cmstatr/ 0000755 0001762 0000144 00000000000 14477012635 011740 5 ustar ligges users cmstatr/NAMESPACE 0000644 0001762 0000144 00000005237 14125331440 013152 0 ustar ligges users # Generated by roxygen2: do not edit by hand
S3method(augment,mnr)
S3method(glance,adk)
S3method(glance,anderson_darling)
S3method(glance,basis)
S3method(glance,equiv_change_mean)
S3method(glance,equiv_mean_extremum)
S3method(glance,levene)
S3method(glance,mnr)
S3method(print,adk)
S3method(print,anderson_darling)
S3method(print,basis)
S3method(print,equiv_change_mean)
S3method(print,equiv_mean_extremum)
S3method(print,levene)
S3method(print,mnr)
export(ad_ksample)
export(anderson_darling_lognormal)
export(anderson_darling_normal)
export(anderson_darling_weibull)
export(augment)
export(basis_anova)
export(basis_hk_ext)
export(basis_lognormal)
export(basis_nonpara_large_sample)
export(basis_normal)
export(basis_pooled_cv)
export(basis_pooled_sd)
export(basis_weibull)
export(calc_cv_star)
export(cv)
export(equiv_change_mean)
export(equiv_mean_extremum)
export(glance)
export(hk_ext_z)
export(hk_ext_z_j_opt)
export(k_equiv)
export(k_factor_normal)
export(levene_test)
export(maximum_normed_residual)
export(nested_data_plot)
export(nonpara_binomial_rank)
export(normalize_group_mean)
export(normalize_ply_thickness)
export(stat_esf)
export(stat_normal_surv_func)
export(tidy)
export(transform_mod_cv)
export(transform_mod_cv_ad)
importFrom(MASS,fitdistr)
importFrom(dplyr,mutate)
importFrom(dplyr,select)
importFrom(dplyr,ungroup)
importFrom(generics,augment)
importFrom(generics,glance)
importFrom(generics,tidy)
importFrom(ggplot2,Stat)
importFrom(ggplot2,aes)
importFrom(ggplot2,element_blank)
importFrom(ggplot2,element_line)
importFrom(ggplot2,expansion)
importFrom(ggplot2,geom_hline)
importFrom(ggplot2,ggplot)
importFrom(ggplot2,ggproto)
importFrom(ggplot2,labs)
importFrom(ggplot2,layer)
importFrom(ggplot2,scale_y_continuous)
importFrom(ggplot2,theme)
importFrom(ggplot2,xlab)
importFrom(ggplot2,ylab)
importFrom(kSamples,ad.test)
importFrom(purrr,map_dfr)
importFrom(rlang,.data)
importFrom(rlang,abort)
importFrom(rlang,call2)
importFrom(rlang,call_args)
importFrom(rlang,call_args_names)
importFrom(rlang,call_name)
importFrom(rlang,enquo)
importFrom(rlang,enquos)
importFrom(rlang,ensym)
importFrom(rlang,eval_tidy)
importFrom(rlang,exec)
importFrom(rlang,fn_fmls_names)
importFrom(rlang,inform)
importFrom(rlang,list2)
importFrom(rlang,quo_get_expr)
importFrom(rlang,quo_text)
importFrom(rlang,warn)
importFrom(stats,dbeta)
importFrom(stats,dnorm)
importFrom(stats,integrate)
importFrom(stats,median)
importFrom(stats,pbeta)
importFrom(stats,pchisq)
importFrom(stats,pf)
importFrom(stats,pnorm)
importFrom(stats,pweibull)
importFrom(stats,qnorm)
importFrom(stats,qt)
importFrom(stats,qweibull)
importFrom(stats,sd)
importFrom(stats,uniroot)
importFrom(stats,var.test)
importFrom(tibble,tibble)
cmstatr/README.md 0000644 0001762 0000144 00000013063 14476101705 013216 0 ustar ligges users
# cmstatr
[](https://github.com/cmstatr/cmstatr/actions/workflows/R-CMD-check.yaml)
[](https://app.codecov.io/gh/cmstatr/cmstatr?branch=master)
[](https://doi.org/10.21105/joss.02265)
[](https://cran.r-project.org/package=cmstatr)
[](https://cran.r-project.org/package=cmstatr)
# What It Does
The `cmstatr` package provides functions for performing statistical
analysis of composite material data. The statistical methods implemented
are those described in [CMH-17-1G](https://www.cmh17.org/). This package
focuses on calculating basis values (lower tolerance bounds) for
material strength properties, as well as performing the associated
diagnostic tests. Functions are also provided for testing for
equivalency between alternate samples and the “qualification” or
“baseline” samples.
Additional details about the package are available in the paper by
Kloppenborg (2020, ).
There is a companion package `cmstatrExt` which provides statistical
methods that are not included in CMH-17, but which may be of use to
practitioners. For more information, please see the [`cmstatrExt`
Website](https://cmstatrext.cmstatr.net).
# Installation
To install `cmstatr` from CRAN, simply run:
``` r
install.packages("cmstatr")
```
If you want the latest development version, you can install it from
`github` using `devtools`. This will also install the dependencies
required to build the vignettes. Optionally, change the value of the
argument `ref` to install `cmstatr` from a different branch of the
repository.
``` r
install.packages(c("devtools", "rmarkdown", "dplyr", "tidyr"))
devtools::install_github("cmstatr/cmstatr", build_vignettes = TRUE,
ref = "master",
build_opts = c("--no-resave-data", "--no-manual"))
```
# Usage
To compute a B-Basis value from an example data set packaged with
`cmstatr` you can do the following:
``` r
library(dplyr)
library(cmstatr)
carbon.fabric.2 %>%
filter(test == "FC") %>%
filter(condition == "RTD") %>%
basis_normal(strength, batch)
#>
#> Call:
#> basis_normal(data = ., x = strength, batch = batch)
#>
#> Distribution: Normal ( n = 18 )
#> B-Basis: ( p = 0.9 , conf = 0.95 )
#> 76.88082
```
For more examples of usage of the `cmstatr` package, see the tutorial
vignette, which can be [viewed
online](https://www.cmstatr.net/articles/cmstatr_Tutorial.html), or can
be loaded as follows, once the package is installed:
``` r
vignette("cmstatr_Tutorial")
```
There is also a vignette showing some examples of the types of graphs
that are typically produced when analyzing composite materials. You can
view this [vignette
online](https://www.cmstatr.net/articles/cmstatr_Graphing.html), or you
can load this vignette with:
``` r
vignette("cmstatr_Graphing")
```
# Philosophical Notes
This package expects
[`tidy data`](https://doi.org/10.18637/jss.v059.i10). That is,
individual observations should be in rows and variables in columns.
Where possible, this package uses general solutions. Look-up tables are
avoided wherever possible.
# Issues
If you’ve found a bug, please open an issue in this repository and
describe the bug. Please include a [reproducible
example](https://reprex.tidyverse.org/) of the bug. If you’re able to
fix the bug, you can do so by submitting a pull request.
If your bug is related to a particular data set, sharing that data set
will help to fix the bug. If you cannot share the data set, please strip
any identifying information and optionally scale the data by an
unspecified factor so that the bug can be reproduced and diagnosed.
# Contributing
Contributions to `cmstatr` are always welcomed. For small changes
(fixing typos or improving the documentation), go ahead and submit a
pull request. For more significant changes, such as new features, please
discuss the proposed change in an issue first.
## Contribution Guidelines
- Please create a git branch for each pull request (PR)
- Before submitting a pull request, please make sure that `R CMD check`
passes with no errors, warnings or notes
- New and modified code should follow the style guide enforced by the
[`lintr`](https://cran.r-project.org/package=lintr) package
- Document all exported functions using
[`roxygen2`](https://cran.r-project.org/package=roxygen2)
- Write tests using
[`testthat`](https://cran.r-project.org/package=testthat). If your
contribution fixes a bug, then the test(s) that you add should fail
before your bug-fix patch is applied and should pass after the code is
patched.
- For changes that affect the user, add a bullet at the top of `NEWS.md`
below the current development version
## Development
Testing is performed using `testthat`. Edition 3 of that package is used
and parallel processing enabled. If you wish to use more than two CPUs,
set the environment variable `TESTTHAT_CPUS` to the number of CPUs that
you want to use. One way of doing this is to create the file `.Rprofile`
with the following contents. This file is ignored both by `git` and also
in `.Rbuildingore`.
