jfa version 0.1.0 (#9)

* jfa version 0.1.0 * Update auditWorkflow.Rmd
koenderks · Dec 14, 2019 · 467306d · 467306d
1 parent cf4477b
commit 467306d
Show file tree

Hide file tree

Showing 19 changed files with 219 additions and 670 deletions.
diff --git a/.Rbuildignore b/.Rbuildignore
@@ -1,2 +1,4 @@
 ^\.travis\.yml$
 cran-comments.md
+^doc$
+^Meta$
diff --git a/.gitignore b/.gitignore
@@ -0,0 +1,2 @@
+doc
+Meta
diff --git a/DESCRIPTION b/DESCRIPTION
@@ -1,17 +1,17 @@
 Package: jfa
 Title: A multi-functional R package for auditing
-Version: 1.0.0
+Version: 0.1.0
 Authors@R: 
     person(given = "Koen",
            family = "Derks",
            role = c("aut", "cre"),
            email = "k.derks@nyenrode.nl")
-Description: The jfa package provides functions for daily use in auditing, such as calculating sample sizes, sampling, and calculating confidence bounds.
+Description: Functions for daily use in auditing, such as calculating sample sizes, sampling, and evaluating samples by calculating confidence bounds.
 Language: en-US
 License: GPL-3
 Encoding: UTF-8
 LazyData: true
-RoxygenNote: 7.0.1
+RoxygenNote: 7.0.2
 VignetteBuilder: knitr
 Suggests: 
     testthat, knitr, rmarkdown
diff --git a/NEWS.md b/NEWS.md
@@ -1,3 +1,3 @@
-# jfa 1.0.0
+# jfa 0.1.0
 
-First version of the `jfa` package.
+First version of the `jfa` package. The package provides four functions: `auditPrior()`, `planning()`, `sampling()`, and `evaluation()`.
diff --git a/R/auditPrior.R b/R/auditPrior.R
@@ -36,23 +36,18 @@
 #'
 #' @examples 
 #' library(jfa)
-#' set.seed(1)
 #' 
-#' # Generate some audit data (N = 1000).
-#' population <- data.frame(ID = sample(1000:100000, size = 1000, replace = FALSE), 
-#'                          bookValue = runif(n = 1000, min = 700, max = 1000))
-#' 
-#' # Specify the materiality, confidence, and expected errors.
+#' # Specify the materiality, confidence, and expected errors:
 #' materiality   <- 0.05   # 5%
 #' confidence    <- 0.95   # 95%
 #' expectedError <- 0.025  # 2.5%
 #' 
-#' # Specify the inherent risk (ir) and control risk (cr).
+#' # Specify the inherent risk (ir) and control risk (cr):
 #' ir <- 1     # 100%
 #' cr <- 0.6   # 60%
 #' 
 #' # Create a beta prior distribution according to the Audit Risk Model (arm) 
-#' # and a binomial likelihood.
+#' # and a binomial likelihood:
 #' prior <- auditPrior(materiality = materiality, confidence = confidence, 
 #'                     method = "arm", ir = ir, cr = cr, 
 #'                     expectedError = expectedError, likelihood = "binomial")
@@ -63,56 +58,6 @@
 #' # Prior sample size:     51 
 #' # Prior errors:          1.27 
 #' # Prior:                 beta(2.275, 50.725)
-#' 
-#' # Calculate the sample size according to the binomial distribution with the specified prior.
-#' sampleSize <- planning(materiality = materiality, confidence = confidence, 
-#'                        expectedError = expectedError, prior = prior, likelihood = "binomial")
-#' print(sampleSize)
-#' 
-#' # jfa planning results for beta prior with binomial likelihood:
-#' #      
-#' # Materiality:             5% 
-#' # Confidence:              95% 
-#' # Sample size:             169 
-#' # Allowed sample errors:   4.23 
-#' # Prior parameter alpha:   2.275 
-#' # Prior parameter beta:    50.725
-#' 
-#' # Draw sample using random monetary unit sampling.
-#' sampleResult <- sampling(population = population, sampleSize = sampleSize, 
-#'                          algorithm = "random", units = "mus", seed = 1, bookValues = "bookValue")
-#' print(sampleResult)
-#' 
-#' # jfa sampling results for random monetary unit sampling: 
-#' #      
-#' # Population size:         1000 
-#' # Sample size:             169 
-#' # Proportion n/N:          0.169 
-#' # Precentage of value:     16.84%
-#' 
-#' # Isolate the sample.
-#' sample <- sampleResult$sample
-#' 
-#' # For this example, we use the book values as audit values. Implies zero errors at this point.
-#' sample$trueValue <- sample$bookValue
-#' 
-#' # One overstatement is found.
-#' sample$trueValue[2] <- sample$trueValue[2] - 500
-#' 
-#' # Evaluate the sample with one partial error using the posterior distribution.
-#' conclusion <- evaluation(sample = sample, bookValues = "bookValue", auditValues = "trueValue", 
-#'                          prior = prior, materiality = 0.05)
-#' print(conclusion)
-#' 
-#' # jfa evaluation results for binomial likelihood with prior:
-#' #   
-#' # Materiality:           5% 
-#' # Confidence:            95% 
-#' # Upper bound:           2.729% 
-#' # Sample size:           169 
-#' # Sample errors:         1 
-#' # Conclusion:            Approve population
-#'  
 #' @export
 
