.sds() which implements the 'exact' based method for RSABE (ncTOST) of the two Laszlos. Documentation included.

- R
Published by Detlew over 8 years ago

PowerTOST - PowerTOST v1.4-6

• Bug fixed in functions relying in simulations if nsims>1e7.
• Functions CVwRfromU() / U2CVwR() calculate CVwR from the upper expanded limit of an ABEL study according to EMA's or Health Canada's rules.
• Power and sample size for TOST: Argument alpha restricted to scalar. Internal functions now allow length = 2 (different alpha's for the two null hypotheses).
• Man pages for non-inferiority again updated.
• Deprecated argument dfCV in expected power functions now completely removed.
• Data lazy loading (allows access by the name)

- R
Published by Detlew almost 9 years ago

PowerTOST - PowerTOST v1.4-5

• Man pages for non-inferiority functions updated to include a description of the underlying hypotheses
• Remaining man pages updated where term 'Null (true) ratio' was mentioned instead of 'True ratio'
• Two new test scrips in /test subdirectory added: testABEL.R and testRSABE which recalculate the sample size tables given in Thotfalusi & Endrenyi "Sample Sizes for Designing Bioequivalence Studies for Highly Variable Drugs". Contributed by Helmut.
• power.scABEL.sdsims() now has an argument design_dta to specify the design via a data.frame. May be useful for considering missing data. Attention! This feature is experimental because the data.frame is not checked at moment.
• Bug in power.scABEL.sdsims() fixed which gave power=NA if alpha=0.
• Internal change of coding in design helpers (repeated creation of data.frame with design characteristics avoided).
• Typo corrected in ExpectedPowerfor_TOST.pdf.
• Updated functions scABEL.ad() and sampleN.scABEL.ad() to allow subject data simulations via power.scABEL.sdsims() if regulator = "EMA". Removed regulator = "ANVISA". Changed the order of sequences to be consistent with the other functions of PowerTOST.
• Renamed the variable 'adj. alpha' in sampleN.scABEL.ad() to 'alpha.adj' for consistency with scABEL.ad(). Bug corrected if pre-specified alpha gives TIE <0.05.
• Removed regulator = "ANVISA" from pa.scABE().
• Small bug in the S3 method plot for class 'pwrA' corrected (text in the 4th box was truncated on top if saved as a PDF). Replaced text() by TeachingDemos::shadowtext() to enhance legibility (interfered with underlying grid).

- R
Published by Detlew about 9 years ago

PowerTOST - PowerTOST v1.4-4

• Administrative change for expected power: cubature::adaptIntegrate replaced by cubature::hcubature to reflect change of function name within package cubature.
• Added function power.scABEL.sdsims() to calculate power for the BE decision via scaled (widened) BE acceptance limits (EMA recommended) based on subject data simulations.
• Low CV (cosmetic) correction in power.scABEL() introduced.
• Removed default CV = 0.3 from scABEL.ad() and sampleN.scABEL.ad(). Stops exceution if CV not specified.
  
• DOI for references added in many man pages. THX to Helmut.
• Bens description of expected power added in /doc subdirectory
• BEpowersamplesizeexcerpt.pdf updated to reflect the changes in computation of OwensQ
• Use of removed functions power.scABEL2() and sampleN.scABEL2() in pa.scABE() corrected.

- R
Published by Detlew over 9 years ago

PowerTOST - PowerTOST v1.4-3

• Little bug in power.TOST() removed which cause power <0 for large degrees of freedom
• Functions for expected power of the TOST procedure and sample size based on expected power reworked to deal also with uncertainty of theta0 or dealing with both uncertainties of CV and theta0. Contributed mainly by Benjamin Lang.
• Functions for expected power of non-inferiority testing and sample size based on that expected power also reworked to deal also with uncertainty of theta0 or dealing with both uncertainties of CV and theta0. Contributed mainly by Benjamin Lang.
• Deprecated functions power.scABEL2() and sampleN.scABEL2() now removed. regulator = "ANVISA" no longer allowed in the scaled ABEL functions.
• OwensQ() simpler/faster implemented. Now based solely on numerical integration in combination with non-central t.
• Owen's T-function, used in OwensQOwen() now based on algorithm AS76 and remarks to that algorithm to avoid numerical errors of the implementation via integrate().
• Data.frame ct9.6.6 in data("data2x2x3") added which was missing since a long time ago.
• Little inconsistency resolved (by Helmut) in output of power analysis functions w.r.t. ratio or percent. Thanks to user myttiri of BEBA forum for pointing out this inconsistency.

- R
Published by Detlew over 9 years ago

PowerTOST - PowerTOST v1.4-2

• ImplementationscaledABEsims.pdf in \doc subdirectory updated to reflect the changes in code of the scaled ABE functions.
• The S3 method plot for class 'pwrA' now has an argument ratiolabel for labeling the axis concerning theta0. Wish of B. Lang.
• Various enhancements in man pages.
• Power and sample size for FDA RSABE now take into account a CVcap if defined as finite.
• Deprecated argument point in functions CI2CV()/CVfromCI() now removed
• Misleading term 'Null (true) ratio' in output of sample size functions changed to 'True ratio'.
• Minor bug in sampleN.2TOST() fixed.

- R
Published by Detlew about 10 years ago

PowerTOST - PowerTOST v1.4-1

• Objects of class 'regSet' now have an additional component 'est_method' which controls the simualtions via key statistics of the evaluation using EMA's ANOVA or FDA's recommended ISC.
  
• power.scABEL()/power.scABEL2() as well as sampleN.scABEL()/sampleN.scABEL2() are now unified. The regulator component 'est_method' is used for switching between sims based on EMA's ANOVA evaluation or ISC evaluation, respectively.
• power.scABEL2()/sampleN.scABEL2() are therefore deprecated and will be removed in future versions. A corresponding warning is thrown.
• URL of PowerTOST on GitHub added, URL for bug reports added.
  

- R
Published by Detlew about 10 years ago