``` r
Sys.setenv(TESTTHAT_CPUS = 8)
```
cmstatr/data/ 0000755 0001762 0000144 00000000000 14065516021 012640 5 ustar ligges users cmstatr/data/carbon.fabric.rda 0000644 0001762 0000144 00000005140 13507422437 016030 0 ustar ligges users BZh91AY&SYR TA{n \SM)z4f AC'6h?Td4hѵbib4a4=dj~Dڞ2I䞚 @ё@ai=M`OPdؚd4j Ia==FOSM
2=OH2=OM!2zd4zG24JhOSzHyO$i
~=@z'f2zQPff嚽E4 Rd^,\q$dG5 / B@2sͼ抿*LFVN,Y*DpL?Y\z $>x<;K&$jZ;|Y<IdH@
ejG KZÀLƞ2oByX2DT;#Ke|>ߞ gnXN^ӆ}UkǶ \VğXqк$rN15 Y_$
py>3'zQJ[=͍/ Ȑ:- `H4̒.FmȨv).JCL{
̓
>-v*,p)^ª!Ģ3NՑnh2 }hc
l{*.n3H*{b_ Zu=JxZtU5`7
;y!إ@ %,mY>:ힻΒY3M%lp@*.VPuLgOuD$M ?$Sj2},Ƥ~{Mu_w6N2.3zjz$g,tFJU &D?&xzgN魑uO`f[{ jb;GGOѬjcau*xWStaOʘo? ɂz]> %^N\:$oȸ3D^KZ18?ng ~،HST"&M|3:Ͳ hRO4g$ܑN$/AT cmstatr/data/carbon.fabric.2.rda 0000644 0001762 0000144 00000004732 14065516021 016167 0 ustar ligges users [ pT^BJL!E
{
tdı"c#YK콛G MLC@BCR
BK:T-A(}huP(swnr%ݙ?A ˕JĿ;s25urؽܬFp}uy 5|Z,egږ'$>jTnJRI2S;^\+,N&Gd*'_K֮Wy+: [N;F\{QeQ:_*⊏
ӕޤI
/.@K'8]w.ޞxOGP.֮n˫n=ޭ˧?Fy>?~i+s8m'km'?4њo 9'yv ο5}dQ[}G>NzkO1>ּ / ~~߬Q?i]S曺vvxF?syަn/#'>Gxwۼm2?pĭv6ٶGdUt_ӡ[;/`l,{ ƾ34O[i+CbzpgN8*~j݉]>v=,zZ9kg'+ vZ(93:֣[F+^zh k
Ϻ5ߋ>+v|>G y 2>{FpY_d G| d/.(Bf! ]d 24k #{%@,q+yṙeQxAdX@F)\)K 6d(Wgd PW2Il#clZd,-kdʏ{*Q3x[4dn>8 Px
&{'9R%>d~Nl wcQxaPYU19d 0.RezD Y _:^0$si)TȽF2('s|03\:[$ƑSH& &̑>"sz MF2IpY |Ȃ]g?
ʛ*m ט\<).' +4eS'"`TV#z
U|Xz ̏=Gy8ݵ&uau?ݗARIXMk}ɦ_K>\
Tt
v
Ca_ưQA
v}8puMB>eW
~eQ#_N!
ӀGOɻ0B7 Q?RyYިۢ
iTT,A~ex̖?geqb>=dCR]bkQl 0ٟ؋0bg)͂>Ig?]wఎO"d{7fT7+]%8T<]g6>V+
Sn} _c?jQ/>ċ$z ~Pg./+=ʟjEgc^Y݈eXo xv g>P~ͬ /Im$s (I_w:IG^kq?#ݫ'jk\{g/
_ 3=g0 $M6V8m3mor7)> | r\uנU?=j.jo|Ȝx!tL4~V\-dx
ݔgl_rvl|kvr=N D ѹtER>{& 5<ߚMz9Z&ˉGq2;/K(JNXHg9h%q=80K!oȶ[ 8ݐPZ|!QL |F"E$ ҪtI^PZ;_3*\eʆF :k#ՍյDl,jԙkkʆ5%RWS]i]X_vu6mFm̚r*ff}eOWڵ,1,-Ɍ
̪ضβ *O;wn, Ί翃ڻQ4 cmstatr/man/ 0000755 0001762 0000144 00000000000 14475364513 012516 5 ustar ligges users cmstatr/man/glance.basis.Rd 0000644 0001762 0000144 00000005347 14021472437 015337 0 ustar ligges users % Generated by roxygen2: do not edit by hand
% Please edit documentation in R/basis.R
\name{glance.basis}
\alias{glance.basis}
\title{Glance at a basis object}
\usage{
\method{glance}{basis}(x, include_diagnostics = FALSE, ...)
}
\arguments{
\item{x}{a basis object}
\item{include_diagnostics}{a logical value indicating whether to include
columns for diagnostic tests. Default FALSE.}
\item{...}{Additional arguments. Not used. Included only to match generic
signature.}
}
\value{
A \code{\link[tibble:tibble]{tibble::tibble()}} with the following
columns:
\itemize{
\item \code{p} the the content of the tolerance bound. Normally 0.90 or 0.99
\item \code{conf} the confidence level. Normally 0.95
\item \code{distribution} a string representing the distribution assumed
when calculating the basis value
\item \code{modcv} a logical value indicating whether the modified
CV approach was used. Only applicable to pooling methods.
\item \code{n} the sample size
\item \code{r} the number of groups used in the calculation. This will
be \code{NA} for single-point basis values
\item \code{basis} the basis value
}
}
\description{
Glance accepts an object of type basis and returns a
\code{\link[tibble:tibble]{tibble::tibble()}} with
one row of summaries for each basis value.
Glance does not do any calculations: it just gathers the results in a
tibble.
}
\details{
For the pooled basis methods (\code{basis_pooled_cv} and
\code{basis_pooled_sd}), the \code{\link[tibble:tibble]{tibble::tibble()}}
returned by \code{glance} will have one row for each group included in
the pooling. For all other basis methods, the resulting \code{tibble}
will have a single row.
If \code{include_diagnostics=TRUE}, there will be additional columns
corresponding with the diagnostic tests performed. These column(s) will
be of type character and will contain a "P" if the diagnostic test
passed, a "F" if the diagnostic test failed, an "O" if the diagnostic
test was overridden or \code{NA} if the test was not run (typically
because an optional argument was not passed to the function that
computed the basis value).
}
\examples{
set.seed(10)
x <- rnorm(20, 100, 5)
b <- basis_normal(x = x)
glance(b)
## # A tibble: 1 x 7
## p conf distribution modcv n r basis
##
## 1 0.9 0.95 Normal FALSE 20 NA 92.0
glance(b, include_diagnostics = TRUE)
## # A tibble: 1 x 11
## p conf distribution modcv n r basis outliers_within…
##
## 1 0.9 0.95 Normal FALSE 20 NA 92.0 NA
## # … with 3 more variables: between_batch_variability ,
## # outliers , anderson_darling_normal
}
\seealso{
\code{\link[=basis]{basis()}}
}
cmstatr/man/maximum_normed_residual.Rd 0000644 0001762 0000144 00000006041 14015477557 017722 0 ustar ligges users % Generated by roxygen2: do not edit by hand
% Please edit documentation in R/mnr.R
\name{maximum_normed_residual}
\alias{maximum_normed_residual}
\title{Detect outliers using the maximum normed residual method}
\usage{
maximum_normed_residual(data = NULL, x, alpha = 0.05)
}
\arguments{
\item{data}{a data.frame}
\item{x}{the variable in the data.frame for which to find the MNR
or a vector if \code{data=NULL}}
\item{alpha}{the significance level for the test. Defaults to 0.05}
}
\value{
an object of class \code{mnr}
This object has the following fields:
\itemize{
\item \code{call} the expression used to call this function
\item \code{data} the original data used to compute the MNR
\item \code{alpha} the value of alpha given by the user
\item \code{mnr} the computed MNR test statistic
\item \code{crit} the critical value given the sample size and the
significance level
\item \code{outliers} a data.frame containing the \code{index} and
\code{value} of each of the identified outliers
\item \code{n_outliers} the number of outliers found
}
}
\description{
This function detects outliers using the maximum normed residual
method described in CMH-17-1G. This method identifies a value
as an outlier if the absolute difference between the value and
the sample mean divided by the sample standard deviation
exceeds a critical value.
}
\details{
\code{data} is an optional argument. If \code{data} is given, it
should be a
\code{data.frame} (or similar object). When \code{data} is specified, the
value of \code{x} is expected to be a variable within \code{data}. If
\code{data} is not specified, \code{x} must be a vector.
The maximum normed residual test is a test for outliers. The test statistic
is given in CMH-17-1G. Outliers are identified in the returned object.
The maximum normed residual test statistic is defined as:
\deqn{MNR = max \frac{\left| x_i - \bar{x} \right|}{s} }{
MNR = max | x_i- x_bar | / s }
When the value of the MNR test statistic exceeds the critical value
defined in Section 8.3.3.1 of CMH-17-1G, the corresponding value
is identified as an outlier. It is then removed from the sample, and
the test statistic is computed again and compared with the critical
value corresponding with the new sample. This process is repeated until
no values are identified as outliers.
}
\examples{
library(dplyr)
carbon.fabric.2 \%>\%
filter(test=="FC" & condition=="ETW2" & batch=="A") \%>\%
maximum_normed_residual(strength)
## Call:
## maximum_normed_residual(data = ., x = strength)
##
## MNR = 1.958797 ( critical value = 1.887145 )
##
## Outliers ( alpha = 0.05 ):
## Index Value
## 6 44.26
carbon.fabric.2 \%>\%
filter(test=="FC" & condition=="ETW2" & batch=="B") \%>\%
maximum_normed_residual(strength)
## Call:
## maximum_normed_residual(data = ., x = strength)
##
## MNR = 1.469517 ( critical value = 1.887145 )
##
## No outliers detected ( alpha = 0.05 )
}
\references{
“Composite Materials Handbook, Volume 1. Polymer Matrix Composites
Guideline for Characterization of Structural Materials,” SAE International,
CMH-17-1G, Mar. 2012.
}
cmstatr/man/k_equiv.Rd 0000644 0001762 0000144 00000006511 14015477557 014456 0 ustar ligges users % Generated by roxygen2: do not edit by hand
% Please edit documentation in R/equiv.R
\name{k_equiv}
\alias{k_equiv}
\title{k-factors for determining acceptance based on sample mean and an extremum}
\usage{
k_equiv(alpha, n)
}
\arguments{
\item{alpha}{the acceptable probability of a type I error}
\item{n}{the number of observations in the sample to test}
}
\value{
a vector with elements c(k1, k2). k1 is for testing the sample
extremum. k2 is for testing the sample mean
}
\description{
k-factors for determining acceptance based on sample mean and an extremum
}
\details{
The k-factors returned by this function are used for determining
whether to accept a new dataset.
This function is used as part of the procedure for
determining acceptance limits for a sample mean and sample minimum.