 auditPrior <- function(materiality, confidence = 0.95, method = "arm", ir = 1, cr = 1, 

diff --git a/R/evaluation.R b/R/evaluation.R
@@ -86,50 +86,50 @@
 #'
 #' @examples
 #' library(jfa)
-#' 
-#' # Generate some audit data (N = 1000)
 #' set.seed(1)
+#' 
+#' # Generate some audit data (N = 1000):
 #' data <- data.frame(ID = sample(1000:100000, size = 1000, replace = FALSE), 
-#'                   bookValue = runif(n = 1000, min = 700, max = 1000))
-#'
-#' # Using the binomial likelihood, calculates the upper 95% confidence bound for a 
-#' # materiality of 5% when 1% full errors are found in a sample (n = 93).
-#' jfaRes <- planning(materiality = 0.05, confidence = 0.95, expectedError = 0.01, 
-#'                    likelihood = "binomial")
-#'
+#'                    bookValue = runif(n = 1000, min = 700, max = 1000))
+#' 
 #' # Using monetary unit sampling, draw a random sample from the population.
-#' samp <- sampling(population = data, sampleSize = jfaRes, units = "mus", 
-#'                  bookValues = "bookValue", algorithm = "random")
-#'
-#' samp$sample$trueValue <- samp$sample$bookValue
-#' samp$sample$trueValue[2] <- samp$sample$trueValue[2] - 500 # One overstatement is found
-#'
-#' # Evaluate the sample using the stringer bound.
-#' conclusion <- evaluation(sample = samp$sample, bookValues = "bookValue", 
-#'                          auditValues = "trueValue", method = "stringer", materiality = 0.05)
-#' print(conclusion)
+#' s1 <- sampling(population = data, sampleSize = 100, units = "mus", 
+#'                bookValues = "bookValue", algorithm = "random")
+#' s1_sample <- s1$sample
+#' s1_sample$trueValue <- s1_sample$bookValue
+#' s1_sample$trueValue[2] <- s1_sample$trueValue[2] - 500 # One overstatement is found
 #' 
-#' # jfa evaluation results for stringer method:
+#' # Using summary statistics, calculate the upper confidence bound according
+#' # to the binomial distribution:
+#' 
+#' e1 <- evaluation(nSumstats = 100, kSumstats = 1, method = "binomial", 
+#'                  materiality = 0.05)
+#' print(e1)
+#' 
+#' # jfa evaluation results for binomial method:
 #' #   
 #' # Materiality:           5% 
 #' # Confidence:            95% 
-#' # Upper bound:           4.244% 
-#' # Sample size:           93 
+#' # Upper bound:           4.656% 
+#' # Sample size:           100 
 #' # Sample errors:         1 
+#' # Sum of taints:         1  
 #' # Conclusion:            Approve population
-#'
-#' # Evaluate the sample using summary statistics (n = 93, k = 1).
-#' conclusion <- evaluation(nSumstats = 93, kSumstats = 1, method = "binomial", 
-#'                          materiality = 0.05)
-#' print(conclusion)
 #' 
-#' # jfa evaluation results for binomial method:
+#' # Evaluate the raw sample using the stringer bound:
+#' 
+#' e2 <- evaluation(sample = s1_sample, bookValues = "bookValue", auditValues = "trueValue", 
+#'                  method = "stringer", materiality = 0.05)
+#' print(e2)
+#' 
+#' # jfa evaluation results for stringer method:
 #' #   
 #' # Materiality:           5% 
 #' # Confidence:            95% 
-#' # Upper bound:           4.999% 
-#' # Sample size:           93 
+#' # Upper bound:           3.952% 
+#' # Sample size:           100 
 #' # Sample errors:         1 
+#' # Sum of taints:         0.587  
 #' # Conclusion:            Approve population
 #' 
 #' @keywords evaluation confidence bound audit

