Package 'mcradds'

Description

mcradds Processing and analyzing of In Vitro Diagnostic Data.

Author(s)

Maintainer: Kai Gu [email protected] [copyright holder]

See Also

Useful links:

• https://github.com/kaigu1990/mcradds

• https://kaigu1990.github.io/mcradds/

• Report bugs at https://github.com/kaigu1990/mcradds/issues

Description

This ADSL is created by subsetting the CDISC ADSL with 60 subjects in each of two treatments like placebo and Xanomeline (this one corresponds to high dose level in the original ADSL).

Usage

adsl_sub

Format

A adsl_sub data set contains 120 observations and 14 variables. And the description of each variable has been labeled in data set.

Description

A copy from VCA::anovaVCA in VCA package

Usage

anovaVCA(...)

Arguments

Value

a class of VCA for downstream analysis.

See Also

VCA::anovaVCA()

Examples

data(glucose)
anovaVCA(value ~ day / run, glucose)

Description

This function compares two AUC of paired two-sample diagnostic assays by standardized difference method, which has a little difference in SE calculation with unpaired design. In order to compare the two assays, this function provides three assessments including 'difference', 'non-inferiority' and 'superiority'. This method of comparing is referred from Liu(2006)'s article that can be found in reference section below.

Usage

aucTest(
  x,
  y,
  response,
  h0 = 0,
  conf.level = 0.95,
  method = c("difference", "non-inferiority", "superiority"),
  ...
)

Arguments

Details

If the samples are not considered independent, such as in a paired design, the SE can not be computed by the method of Delong provided in pROC package. Here the aucTest function use the standardized difference approach from Liu(2006) publication to compute the SE and corresponding hypothesis test statistic for a paired design study.

• difference is to test the difference between two diagnostic tests, the default h0 is zero.

• non-inferiority is to test the new diagnostic tests is no worse than the standard diagnostic test in a specific margin, but the same time maybe it's safer, easier to administer or cost less.

• superiority is to test the test the new diagnostic tests is better than the standard diagnostic test in a specific margin(default is zero), having better efficacy.

Value

A RefInt object contains relevant results in comparing the paired ROC of two-sample assays.

Note

The test of significance for the difference is not equal to the result of EP24A2 Appendix D. Table D2. Because the Table D2 uses the method of Hanley & McNeil (1982), whereas this function here uses the method of DeLong et al. (1988), which results in the difference of SE. Thus the corresponding Z statistic and P value will be not equal as well.

References

Jen-Pei Liu (2006) "Tests of equivalence and non-inferiority for diagnostic accuracy based on the paired areas under ROC curves". Statist. Med. , 25:1219–1238. DOI: 10.1002/sim.2358.

Examples

data("ldlroc")
# H0 : Difference between areas = 0:
aucTest(x = ldlroc$LDL, y = ldlroc$OxLDL, response = ldlroc$Diagnosis)

# H0 : Superiority margin <= 0.1:
aucTest(
  x = ldlroc$LDL, y = ldlroc$OxLDL, response = ldlroc$Diagnosis,
  method = "superiority", h0 = 0.1
)

# H0 : Non-inferiority margin <= -0.1:
aucTest(
  x = ldlroc$LDL, y = ldlroc$OxLDL, response = ldlroc$Diagnosis,
  method = "non-inferiority", h0 = -0.1
)

Description

Draw a ggplot-based difference Bland-Altman plot of reference assay vs. test assay for BAsummary object, and a regression plot for MCResult. Also Providing the necessary and useful option arguments for presentation.

Usage

autoplot(object, ...)