These acceptance limits are often used to set acceptance limits for
material strength for each lot of material, or each new manufacturing
site. When a sample meets the criteria that its mean and its minimum are
both greater than these limits, then one may accept the lot of material
or the new manufacturing site.
This procedure is used to ensure that the strength of material processed
at a second site, or made with a new batch of material are not degraded
relative to the data originally used to determine basis values for the
material. For more information about the use of this procedure, see
CMH-17-1G or PS-ACE 100-2002-006.
According to Vangel (2002), the use of mean and extremum for this purpose
is more powerful than the use of mean and standard deviation.
The results of this function match those published by Vangel within
0.05\\% for \eqn{n > 2} and \eqn{\alpha \le 0.25}. Those results published
by Vangel are identical to those published in CMH-17-1G.
This function uses numerical integration and numerical optimization to
find values of the factors \eqn{k_1} and \eqn{k_2} based on Vangel's
saddle point approximation.
The value \eqn{n} refers to the number of observations in the sample
being compared with the original population (the qualification sample is
usually assumed to be equal to the population statistics).
The value of \eqn{alpha} is the acceptable probability of a type I error.
Normally, this is set to 0.05 for material or process equivalency and 0.01
when setting lot acceptance limits. Though, in principle, this parameter
can be set to any number between 0 and 1. This function, however, has only
been validated in the range of \eqn{1e-5 \le alpha \le 0.5}.
}
\examples{
qual_mean <- 100
qual_sd <- 3.5
k <- k_equiv(0.01, 5)
print("Minimum Individual Acceptance Limit:")
print(qual_mean - qual_sd * k[1])
print("Minimum Average Acceptance Limit:")
print(qual_mean - qual_sd * k[2])
## [1] "Minimum Individual Acceptance Limit:"
## [1] 89.24981
## [1] "Minimum Average Acceptance Limit:"
## [1] 96.00123
}
\references{
M. G. Vangel. Lot Acceptance and Compliance Testing Using the Sample Mean
and an Extremum, Technometrics, vol. 44, no. 3. pp. 242–249. 2002.
“Composite Materials Handbook, Volume 1. Polymer Matrix Composites
Guideline for Characterization of Structural Materials,” SAE International,
CMH-17-1G, Mar. 2012.
Federal Aviation Administration, “Material Qualification and Equivalency
for Polymer Matrix Composite Material Systems,” PS-ACE 100-2002-006,
Sep. 2003.
}
\seealso{
\code{\link[=equiv_mean_extremum]{equiv_mean_extremum()}}
}
cmstatr/man/ad_ksample.Rd 0000644 0001762 0000144 00000006243 14015477557 015115 0 ustar ligges users % Generated by roxygen2: do not edit by hand
% Please edit documentation in R/adk.R
\name{ad_ksample}
\alias{ad_ksample}
\title{Anderson--Darling K-Sample Test}
\usage{
ad_ksample(data = NULL, x, groups, alpha = 0.025)
}
\arguments{
\item{data}{a data.frame}
\item{x}{the variable in the data.frame on which to perform the
Anderson--Darling k-Sample test (usually strength)}
\item{groups}{a variable in the data.frame that defines the groups}
\item{alpha}{the significance level (default 0.025)}
}
\value{
Returns an object of class \code{adk}. This object has the following fields:
\itemize{
\item \code{call} the expression used to call this function
\item \code{data} the original data used to compute the ADK
\item \code{groups} a vector of the groups used in the computation
\item \code{alpha} the value of alpha specified
\item \code{n} the total number of observations
\item \code{k} the number of groups
\item \code{sigma} the computed standard deviation of the test statistic
\item \code{ad} the value of the Anderson--Darling k-Sample test statistic
\item \code{p} the computed p-value
\item \code{reject_same_dist} a boolean value indicating whether the null
hypothesis that all samples come from the same distribution is rejected
\item \code{raw} the original results returned from
\link[kSamples:ad.test]{ad.test}
}
}
\description{
This function performs an Anderson--Darling k-sample test. This is used to
determine if several samples (groups) share a common (unspecified)
distribution.
}
\details{
This function is a wrapper for the \link[kSamples:ad.test]{ad.test} function from
the package \code{kSamples}. The method "exact" is specified in the call to
\code{ad.test}. Refer to that package's documentation for details.
There is a minor difference in the formulation of the Anderson--Darling
k-Sample test in CMH-17-1G, compared with that in the Scholz and
Stephens (1987). This difference affects the test statistic and the
critical value in the same proportion, and therefore the conclusion of
the test is unaffected. When
comparing the test statistic generated by this function to that generated
by software that uses the CMH-17-1G formulation (such as ASAP, CMH17-STATS,
etc.), the test statistic reported by this function will be greater by
a factor of \eqn{(k - 1)}, with a corresponding change in the critical
value.
For more information about the difference between this function and
the formulation in CMH-17-1G, see the vignette on the subject, which
can be accessed by running \code{vignette("adktest")}
}
\examples{
library(dplyr)
carbon.fabric \%>\%
filter(test == "WT") \%>\%
filter(condition == "RTD") \%>\%
ad_ksample(strength, batch)
##
## Call:
## ad_ksample(data = ., x = strength, groups = batch)
##
## N = 18 k = 3
## ADK = 0.912 p-value = 0.95989
## Conclusion: Samples come from the same distribution ( alpha = 0.025 )
}
\references{
F. W. Scholz and M. Stephens, “K-Sample Anderson--Darling Tests,” Journal
of the American Statistical Association, vol. 82, no. 399. pp. 918–924,
Sep-1987.
“Composite Materials Handbook, Volume 1. Polymer Matrix Composites
Guideline for Characterization of Structural Materials,” SAE International,
CMH-17-1G, Mar. 2012.
}
cmstatr/man/carbon.fabric.Rd 0000644 0001762 0000144 00000001245 14065516021 015464 0 ustar ligges users % Generated by roxygen2: do not edit by hand
% Please edit documentation in R/data.R
\docType{data}
\name{carbon.fabric}
\alias{carbon.fabric}
\alias{carbon.fabric.2}
\title{Sample data for a generic carbon fabric}
\format{
An object of class \code{data.frame} with 216 rows and 5 columns.
An object of class \code{data.frame} with 177 rows and 9 columns.
}
\usage{
carbon.fabric
carbon.fabric.2
}
\description{
Datasets containing sample data that is typical of a generic carbon
fabric prepreg. This data is used in several examples within the
\code{cmstatr} package. This data is fictional and should
only be used for learning how to use this package.
}
\keyword{datasets}
cmstatr/man/basis.Rd 0000644 0001762 0000144 00000044067 14065516021 014105 0 ustar ligges users % Generated by roxygen2: do not edit by hand
% Please edit documentation in R/basis.R
\name{basis}
\alias{basis}
\alias{basis_normal}
\alias{basis_lognormal}
\alias{basis_weibull}
\alias{basis_pooled_cv}
\alias{basis_pooled_sd}
\alias{basis_hk_ext}
\alias{basis_nonpara_large_sample}
\alias{basis_anova}
\title{Calculate basis values}
\usage{
basis_normal(
data = NULL,
x,
batch = NULL,
p = 0.9,
conf = 0.95,
override = c()
)
basis_lognormal(
data = NULL,
x,
batch = NULL,
p = 0.9,
conf = 0.95,
override = c()
)
basis_weibull(
data = NULL,
x,
batch = NULL,
p = 0.9,
conf = 0.95,
override = c()
)
basis_pooled_cv(
data = NULL,
x,
groups,
batch = NULL,
p = 0.9,
conf = 0.95,
modcv = FALSE,
override = c()
)
basis_pooled_sd(
data = NULL,
x,
groups,
batch = NULL,
p = 0.9,
conf = 0.95,
modcv = FALSE,
override = c()
)
basis_hk_ext(
data = NULL,
x,
batch = NULL,
p = 0.9,
conf = 0.95,
method = c("optimum-order", "woodward-frawley"),
override = c()
)
basis_nonpara_large_sample(
data = NULL,
x,
batch = NULL,
p = 0.9,
conf = 0.95,
override = c()
)
basis_anova(data = NULL, x, groups, p = 0.9, conf = 0.95, override = c())
}
\arguments{
\item{data}{a data.frame}
\item{x}{the variable in the data.frame for which to find the basis value}
\item{batch}{the variable in the data.frame that contains the batches.}
\item{p}{the content of the tolerance bound. Should be 0.90 for B-Basis
and 0.99 for A-Basis}
\item{conf}{confidence level Should be 0.95 for both A- and B-Basis}
\item{override}{a list of names of diagnostic tests to override,
if desired. Specifying "all" will override all diagnostic
tests applicable to the current method.}
\item{groups}{the variable in the data.frame representing the groups}
\item{modcv}{a logical value indicating whether the modified CV approach
should be used. Only applicable to pooling methods.}
\item{method}{the method for Hanson--Koopmans nonparametric basis values.
should be "optimum-order" for B-Basis and "woodward-frawley"
for A-Basis.}
}
\value{
an object of class \code{basis}
This object has the following fields:
\itemize{
\item \code{call} the expression used to call this function
\item \code{distribution} the distribution used (normal, etc.)
\item \code{p} the value of \eqn{p} supplied
\item \code{conf} the value of \eqn{conf} supplied
\item \code{modcv} a logical value indicating whether the modified
CV approach was used. Only applicable to pooling methods.
\item \code{data} a copy of the data used in the calculation
\item \code{groups} a copy of the groups variable.
Only used for pooling and ANOVA methods.