diff --git a/R/hidden.R b/R/hidden.R
@@ -36,7 +36,7 @@ print.jfaSampling <- function(x, ...){
 #      
 # Population size:        ", nrow(x$population),"
 # Sample size:            ", nrow(x$sample),"
-# Proportion n/N:         ", round(nrow(x$sample)/nrow(x$population)), 3) 
+# Proportion n/N:         ", round(nrow(x$sample)/nrow(x$population), 3)) 
   }
 }
 

diff --git a/R/planning.R b/R/planning.R
@@ -48,17 +48,51 @@
 #' # Using the binomial distribution, calculates the required sample size for a 
 #' # materiality of 5% when 2.5% mistakes are expected to be found in the sample.
 #' 
-#' # Frequentist planning with binomial likelihood.
-#' planning(materiality = 0.05, confidence = 0.95, expectedError = 0.025, 
-#'          likelihood = "binomial")
+#' # Frequentist planning with binomial likelihood:
 #' 
-#' # Bayesian planning with uninformed prior.
-#' planning(materiality = 0.05, confidence = 0.95, expectedError = 0.025, 
-#'          likelihood = "binomial", prior = TRUE)
+#' p1 <- planning(materiality = 0.05, confidence = 0.95, expectedError = 0.025, 
+#'                likelihood = "binomial")
+#' print(p1)
 #' 
-#' # Bayesian planning with informed prior (based on 10 correct observations).
-#' planning(materiality = 0.05, confidence = 0.95, expectedError = 0.025, 
-#'          likelihood = "binomial", prior = TRUE, kPrior = 0, nPrior = 10)
+#' # jfa planning results for binomial likelihood:
+#' #      
+#' # Materiality:             5% 
+#' # Confidence:              95% 
+#' # Sample size:             234 
+#' # Allowed sample errors:   6
+#' 
+#' # Bayesian planning with uninformed prior:
+#' 
+#' p2 <- planning(materiality = 0.05, confidence = 0.95, expectedError = 0.025, 
+#'                likelihood = "binomial", prior = TRUE)
+#' print(p2)
+#' 
+#' # jfa planning results for beta prior with binomial likelihood:
+#' #      
+#' # Materiality:             5% 
+#' # Confidence:              95% 
+#' # Sample size:             220 
+#' # Allowed sample errors:   5.5 
+#' # Prior parameter alpha:   1 
+#' # Prior parameter beta:    1
+#' 
+#' # Bayesian planning with informed prior:
+#' 
+#' prior <- auditPrior(materiality = 0.05, confidence = 0.95, cr = 0.6, 
+#'                     expectedError = 0.025, likelihood = "binomial")
+#' 
+#' p3 <- planning(materiality = 0.05, confidence = 0.95, expectedError = 0.025,
+#'                prior = prior)
+#' print(p3)
+#' 
+#' # jfa planning results for beta prior with binomial likelihood:
+#' #      
+#' # Materiality:             5% 
+#' # Confidence:              95% 
+#' # Sample size:             169 
+#' # Allowed sample errors:   4.23 
+#' # Prior parameter alpha:   2.275 
+#' # Prior parameter beta:    50.725
 #'
 #' @keywords planning sample size audit
 #'
@@ -129,7 +163,8 @@ planning <- function(materiality, confidence = 0.95, expectedError = 0, likeliho
           break
         }
       } else {
-        prob <- stats::dbinom(0:ceiling(implicitK), size = i, prob = materiality)
+        implicitK <- ceiling(implicitK)
+        prob <- stats::dbinom(0:implicitK, size = i, prob = materiality)
         if(sum(prob) < (1 - confidence)){
           ss <- i
           break