## S4 method for signature 'BAsummary'
autoplot(
  object,
  type = c("absolute", "relative"),
  color = "black",
  fill = "lightgray",
  size = 1.5,
  shape = 21,
  jitter = FALSE,
  ref.line = TRUE,
  ref.line.params = list(col = "blue", linetype = "solid", size = 1),
  ci.line = FALSE,
  ci.line.params = list(col = "blue", linetype = "dashed"),
  loa.line = TRUE,
  loa.line.params = list(col = "blue", linetype = "dashed"),
  label = TRUE,
  label.digits = 4,
  label.params = list(col = "black", size = 4),
  x.nbreak = NULL,
  y.nbreak = NULL,
  x.title = NULL,
  y.title = NULL,
  main.title = NULL
)

## S4 method for signature 'MCResult'
autoplot(
  object,
  color = "black",
  fill = "lightgray",
  size = 1.5,
  shape = 21,
  jitter = FALSE,
  identity = TRUE,
  identity.params = list(col = "gray", linetype = "dashed"),
  reg = TRUE,
  reg.params = list(col = "blue", linetype = "solid"),
  equal.axis = FALSE,
  legend.title = TRUE,
  legend.digits = 2,
  x.nbreak = NULL,
  y.nbreak = NULL,
  x.title = NULL,
  y.title = NULL,
  main.title = NULL
)

Arguments

Value

A ggplot based Bland-Altman plot or regression plot that can be easily customized using additional ggplot functions.

Note

If you'd like to alter any part that this autoplot function haven't provided, adding other ggplot statements are suggested.

See Also

h_difference() to see the type details.

mcr::mcreg() to see the regression parameters.

Examples

# Specify the type for difference plot
data("platelet")
object <- blandAltman(x = platelet$Comparative, y = platelet$Candidate)
autoplot(object)
autoplot(object, type = "relative")

# Set the addition parameters for `geom_point`
autoplot(object,
  type = "relative",
  jitter = TRUE,
  fill = "lightblue",
  color = "grey",
  size = 2
)

# Set the color and line type for reference and limits of agreement lines
autoplot(object,
  type = "relative",
  ref.line.params = list(col = "red", linetype = "solid"),
  loa.line.params = list(col = "grey", linetype = "solid")
)

# Set label color, size and digits
autoplot(object,
  type = "absolute",
  ref.line.params = list(col = "grey"),
  loa.line.params = list(col = "grey"),
  label.digits = 2,
  label.params = list(col = "grey", size = 3, fontface = "italic")
)

# Add main title, X and Y axis titles, and adjust X ticks.
autoplot(object,
  type = "absolute",
  x.nbreak = 6,
  main.title = "Bland-Altman Plot",
  x.title = "Mean of Test and Reference Methods",
  y.title = "Reference - Test"
)
# Using the default arguments for regression plot
data("platelet")
fit <- mcreg(
  x = platelet$Comparative, y = platelet$Candidate,
  method.reg = "Deming", method.ci = "jackknife"
)
autoplot(fit)

# Only present the regression line and alter the color and shape.
autoplot(fit,
  identity = FALSE,
  reg.params = list(col = "grey", linetype = "dashed"),
  legend.title = FALSE,
  legend.digits = 4
)

Description

The BAsummary class is used to display the BlandAltman analysis and outliers.

Usage

BAsummary(call, data, stat, param)

Arguments

Value

An object of class BAsummary.

Slots

call

call

data

data

outlier

outlier

param

param

Description

Calculate the Bland-Altman related statistics with specific difference type, such as difference, limited of agreement and confidence interval. And the outlier detecting function and graphic function will get the difference result from this.

Usage

blandAltman(x, y, sid = NULL, type1 = 3, type2 = 5, conf.level = 0.95)

Arguments

Value

A object with BAsummary class that contains the BlandAltman analysis.

• data a data frame contains the raw data from the input.

• stat a list contains the summary table (tab) of Bland-Altman analysis, vector (absolute_diff) of absolute difference and vector (relative_diff) of relative difference.

See Also

h_difference() to see the type details.

Examples

data("platelet")
blandAltman(x = platelet$Comparative, y = platelet$Candidate)

# with sample id as input sid
blandAltman(x = platelet$Comparative, y = platelet$Candidate, sid = platelet$Sample)

# Specifiy the type for difference
blandAltman(x = platelet$Comparative, y = platelet$Candidate, type1 = 1, type2 = 4)

Description

A copy from mcr::calcBias in mcr package

Usage

calcBias(...)