\item \code{batch} a copy of the batch data used for diagnostic tests
\item \code{modcv_transformed_data} the data after the modified CV transformation
\item \code{override} a vector of the names of diagnostic tests that
were overridden. \code{NULL} if none were overridden
\item \code{diagnostic_results} a named character vector containing the
results of all the diagnostic tests. See the Details section for
additional information
\item \code{diagnostic_failures} a vector containing any diagnostic tests
that produced failures
\item \code{n} the number of observations
\item \code{r} the number of groups, if a pooling method was used.
Otherwise it is NULL.
\item \code{basis} the basis value computed. This is a number
except when pooling methods are used, in which case it is a data.frame.
}
}
\description{
Calculate the basis value for a given data set. There are various functions
to calculate the basis values for different distributions.
The basis value is the lower one-sided tolerance bound of a certain
proportion of the population. For more information on tolerance bounds,
see Meeker, et. al. (2017).
For B-Basis, set the content of tolerance bound to \eqn{p=0.90} and
the confidence level to \eqn{conf=0.95}; for A-Basis, set \eqn{p=0.99} and
\eqn{conf=0.95}. While other tolerance bound
contents and confidence levels may be computed, they are infrequently
needed in practice.
These functions also perform some automated diagnostic
tests of the data prior to calculating the basis values. These diagnostic
tests can be overridden if needed.
}
\details{
\code{data} is an optional argument. If \code{data} is given, it should
be a
\code{data.frame} (or similar object). When \code{data} is specified, the
value of \code{x} is expected to be a variable within \code{data}. If
\code{data} is not specified, \code{x} must be a vector.
When \code{modcv=TRUE} is set, which is only applicable to the
pooling methods,
the data is first modified according to the modified coefficient
of variation (CV)
rules. This modified data is then used when both calculating the
basis values and
also when performing the diagnostic tests. The modified CV approach
is a way of
adding extra variance to datasets with unexpectedly low variance.
\code{basis_normal} calculate the basis value by subtracting \eqn{k} times
the standard deviation from the mean. \eqn{k} is given by
the function \code{\link[=k_factor_normal]{k_factor_normal()}}. The equations in
Krishnamoorthy and Mathew (2008) are used.
\code{basis_normal} also
performs a diagnostic test for outliers (using
\code{\link[=maximum_normed_residual]{maximum_normed_residual()}})
and a diagnostic test for normality (using
\code{\link[=anderson_darling_normal]{anderson_darling_normal()}}).
If the argument \code{batch} is given, this function also performs
a diagnostic test for outliers within
each batch (using \code{\link[=maximum_normed_residual]{maximum_normed_residual()}})
and a diagnostic test for between batch variability (using
\code{\link[=ad_ksample]{ad_ksample()}}). The argument \code{batch} is only used
for these diagnostic tests.
\code{basis_lognormal} calculates the basis value in the same way
that \code{basis_normal} does, except that the natural logarithm of the
data is taken.
\code{basis_lognormal} function also performs
a diagnostic test for outliers (using
\code{\link[=maximum_normed_residual]{maximum_normed_residual()}})
and a diagnostic test for normality (using
\code{\link[=anderson_darling_lognormal]{anderson_darling_lognormal()}}).
If the argument \code{batch} is given, this function also performs
a diagnostic test for outliers within
each batch (using \code{\link[=maximum_normed_residual]{maximum_normed_residual()}})
and a diagnostic test for between batch variability (using
\code{\link[=ad_ksample]{ad_ksample()}}). The argument \code{batch} is only used
for these diagnostic tests.
\code{basis_weibull} calculates the basis value for data distributed
according to a Weibull distribution. The confidence level for the
content requested is calculated using the conditional method, as
described in Lawless (1982) Section 4.1.2b. This has good agreement
with tables published in CMH-17-1G. Results differ between this function
and STAT17 by approximately 0.5\\%.
\code{basis_weibull} function also performs
a diagnostic test for outliers (using
\code{\link[=maximum_normed_residual]{maximum_normed_residual()}})
and a diagnostic test for normality (using
\code{\link[=anderson_darling_weibull]{anderson_darling_weibull()}}).
If the argument \code{batch} is given, this function also performs
a diagnostic test for outliers within
each batch (using \code{\link[=maximum_normed_residual]{maximum_normed_residual()}})
and a diagnostic test for between batch variability (using
\code{\link[=ad_ksample]{ad_ksample()}}). The argument \code{batch} is only used
for these diagnostic tests.
\code{basis_hk_ext} calculates the basis value using the Extended
Hanson--Koopmans method, as described in CMH-17-1G and Vangel (1994).
For nonparametric distributions, this function should be used for samples
up to n=28 for B-Basis and up to \eqn{n=299} for A-Basis.
This method uses a pair of order statistics to determine the basis value.
CMH-17-1G suggests that for A-Basis, the first and last order statistic
is used: this is called the "woodward-frawley" method in this package,
after the paper in which this approach is described (as referenced
by Vangel (1994)). For B-Basis, another approach is used whereby the
first and \code{j-th} order statistic are used to calculate the basis value.
In this approach, the \code{j-th} order statistic is selected to minimize
the difference between the tolerance limit (assuming that the order
statistics are equal to the expected values from a standard normal
distribution) and the population quantile for a standard normal
distribution. This approach is described in Vangel (1994). This second
method (for use when calculating B-Basis values) is called
"optimum-order" in this package.
The results of \code{basis_hk_ext} have been
verified against example results from the program STAT-17. Agreement is
typically well within 0.2\%.
Note that the implementation of \code{hk_ext_z_j_opt} changed after \code{cmstatr}
version 0.8.0. This function is used internally by \code{basis_hk_ext}
when \code{method = "optimum-order"}. This implementation change may mean
that basis values computed using this method may change slightly
after version 0.8.0. However, both implementations seem to be equally
valid. See the included vignette
for a discussion of the differences between the implementation before
and after version 0.8.0, as well as the factors given in CMH-17-1G.
To access this vignette, run: \code{vignette("hk_ext", package = "cmstatr")}
\code{basis_hk_ext} also performs
a diagnostic test for outliers (using
\code{\link[=maximum_normed_residual]{maximum_normed_residual()}})
and performs a pair of tests that the sample size and method selected
follow the guidance described above.
If the argument \code{batch} is given, this function also performs
a diagnostic test for outliers within
each batch (using \code{\link[=maximum_normed_residual]{maximum_normed_residual()}})
and a diagnostic test for between batch variability (using
\code{\link[=ad_ksample]{ad_ksample()}}). The argument \code{batch} is only used
for these diagnostic tests.
\code{basis_nonpara_large_sample} calculates the basis value
using the large sample method described in CMH-17-1G. This method uses
a sum of binomials to determine the rank of the ordered statistic
corresponding with the desired tolerance limit (basis value). Results
of this function have been verified against results of the STAT-17
program.
\code{basis_nonpara_large_sample} also performs
a diagnostic test for outliers (using
\code{\link[=maximum_normed_residual]{maximum_normed_residual()}})
and performs a test that the sample size is sufficiently large.
If the argument \code{batch} is given, this function also performs
a diagnostic test for outliers within
each batch (using \code{\link[=maximum_normed_residual]{maximum_normed_residual()}})
and a diagnostic test for between batch variability (using
\code{\link[=ad_ksample]{ad_ksample()}}). The argument \code{batch} is only used
for these diagnostic tests.
\code{basis_anova} calculates basis values using the ANOVA method.
\code{x} specifies the data (normally strength) and \code{groups}
indicates the group corresponding to each observation. This method is
described in CMH-17-1G, but when the ratio of between-batch mean
square to the within-batch mean square is less than or equal
to one, the tolerance factor is calculated based on pooling the data
from all groups. This approach is recommended by Vangel (1992)
and by Krishnamoorthy and Mathew (2008), and is also implemented
by the software CMH17-STATS and STAT-17.
This function automatically performs a diagnostic
test for outliers within each group
(using \code{\link[=maximum_normed_residual]{maximum_normed_residual()}}) and a test for between
group variability (using \code{\link[=ad_ksample]{ad_ksample()}}) as well as checking
that the data contains at least 5 groups.
This function has been verified against the results of the STAT-17 program.
\code{basis_pooled_sd} calculates basis values by pooling the data from
several groups together. \code{x} specifies the data (normally strength)
and \code{group} indicates the group corresponding to each observation.
This method is described in CMH-17-1G and matches the pooling method
implemented in ASAP 2008.
\code{basis_pooled_cv} calculates basis values by pooling the data from
several groups together. \code{x} specifies the data (normally strength)
and \code{group} indicates the group corresponding to each observation.
This method is described in CMH-17-1G.
\code{basis_pooled_sd} and \code{basis_pooled_cv} both automatically
perform a number of diagnostic tests. Using
\code{\link[=maximum_normed_residual]{maximum_normed_residual()}}, they check that there are no
outliers within each group and batch (provided that \code{batch} is
specified). They check the between batch variability using
\code{\link[=ad_ksample]{ad_ksample()}}. They check that there are no outliers within
each group (pooling all batches) using
\code{\link[=maximum_normed_residual]{maximum_normed_residual()}}. They check for the normality
of the pooled data using \code{\link[=anderson_darling_normal]{anderson_darling_normal()}}.
\code{basis_pooled_sd} checks for equality of variance of all
data using \code{\link[=levene_test]{levene_test()}} and \code{basis_pooled_cv}
checks for equality of variances of all data after transforming it
using \code{\link[=normalize_group_mean]{normalize_group_mean()}}
using \code{\link[=levene_test]{levene_test()}}.
The object returned by these functions includes the named vector
\code{diagnostic_results}. This contains all of the diagnostic tests
performed. The name of each element of the vector corresponds with the
name of the diagnostic test. The contents of each element will be
"P" if the diagnostic test passed, "F" if the diagnostic test failed,
"O" if the diagnostic test was overridden and \code{NA} if the
diagnostic test was skipped (typically because an optional
argument was not supplied).