diff --git a/R/sampling.R b/R/sampling.R
@@ -48,22 +48,40 @@
 #'
 #' @examples
 #' library(jfa)
+#' set.seed(1)
 #' 
 #' # Generate some audit data (N = 1000).
 #' population <- data.frame(ID = sample(1000:100000, size = 1000, replace = FALSE), 
 #'                          bookValue = runif(n = 1000, min = 700, max = 1000))
 #' 
-#' # Calculate the sample size according to the binomial distribution with zero errors
-#' jfaRes <- planning(materiality = 0.05, confidence = 0.95, expectedError = 0, 
-#'                    likelihood = "binomial")
-#'
-#' # Draw sample using random record sampling
-#' sampling(population = population, sampleSize = jfaRes, algorithm = "random", 
-#'          units = "records", seed = 1)
+#' # Draw a custom sample of 100 from the population (via random record sampling):
+#' 
+#' s1 <- sampling(population = population, sampleSize = 100, algorithm = "random", 
+#'                units = "records", seed = 1)
+#' print(s1)
+#' 
+#' # jfa sampling results for random random record sampling: 
+#' #      
+#' # Population size:         1000 
+#' # Sample size:             100 
+#' # Proportion n/N:          0.1
+#' 
+#' # Use the result from the planning stage in the sampling stage:
+#' 
+#' p1 <- planning(materiality = 0.05, confidence = 0.95, expectedError = 0.025, 
+#'                likelihood = "binomial")
+#' 
+#' # Draw a sample via random monetary unit sampling:
+#' s2 <- sampling(population = population, sampleSize = p1, algorithm = "random", 
+#'                units = "mus", seed = 1, bookValues = "bookValue")
+#' print(s2)
 #' 
-#' # Draw sample using random monetary unit sampling
-#' sampling(population = population, sampleSize = jfaRes, algorithm = "random", 
-#'          units = "mus", bookValues = "bookValue", seed = 1)
+#' # jfa sampling results for random monetary unit sampling: 
+#' #      
+#' # Population size:         1000 
+#' # Sample size:             234 
+#' # Proportion n/N:          0.234 
+#' # Percentage of value:     23.3%
 #'
 #' @keywords sampling sample audit
 #'

diff --git a/README.md b/README.md
@@ -19,7 +19,7 @@
 * [Functions](##Functions) 
 * [Poster](##Poster) 
 
-For complete documentation, see the package [manual](./man/manual/jfa_1.0.0.pdf). For a complete example, see the package [vignette](./vignettes/jfaVignette.html).
+For complete documentation, see the package [manual](./man/manual/jfa_0.1.0.pdf). For a complete example, see the package [vignette](./vignettes/jfaVignette.html).
 
 ### Authors
 

diff --git a/cran-comments.md b/cran-comments.md
@@ -6,4 +6,4 @@
 There were no ERRORs or WARNINGs or NOTEs. 
 
 ## Downstream dependencies
-There are currently no downstream dependencies for this package
+There are currently no downstream dependencies for this package.