The following list summarizes the diagnostic tests automatically
performed by each function.
\itemize{
\item \code{basis_normal}
\itemize{
\item \code{outliers_within_batch}
\item \code{between_batch_variability}
\item \code{outliers}
\item \code{anderson_darling_normal}
}
\item \code{basis_lognormal}
\itemize{
\item \code{outliers_within_batch}
\item \code{between_batch_variability}
\item \code{outliers}
\item \code{anderson_darling_lognormal}
}
\item \code{basis_weibull}
\itemize{
\item \code{outliers_within_batch}
\item \code{between_batch_variability}
\item \code{outliers}
\item \code{anderson_darling_weibull}
}
\item \code{basis_pooled_cv}
\itemize{
\item \code{outliers_within_batch}
\item \code{between_group_variability}
\item \code{outliers_within_group}
\item \code{pooled_data_normal}
\item \code{normalized_variance_equal}
}
\item \code{basis_pooled_sd}
\itemize{
\item \code{outliers_within_batch}
\item \code{between_group_variability}
\item \code{outliers_within_group}
\item \code{pooled_data_normal}
\item \code{pooled_variance_equal}
}
\item \code{basis_hk_ext}
\itemize{
\item \code{outliers_within_batch}
\item \code{between_batch_variability}
\item \code{outliers}
\item \code{sample_size}
}
\item \code{basis_nonpara_large_sample}
\itemize{
\item \code{outliers_within_batch}
\item \code{between_batch_variability}
\item \code{outliers}
\item \code{sample_size}
}
\item \code{basis_anova}
\itemize{
\item \code{outliers_within_group}
\item \code{equality_of_variance}
\item \code{number_of_groups}
}
}
}
\examples{
library(dplyr)
# A single-point basis value can be calculated as follows
# in this example, three failed diagnostic tests are
# overridden.
carbon.fabric \%>\%
filter(test == "FC") \%>\%
filter(condition == "RTD") \%>\%
basis_normal(strength, batch,
override = c("outliers",
"outliers_within_batch",
"anderson_darling_normal"))
## Call:
## basis_normal(data = ., x = strength, batch = batch,
## override = c("outliers", "outliers_within_batch",
## "anderson_darling_normal"))
##
## Distribution: Normal ( n = 18 )
## The following diagnostic tests were overridden:
## `outliers`,
## `outliers_within_batch`,
## `anderson_darling_normal`
## B-Basis: ( p = 0.9 , conf = 0.95 )
## 76.94656
# A set of pooled basis values can also be calculated
# using the pooled standard deviation method, as follows.
# In this example, one failed diagnostic test is overridden.
carbon.fabric \%>\%
filter(test == "WT") \%>\%
basis_pooled_sd(strength, condition, batch,
override = c("outliers_within_batch"))
## Call:
## basis_pooled_sd(data = ., x = strength, groups = condition,
## batch = batch, override = c("outliers_within_batch"))
##
## Distribution: Normal - Pooled Standard Deviation ( n = 54, r = 3 )
## The following diagnostic tests were overridden:
## `outliers_within_batch`
## B-Basis: ( p = 0.9 , conf = 0.95 )
## CTD 127.6914
## ETW 125.0698
## RTD 132.1457
}
\references{
J. F. Lawless, Statistical Models and Methods for Lifetime Data.
New York: John Wiley & Sons, 1982.
“Composite Materials Handbook, Volume 1. Polymer Matrix Composites
Guideline for Characterization of Structural Materials,” SAE International,
CMH-17-1G, Mar. 2012.
M. Vangel, “One-Sided Nonparametric Tolerance Limits,”
Communications in Statistics - Simulation and Computation,
vol. 23, no. 4. pp. 1137–1154, 1994.
K. Krishnamoorthy and T. Mathew, Statistical Tolerance Regions: Theory,
Applications, and Computation. Hoboken: John Wiley & Sons, 2008.
W. Meeker, G. Hahn, and L. Escobar, Statistical Intervals: A Guide
for Practitioners and Researchers, Second Edition.
Hoboken: John Wiley & Sons, 2017.
M. Vangel, “New Methods for One-Sided Tolerance Limits for a One-Way
Balanced Random-Effects ANOVA Model,” Technometrics, vol. 34, no. 2.
Taylor & Francis, pp. 176–185, 1992.
}
\seealso{
\code{\link[=hk_ext_z_j_opt]{hk_ext_z_j_opt()}}
\code{\link[=k_factor_normal]{k_factor_normal()}}
\code{\link[=transform_mod_cv]{transform_mod_cv()}}
\code{\link[=maximum_normed_residual]{maximum_normed_residual()}}
\code{\link[=anderson_darling_normal]{anderson_darling_normal()}}
\code{\link[=anderson_darling_lognormal]{anderson_darling_lognormal()}}
\code{\link[=anderson_darling_weibull]{anderson_darling_weibull()}}
\code{\link[=ad_ksample]{ad_ksample()}}
\code{\link[=normalize_group_mean]{normalize_group_mean()}}
}
cmstatr/man/k_factor_normal.Rd 0000644 0001762 0000144 00000006043 14015477557 016153 0 ustar ligges users % Generated by roxygen2: do not edit by hand
% Please edit documentation in R/basis.R
\name{k_factor_normal}
\alias{k_factor_normal}
\title{Calculate k factor for basis values (\eqn{kB}, \eqn{kA}) with normal
distribution}
\usage{
k_factor_normal(n, p = 0.9, conf = 0.95)
}
\arguments{
\item{n}{the number of observations (i.e. coupons)}
\item{p}{the desired content of the tolerance bound.
Should be 0.90 for B-Basis and 0.99 for A-Basis}
\item{conf}{confidence level. Should be 0.95 for both A- and B-Basis}
}
\value{
the calculated factor
}
\description{
The factors returned by this function are used when calculating basis
values (one-sided confidence bounds) when the data are normally
distributed. The basis value will
be equal to \eqn{\bar{x} - k s}{x_bar - k s},
where \eqn{\bar{x}}{x_bar} is the sample mean,
\eqn{s} is the sample standard deviation and \eqn{k} is the result
of this function.
This function is internally used by \code{\link[=basis_normal]{basis_normal()}} when
computing basis values.
}
\details{
This function calculates the k factors used when determining A- and
B-Basis values for normally distributed data. To get \eqn{kB}, set
the content of the tolerance bound to \code{p = 0.90} and
the confidence level to \code{conf = 0.95}. To get \eqn{kA}, set
\code{p = 0.99} and \code{conf = 0.95}. While other tolerance bound
contents and confidence levels may be computed, they are infrequently
needed in practice.
The k-factor is calculated using equation 2.2.3 of
Krishnamoorthy and Mathew (2008).
This function has been validated against the \eqn{kB} tables in
CMH-17-1G for each value of \eqn{n} from \eqn{n = 2} to \eqn{n = 95}.
It has been validated against the \eqn{kA} tables in CMH-17-1G for each
value of \eqn{n} from \eqn{n = 2} to \eqn{n = 75}. Larger values of \eqn{n}
also match the tables in CMH-17-1G, but R
emits warnings that "full precision may not have been achieved." When
validating the results of this function against the tables in CMH-17-1G,
the maximum allowable difference between the two is 0.002. The tables in
CMH-17-1G give values to three decimal places.
For more information about tolerance bounds in general, see
Meeker, et. al. (2017).
}
\examples{
kb <- k_factor_normal(n = 10, p = 0.9, conf = 0.95)
print(kb)
## [1] 2.35464
# This can be used to caclulate the B-Basis if
# the sample mean and sample standard deviation
# is known, and data is assumed to be normally
# distributed
sample_mean <- 90
sample_sd <- 5.2
print("B-Basis:")
print(sample_mean - sample_sd * kb)
## [1] B-Basis:
## [1] 77.75587
}
\references{
K. Krishnamoorthy and T. Mathew, Statistical Tolerance Regions: Theory,
Applications, and Computation. Hoboken: John Wiley & Sons, 2008.
W. Meeker, G. Hahn, and L. Escobar, Statistical Intervals: A Guide
for Practitioners and Researchers, Second Edition.
Hoboken: John Wiley & Sons, 2017.
“Composite Materials Handbook, Volume 1. Polymer Matrix Composites
Guideline for Characterization of Structural Materials,” SAE International,
CMH-17-1G, Mar. 2012.
}
\seealso{
\code{\link[=basis_normal]{basis_normal()}}
}
cmstatr/man/glance.levene.Rd 0000644 0001762 0000144 00000003124 14015477557 015516 0 ustar ligges users % Generated by roxygen2: do not edit by hand
% Please edit documentation in R/levene.R
\name{glance.levene}
\alias{glance.levene}
\title{Glance at a \code{levene} object}
\usage{
\method{glance}{levene}(x, ...)
}
\arguments{
\item{x}{a \code{levene} object returned from \code{\link[=levene_test]{levene_test()}}}
\item{...}{Additional arguments. Not used. Included only to match generic
signature.}
}
\value{
A one-row \code{\link[tibble:tibble]{tibble::tibble()}} with the following
columns:
\itemize{
\item \code{alpha} the value of alpha specified
\item \code{modcv} a logical value indicating whether the modified
CV approach was used.
\item \code{n} the total number of observations
\item \code{k} the number of groups
\item \code{f} the value of the F test statistic
\item \code{p} the computed p-value
\item \code{reject_equal_variance} a boolean value indicating whether the
null hypothesis that all samples have the same variance is rejected
}
}
\description{
Glance accepts an object of type \code{levene} and returns a
\code{\link[tibble:tibble]{tibble::tibble()}} with
one row of summaries.
Glance does not do any calculations: it just gathers the results in a
tibble.
}
\examples{
df <- data.frame(
groups = c(rep("A", 5), rep("B", 6)),
strength = c(rnorm(5, 100, 6), rnorm(6, 105, 7))
)
levene_result <- levene_test(df, strength, groups)
glance(levene_result)
## # A tibble: 1 x 7
## alpha modcv n k f p reject_equal_variance
##
## 1 0.05 FALSE 11 2 0.0191 0.893 FALSE
}
\seealso{
\code{\link[=levene_test]{levene_test()}}
}
cmstatr/man/stat_normal_surv_func.Rd 0000644 0001762 0000144 00000002530 14015477557 017425 0 ustar ligges users % Generated by roxygen2: do not edit by hand
% Please edit documentation in R/plotting.R
\name{stat_normal_surv_func}
\alias{stat_normal_surv_func}
\title{Normal Survival Function}
\usage{
stat_normal_surv_func(
mapping = NULL,
data = NULL,
geom = "smooth",
position = "identity",
show.legend = NA,
inherit.aes = TRUE,
n = 100,
pad = FALSE,
...
)
}
\arguments{
\item{mapping}{Set of aesthetic mappings created by \code{aes()}.}
\item{data}{The data to be displayed in this layer. This has the
same usage as a \code{ggplot2} \code{stat} function.}
\item{geom}{The geometric object to use to display the data.}
\item{position}{Position argument}
\item{show.legend}{Should this layer be included in the legends?}
\item{inherit.aes}{If \code{FALSE}, overrides the default aesthetic,
rather than combining with them.}
\item{n}{If \code{NULL}, do not interpolated. Otherwise, the
number of points to interpolate.}
\item{pad}{If \code{TRUE}, pad the ESF with additional points
\verb{(-Inf, 0)} and \verb{(0, Inf)}.}
\item{...}{Other arguments to pass on to \code{layer}.}
}
\description{
The Normal survival function provides a visualization of a
distribution. A normal curve is fit based on the mean and standard
deviation of the data, and the survival function of this normal
curve is plotted. The survival function is simply one minus the
CDF.
}
cmstatr/man/hk_ext.Rd 0000644 0001762 0000144 00000006660 14015477557 014302 0 ustar ligges users % Generated by roxygen2: do not edit by hand
% Please edit documentation in R/basis.R
\name{hk_ext}
\alias{hk_ext}
\alias{hk_ext_z}
\alias{hk_ext_z_j_opt}
\title{Calculate values related to Extended Hanson--Koopmans tolerance bounds}
\usage{
hk_ext_z(n, i, j, p, conf)
hk_ext_z_j_opt(n, p, conf)
}
\arguments{
\item{n}{the sample size}
\item{i}{the first order statistic (1 <= i < j)}
\item{j}{the second order statistic (i < j <= n)}
\item{p}{the content of the tolerance bound (normally 0.90 or 0.99)}
\item{conf}{the confidence level (normally 0.95)}
}
\value{
For \code{hk_ext_z}, the return value is a numeric value representing
the parameter z (denoted as k in CMH-17-1G).
For \code{hk_ext_z_j_opt}, the return value is named list containing
\code{z} and \code{k}. The former is the value of z, as defined by
Vangel (1994), and the latter is the corresponding order statistic.
}
\description{
Calculates values related to Extended Hanson--Koopmans tolerance bounds
as described by Vangel (1994).
}
\details{
Hanson (1964) presents a nonparametric method for determining
tolerance bounds based on consecutive order statistics.
Vangel (1994) extends this method using non-consecutive order statistics.
The extended Hanson--Koopmans method calculates a tolerance bound
(basis value) based on two order statistics and a weighting value
\code{z}. The value of \code{z} is based on the sample size, which
order statistics are selected, the desired content of the tolerance
bond and the desired confidence level.
The function \code{hk_ext_z} calculates the weighting variable \code{z}
based on selected order statistics \code{i} and \code{j}. Based on this
value \code{z}, the tolerance bound can be calculated as:
\deqn{S = z X_{(i)} + (1 - z) X_{(j)}}{S = z X(i) + (1 - z) X(j)}
Where \eqn{X_{(i)}}{X(i)} and \eqn{X_{(j)}}{X(j)} are the \code{i-th}
and \code{j-th} ordered observation.
The function \code{hk_ext_z_j_opt} determines the value of \code{j} and
the corresponding value of \code{z}, assuming \code{i=1}. The value
of \code{j} is selected such that the computed tolerance limit is
nearest to the desired population quantile for a standard normal
distribution when the order statistics are equal to the expected
value of the order statistics for the standard normal distribution.
}
\examples{
# The factors from Table 1 of Vangel (1994) can be recreated
# using the hk_ext_z function. For the sample size n=21,
# the median is the 11th ordered observation. The factor
# required for calculating the tolerance bound with a content
# of 0.9 and a confidence level of 0.95 based on the median
# and first ordered observation can be calculated as follows.
hk_ext_z(n = 21, i = 1, j = 11, p = 0.9, conf = 0.95)
## [1] 1.204806
# The hk_ext_z_j_opt function can be used to refine this value
# of z by finding an optimum value of j, rather than simply
# using the median. Here, we find that the optimal observation
# to use is the 10th, not the 11th (which is the median).
hk_ext_z_j_opt(n = 21, p = 0.9, conf = 0.95)
## $z
## [1] 1.217717
##
## $j
## [1] 10
}
\references{
M. Vangel, “One-Sided Nonparametric Tolerance Limits,”
Communications in Statistics - Simulation and Computation,
vol. 23, no. 4. pp. 1137–1154, 1994.
D. L. Hanson and L. H. Koopmans,
“Tolerance Limits for the Class of Distributions with Increasing
Hazard Rates,” The Annals of Mathematical Statistics,
vol. 35, no. 4. pp. 1561–1570, 1964.
}
\seealso{
\code{\link[=basis_hk_ext]{basis_hk_ext()}}
}
cmstatr/man/normalize_group_mean.Rd 0000644 0001762 0000144 00000002753 13676373651 017235 0 ustar ligges users % Generated by roxygen2: do not edit by hand
% Please edit documentation in R/norm.R
\name{normalize_group_mean}
\alias{normalize_group_mean}
\title{Normalize values to group means}
\usage{
normalize_group_mean(x, group)
}
\arguments{
\item{x}{the variable containing the data to normalized}
\item{group}{the variable containing the groups}
}
\value{
Returns a vector of normalized values
}
\description{
This function computes the mean of each group, then divides each
observation by its corresponding group mean. This is commonly done
when pooling data across environments.
}
\details{
Computes the mean for each group, then divides each value by the mean for
the corresponding group.
}
\examples{
library(dplyr)
carbon.fabric.2 \%>\%
filter(test == "WT") \%>\%
select(condition, strength) \%>\%
mutate(condition_norm = normalize_group_mean(strength, condition)) \%>\%
head(10)
## condition strength condition_norm
## 1 CTD 142.817 1.0542187
## 2 CTD 135.901 1.0031675
## 3 CTD 132.511 0.9781438
## 4 CTD 135.586 1.0008423
## 5 CTD 125.145 0.9237709
## 6 CTD 135.203 0.9980151
## 7 CTD 128.547 0.9488832
## 8 CTD 127.709 0.9426974
## 9 CTD 127.074 0.9380101
## 10 CTD 126.879 0.9365706
}
\references{
“Composite Materials Handbook, Volume 1. Polymer Matrix Composites
Guideline for Characterization of Structural Materials,” SAE International,
CMH-17-1G, Mar. 2012.
}
cmstatr/man/augment.mnr.Rd 0000644 0001762 0000144 00000004272 14015477557 015250 0 ustar ligges users % Generated by roxygen2: do not edit by hand
% Please edit documentation in R/mnr.R
\name{augment.mnr}
\alias{augment.mnr}
\title{Augment data with information from an \code{mnr} object}
\usage{
\method{augment}{mnr}(x, data = x$data, ...)
}
\arguments{
\item{x}{an \code{mnr} object created by
\code{\link[=maximum_normed_residual]{maximum_normed_residual()}}}
\item{data}{a \code{data.frame} or
\code{\link[tibble:tibble]{tibble::tibble()}}
containing the original data that was passed to
\code{maximum_normed_residual}}
\item{...}{Additional arguments. Not used. Included only to match generic
signature.}
}
\value{
When \code{data} is supplied, \code{augment} returns \code{data}, but with
one column appended. When \code{data} is not supplied, \code{augment}
returns a new \code{\link[tibble:tibble]{tibble::tibble()}} with the column
\code{values} containing the original values used by
\code{maximum_normed_residaul} plus one additional column. The additional
column is:
\itemize{
\item \code{.outler} a logical value indicating whether the observation
is an outlier
}
}
\description{
Augment accepts an \code{mnr} object (returned from the function
\code{\link[=maximum_normed_residual]{maximum_normed_residual()}}) and a dataset and adds the column
\code{.outlier} to the dataset. The column \code{.outlier} is a logical
vector indicating whether each observation is an outlier.
When passing data into \code{augment} using the \code{data} argument,
the data must be exactly the data that was passed to
\code{maximum_normed_residual}.
}
\examples{
data <- data.frame(strength = c(80, 98, 96, 97, 98, 120))
m <- maximum_normed_residual(data, strength)
# augment can be called with the original data
augment(m, data)
## strength .outlier
## 1 80 FALSE
## 2 98 FALSE
## 3 96 FALSE
## 4 97 FALSE
## 5 98 FALSE
## 6 120 FALSE
# or augment can be called without the orignal data and it will be
# reconstructed
augment(m)
## # A tibble: 6 x 2
## values .outlier
##
## 1 80 FALSE
## 2 98 FALSE
## 3 96 FALSE
## 4 97 FALSE
## 5 98 FALSE
## 6 120 FALSE
}
\seealso{
\code{\link[=maximum_normed_residual]{maximum_normed_residual()}}
}
cmstatr/man/nonpara_binomial_rank.Rd 0000644 0001762 0000144 00000006026 14015477557 017337 0 ustar ligges users % Generated by roxygen2: do not edit by hand
% Please edit documentation in R/basis.R
\name{nonpara_binomial_rank}
\alias{nonpara_binomial_rank}
\title{Rank for distribution-free tolerance bound}
\usage{
nonpara_binomial_rank(n, p, conf)
}
\arguments{
\item{n}{the sample size}
\item{p}{the desired content for the tolerance bound}
\item{conf}{the confidence level for the desired tolerance bound}
}
\value{
The rank corresponding with the desired tolerance bound
}
\description{
Calculates the rank order for finding distribution-free tolerance
bounds for large samples. This function should only be used for
computing B-Basis for samples larger than 28 or A-Basis for samples
larger than 298. This function is used by
\code{\link[=basis_nonpara_large_sample]{basis_nonpara_large_sample()}}.
}
\details{
This function uses the sum of binomial terms to determine the rank
of the ordered statistic that corresponds with the desired tolerance
limit. This approach does not assume any particular distribution. This
approach is described by Guenther (1969) and by CMH-17-1G.
The results of this function have been verified against the tables in
CMH-17-1G and agreement was found for all sample sizes published in
CMH-17-1G for both A- and B-Basis, as well as the sample sizes
\code{n+1} and \code{n-1}, where
\code{n} is the sample size published in CMH-17-1G.
The tables in CMH-17-1G purportedly list the smallest sample sizes
for which a particular rank can be used. That is, for a sample size
one less than the \code{n} published in the table, the next lowest rank
would be used. In some cases, the results of this function disagree by a
rank of one for sample sizes one less than the \code{n} published in the
table. This indicates a disagreement in that sample size at which
the rank should change. This is likely due to numerical
differences in this function and the procedure used to generate the tables.
However, the disagreement is limited to sample 6500 for A-Basis; no
discrepancies have been identified for B-Basis. Since these sample sizes are
uncommon for composite materials
testing, and the difference between subsequent order statistics will be
very small for samples this large, this difference will have no practical
effect on computed tolerance bounds.
}
\examples{
nonpara_binomial_rank(n = 1693, p = 0.99, conf = 0.95)
## [1] 11
# The above example indicates that for a sample of 1693 observations,
# the A-Basis is best approximated as the 11th ordered observation.
# In the example below, the same ordered observation would also be used
# for a sample of size 1702.
nonpara_binomial_rank(n = 1702, p = 0.99, conf = 0.95)
## [1] 11
}
\references{
W. Guenther, “Determination of Sample Size for Distribution-Free
Tolerance Limits,” Jan. 1969.
Available online: \url{https://www.duo.uio.no/handle/10852/48686}
“Composite Materials Handbook, Volume 1. Polymer Matrix Composites
Guideline for Characterization of Structural Materials,” SAE International,
CMH-17-1G, Mar. 2012.
}
\seealso{
\code{\link[=basis_nonpara_large_sample]{basis_nonpara_large_sample()}}
}
cmstatr/man/glance.mnr.Rd 0000644 0001762 0000144 00000002310 14015477557 015030 0 ustar ligges users % Generated by roxygen2: do not edit by hand
% Please edit documentation in R/mnr.R
\name{glance.mnr}
\alias{glance.mnr}
\title{Glance at a \code{mnr} (maximum normed residual) object}
\usage{
\method{glance}{mnr}(x, ...)
}
\arguments{
\item{x}{An \code{mnr} object}
\item{...}{Additional arguments. Not used. Included only to match generic
signature.}
}
\value{
A one-row \code{\link[tibble:tibble]{tibble::tibble()}} with the following
columns:
\itemize{
\item \code{mnr} the computed MNR test statistic
\item \code{alpha} the value of alpha used for the test
\item \code{crit} the critical value given the sample size and the
significance level
\item \code{n_outliers} the number of outliers found
}
}
\description{
Glance accepts an object of type \code{mnr} and returns a
\code{\link[tibble:tibble]{tibble::tibble()}} with
one row of summaries.
Glance does not do any calculations: it just gathers the results in a
tibble.
}
\examples{
x <- c(rnorm(20, 100, 5), 10)
m <- maximum_normed_residual(x = x)
glance(m)
## # A tibble: 1 x 4
## mnr alpha crit n_outliers
##
## 1 4.23 0.05 2.73 1
}
\seealso{
\code{\link[=maximum_normed_residual]{maximum_normed_residual()}}
}
cmstatr/man/equiv_mean_extremum.Rd 0000644 0001762 0000144 00000017074 14015477557 017100 0 ustar ligges users % Generated by roxygen2: do not edit by hand
% Please edit documentation in R/equiv.R
\name{equiv_mean_extremum}
\alias{equiv_mean_extremum}
\title{Test for decrease in mean or minimum individual}
\usage{
equiv_mean_extremum(
df_qual = NULL,
data_qual = NULL,
mean_qual = NULL,
sd_qual = NULL,
data_sample = NULL,
n_sample = NULL,
alpha,
modcv = FALSE
)
}
\arguments{
\item{df_qual}{(optional) a data.frame containing the qualification data.
Defaults to NULL.}
\item{data_qual}{(optional) a vector of observations from the
"qualification" data to which equivalency is being tested. Or the column of
\code{df_qual} that contains this data. Defaults to NULL}
\item{mean_qual}{(optional) the mean from the "qualification" data to which
equivalency is being tested. Defaults to NULL}
\item{sd_qual}{(optional) the standard deviation from the "qualification"
data to which equivalency is being tested. Defaults to NULL}
\item{data_sample}{(optional) a vector of observations from the sample for
which equivalency is being tested. Defaults to NULL}
\item{n_sample}{(optional) the number of observations in the sample for
which equivalency will be tested. Defaults to NULL}
\item{alpha}{the acceptable probability of a type I error}
\item{modcv}{(optional) a boolean value indicating whether a modified CV
should be used. Defaults to FALSE, in which case the standard deviation
supplied (or calculated from \code{data_qual}) will be used directly.}
}
\value{
Returns an object of class \code{equiv_mean_extremum}. This object is a list
with the following named elements:
\itemize{
\item \code{call} the expression used to call this function
\item \code{alpha} the value of alpha passed to this function
\item \code{n_sample} the number of observations in the sample for which
equivalency is being checked. This is either the value \code{n_sample}
passed to this function or the length of the vector \code{data_sample}.
\item \code{k1} the factor used to calculate the minimum individual
threshold. The minimum individual threshold is calculated as
\eqn{W_{min} = qual\,mean - k_1 \cdot qual\,sd}{
Wmin = qual_mean - k1 * qual_sd}
\item \code{k2} the factor used to calculate the threshold for mean. The
threshold for mean is calculated as
\eqn{W_{mean} = qual\,mean - k_2 \cdot qual\,sd}{
Wmean = qual_mean - k2 * qual_sd}
\item \code{modcv} logical value indicating whether the acceptance
thresholds are calculated using the modified CV approach
\item \code{cv} the coefficient of variation of the qualification data.
This value is not modified, even if \code{modcv=TRUE}
\item \code{cv_star} The modified coefficient of variation. If
\code{modcv=FALSE}, this will be \code{NULL}
\item \code{threshold_min_indiv} The calculated threshold value for
minimum individual
\item \code{threshold_mean} The calculated threshold value for mean
\item \code{result_min_indiv} a character vector of either "PASS" or
"FAIL" indicating whether the data from \code{data_sample} passes the
test for minimum individual. If \code{data_sample} was not supplied,
this value will be \code{NULL}
\item \code{result_mean} a character vector of either "PASS" or
"FAIL" indicating whether the data from \code{data_sample} passes the
test for mean. If \code{data_sample} was not supplied, this value will
be \code{NULL}
\item \code{min_sample} The minimum value from the vector
\code{data_sample}. if \code{data_sample} was not supplied, this will
have a value of \code{NULL}
\item \code{mean_sample} The mean value from the vector
\code{data_sample}. If \code{data_sample} was not supplied, this will
have a value of \code{NULL}
}
}
\description{
This test is used when determining if a new process or
manufacturing location produces material properties that are
"equivalent" to an existing dataset, and hence the existing
basis values are applicable to the new dataset. This test is also
sometimes used for determining if a new batch of material is acceptable.
This function determines thresholds based on both minimum
individual and mean, and optionally evaluates a sample against those
thresholds. The joint distribution between the sample mean
and sample minimum is used to generate these thresholds.
When there is no true difference between the existing ("qualification")
and the new population from which the sample is obtained, there is a
probability of \eqn{\alpha} of falsely concluding that there is a
difference in mean or variance. It is assumed that both the original
and new populations are normally distributed.
According to Vangel (2002), this test provides improved power compared
with a test of mean and standard deviation.
}
\details{
This function is used to
determine acceptance limits for a sample mean and sample minimum.
These acceptance limits are often used to set acceptance limits for
material strength for each lot of material, or each new manufacturing
site. When a sample meets the criteria that its mean and its minimum are
both greater than these limits, then one may accept the lot of material
or the new manufacturing site.
This procedure is used to ensure that the strength of material processed
at a second site, or made with a new batch of material are not degraded
relative to the data originally used to determine basis values for the
material. For more information about the use of this procedure, see
CMH-17-1G or PS-ACE 100-2002-006.
There are several optional arguments to this function. However, you can't
omit all of the optional arguments. You must supply either
\code{data_sample} or \code{n_sample}, but not both. You must also supply
either \code{data_qual} (and \code{df_qual} if \code{data_qual} is a
variable name and not a vector) or both \code{mean_qual} and \code{sd_qual},
but if you supply \code{data_qual} (and possibly \code{df_qual}) you should
not supply either \code{mean_qual} or \code{sd_qual} (and visa-versa). This
function will issue a warning or error if you violate any of these rules.
If \code{modcv} is TRUE, the standard deviation used to calculate the
thresholds will be replaced with a standard deviation calculated
using the Modified Coefficient of Variation (CV) approach.
The Modified CV approach is a way of adding extra variance to the
qualification data in the case that the qualification data has less
variance than expected, which sometimes occurs when qualification testing
is performed in a short period of time.
Using the Modified CV approach, the standard deviation is calculated by
multiplying \code{CV_star * mean_qual} where \code{mean_qual} is either the
value supplied or the value calculated by \code{mean(data_qual)} and
\eqn{CV*} is the value computed by \code{\link[=calc_cv_star]{calc_cv_star()}}.
}
\examples{
equiv_mean_extremum(alpha = 0.01, n_sample = 6,
mean_qual = 100, sd_qual = 5.5, modcv = TRUE)
##
## Call:
## equiv_mean_extremum(mean_qual = 100, sd_qual = 5.5, n_sample = 6,
## alpha = 0.01, modcv = TRUE)
##
## Modified CV used: CV* = 0.0675 ( CV = 0.055 )
##
## For alpha = 0.01 and n = 6
## ( k1 = 3.128346 and k2 = 1.044342 )
## Min Individual Sample Mean
## Thresholds: 78.88367 92.95069
}
\references{
M. G. Vangel. Lot Acceptance and Compliance Testing Using the Sample Mean
and an Extremum, Technometrics, vol. 44, no. 3. pp. 242–249. 2002.
“Composite Materials Handbook, Volume 1. Polymer Matrix Composites
Guideline for Characterization of Structural Materials,” SAE International,
CMH-17-1G, Mar. 2012.
Federal Aviation Administration, “Material Qualification and Equivalency
for Polymer Matrix Composite Material Systems,” PS-ACE 100-2002-006,
Sep. 2003.
}
\seealso{
\code{\link[=k_equiv]{k_equiv()}}
\code{\link[=calc_cv_star]{calc_cv_star()}}
}
cmstatr/man/figures/ 0000755 0001762 0000144 00000000000 14052741370 014151 5 ustar ligges users cmstatr/man/figures/logo.png 0000644 0001762 0000144 00000066335 13660767610 015645 0 ustar ligges users PNG
IHDR X? sBIT|d pHYs [ [h tEXtSoftware www.inkscape.org< IDATxw|TUڀ;HH轓PPWņU?WWWZ@ׂ* H!M@dfL Fɽs$}y{@j%X
y,>EV ~ i\b`!$$$H[s Q%$$HV4%$Z8J` G
5HHPpj7\EY>D b$' nrEp43|ȉ|0 =b / )ZY.
p'ч_\v>! p '`'OLrr2K,h%1k#zl"BaWh s n\"ޞу5kְj*:uT/j07 "BQ{uy#4 7$DӲVBBBXx1IIIL8;.
Pt'3ȍ#N# M}q)H# p1؇SqƑҥK kA\j`}_*D`zuy9݇>$O a.]Xbׯo߾Xޑ" XJ]C5X)Ui $?:xafh\#od *e C ̫;1-s R5z# p R;A;IMMe Ս]MZF N;ez|i49Z%# p݈"?zc,_6m. {)5pq 4,Mh:W#q|ui%$0DS/a۶mYlwfP`#7\&VCw%4pP*$̞=&lb.]˄vF/Ui$x i1w 9rE+!Q(1~6!,vJ+OVJ@jAt~FLYj ;z\d(P/坋@Bj $IxbèQͫbFWQ)cj $5 k0T*7o iii̟? z( j5FʩwRh<q2ٿ?K,!0koTMJِ\rj ]
p4)qgZڵ+Vbݺuu(]92Q
k0`Z W G4j%((E W6+
j RX@\"VGb|&IlH,=uBOUi 9
cI!Cc/_N W6[TW 펊j mBШ=R5Okbf\֥J3wCt:dRyuP*z .@sWi2 ^!A!+,ܵ F ((0a0 ssALhhSШ&Pl~gqL52 x x40-=m
bɓygf=\leQj>Z%,ZpF ɣC_xϘ7o6A%~ՍÙN)J>G܇#7>&j RLL K,aΝ;Ǟ={ذa bZ@``[ P 7aԨ]Ƀ u{8Mն||4߀HH㎪81^܁P}Y y:gP{^~[4 z}BCȨ#9sCmBuuᣏV0gΟ2QD_\}FI oms@aRX x$T*<
AURRΝ;Yr !??@t"0 h&Ojcп@&鳹rPTE\^]\E ("^dzdz)**b˖|r{죰̬X,٨T::铹뮛СC/~;f4Z?Wv
La~Dzk㎪a O|(Iڽ{w|M&Meڍ,_#)ǒ)(($ ";aa̚5{|*nu_РR)Wlv\# Up% xqǥ*<<裨Tclf
,{ ̬#J""ӦMk y^f͚ Y_? 7OAW
/4\ Q\ E pkw4g{/2o_VRQɞ={Xk6oF^^)GB}x^V^ԩ0h "r̥L{x As8tpcǎeuJpa&^C ;Tl"""zҾ}^z ƍ[~&z 6ȯD
Lض|3|QU[*e$b}FrS)eͲ&VsBj c\24")x@ӱ` ?ٳj|J6mx'HIΊK>|
uGЫp֮ӽ
9
r Q74 STB֒ 0c Yp!/el
7ؚ]~
ıc<^/Qͺ]sR5VYI߫S #rAغu++Vb\.zbX ƎBc5\{4 XV)
QK&tˣ˫lbCCT{% #""Xt)wfM2F^ظ;}z FaA>o Vr
% ]ԪE|XL֗J fʕ 6o 4':vlܹ)3;8r?+7 Fjueee'rEU_1h f}@.1$NM%:O
'Oիӟtŕilr9ƍd g%e J;VPp:#Ѫo|AF}=:L4TO͍1I> _c]K٬I: YdB7 *e Cv k9x(+L\ WէǤ$fhp+Bׯ/qbdPZVdB75X>,<-ӣ˫D,BY٠
pG;GF1rdU\X|Zәumnv
iVuKPĴF [ ;xjС RӶp睏Z5u:B$ڿ(] ZEx:
U*Ҩ*67Edd$˖-c̟0wLlfܸ),b 6kA@7 tڻ= @u~ ^]Qi'{`%h{"ؾ};gϾɮ]r7c6+ټ'bb9p٭|h"Ni=:i{w#j]% z "77>ij&$$0˿ÑIddoMJTT+rZ P(⤹\.' @1% `xӽ0N'U)ͷJ˦!˞ `ɒ%5A7p>Vŭ T*d2h JFF)}_ ZBT* r \Rkd(
:-ADDC(:wKtԉHMM|)$J˾ 0 N;x Ȯ| O"nV+!!!gʢ̂̌bfwRldpj Ng@*cƌr>))gV9~PTǚ5_3h >̊f- ',,
-mkמL<{ﻹ^fqN<ɑ#i :x'NGiR?p:7aHp{`F2Q^Dyr6l2v%@7
$IuCyþ4N Ün]y}ʠw4oo!\sLp;Z'vҫpLŅ]ָWaa!7[NtXe .t 5C&1"֗JYY &! [~GJJ
SP AQ{ 1n~1/~$`Z$x+&Sltf{ju P`` >,Y [ؼftft9ApT*q8dZW!*FCYTJK6ܞGA1h z>@Ua]fmAn^ YYg9uj? y7ڥ;>znФ+6oSOʩ?
څ\ޖ%*P`Eg)6ZRcqÇgʕu`c/jVft:Ap9dZw X,9#j hWK5Veر +zŬ^+ }
i'O߿c=`9FӶm;xr,"h'FC֧J\adAg`6ڢd葄FQd2gO. L] ֭[1c{`Qe Һ5D ߝO6~FΝk%1 ̚u MJv ÇMh<3= _HiiH{ F [n~_=G
"NRޫ :-n)h ð0z-g Tl8 vp
dZ6G^^rб'vbS)2vYyXFP@zNvQtMڷ &&ѧT*Sԩ7p)-z_]Ϲ'x yefͺT ^ %$2"Gl| vd. \kח.]rl,V Ndddp(;\ Ovv. BdDDbv4I&D6n- \Ȥëر4D@Idd ;#:=]Eѥһws
M W)((_/<_?cʏ뼹xb~ ERRq#KkFǭ Seo?bXY͆Z-7!#3 Lz 9hf-zӧ#F#Gfw^֭K`s0$&d, t CdHڷGt
$..z?;xE?>p gO"6!2s6ZCۈj݊n:гWk
W^6m½ӧr9ՄuA!8q(C &<\ &M=o뾥{m,\GRџ 347M={͛ٽ;>}'QP 8E F%
[](https://github.com/cmstatr/cmstatr/actions/workflows/R-CMD-check.yaml)
[](https://app.codecov.io/gh/cmstatr/cmstatr?branch=master)
[](https://doi.org/10.21105/joss.02265)
[](https://cran.r-project.org/package=cmstatr)
[](https://cran.r-project.org/package=cmstatr)
# What It Does
The `cmstatr` package provides functions for performing statistical
analysis of composite material data. The statistical methods implemented
are those described in [CMH-17-1G](https://www.cmh17.org/). This package
focuses on calculating basis values (lower tolerance bounds) for
material strength properties, as well as performing the associated
diagnostic tests. Functions are also provided for testing for
equivalency between alternate samples and the “qualification” or
“baseline” samples.
Additional details about the package are available in the paper by
Kloppenborg (2020,