Arguments

Value

Bis and corresponding confidence interval for the specific medical decision levels (x.levels).

See Also

mcr::calcBias()

Examples

data(platelet)
fit <- mcreg(
  x = platelet$Comparative, y = platelet$Candidate,
  method.reg = "Deming", method.ci = "jackknife"
)
calcBias(fit, x.levels = c(30, 200))
calcBias(fit, x.levels = c(30, 200), type = "proportional")
calcBias(fit, x.levels = c(30, 200), type = "proportional", percent = FALSE)

Description

This example calcium can be used to compute the reference range of Calcium in 240 medical students by sex.

Usage

calcium

Format

A calcium data set contains 240 observations and 3 variables.

Sample

Sample id

Value

Measurements from target subjects

Group

Sex group of target subjects

Source

CLSI-EP28A3 Table 4. is cited in this data set.

Description

This function concatenates inputs like cat() and prints them with newline.

Usage

cat_with_newline(...)

Arguments

Value

None, only used for the side effect of producing the concatenated output in the R console.

See Also

This is similar to cli::cat_line().

Examples

cat_with_newline("hello", "world")

Description

The Desc class serves as the store for results from frequency and univariate statistics analysis.

Usage

Desc(func, mat, stat)

Arguments

Value

An object of class Desc.

Slots

func

func

mat

mat

stat

stat

Description

Create a summary table for one or more variables by one group, as well as a total column if necessary.

Usage

descfreq(
  data,
  denom = NULL,
  var,
  bygroup,
  format,
  fctdrop = FALSE,
  addtot = FALSE,
  na_str = NULL
)

Arguments

Value

A object Desc contains an intermediate data with long form for post-processing and final data with wide form for presentation.

Note

By default, the each category is sorted based on the corresponding factor level of var variable. If the variable is not a factor, that will be sorted alphabetically.

Examples

data(adsl_sub)

# Count the age group by treatment with 'xx (xx.x%)' format
adsl_sub %>%
  descfreq(
    var = "AGEGR1",
    bygroup = "TRTP",
    format = "xx (xx.x%)"
  )

# Count the race by treatment with 'xx (xx.xx)' format and replace NA with '0'
adsl_sub %>%
  descfreq(
    var = "RACE",
    bygroup = "TRTP",
    format = "xx (xx.xx)",
    na_str = "0"
  )

# Count the sex by treatment adding total column
adsl_sub %>%
  descfreq(
    var = "SEX",
    bygroup = "TRTP",
    format = "xx (xx.x%)",
    addtot = TRUE
  )

# Count multiple variables by treatment and sort category by corresponding factor levels
adsl_sub %>%
  dplyr::mutate(
    AGEGR1 = factor(AGEGR1, levels = c("<65", "65-80", ">80")),
    SEX = factor(SEX, levels = c("M", "F")),
    RACE = factor(RACE, levels = c(
      "WHITE", "AMERICAN INDIAN OR ALASKA NATIVE",
      "BLACK OR AFRICAN AMERICAN"
    ))
  ) %>%
  descfreq(
    var = c("AGEGR1", "SEX", "RACE"),
    bygroup = "TRTP",
    format = "xx (xx.x%)",
    addtot = TRUE,
    na_str = "0"
  )

Description

Create a summary table with a set of descriptive statistics for one or more variables by one group, as well as a total column if necessary.

Usage

descvar(
  data,
  var,
  bygroup,
  stats = getOption("mcradds.stats.default"),
  autodecimal = TRUE,
  decimal = 1,
  addtot = FALSE,
  .perctype = 2
)

Arguments

Value

A object Desc contains an intermediate data with long form for post-processing and final data with wide form for presentation.

Note

The decimal precision is based on two aspects, one is the original precision from the variable or the decimal argument, and the second is the common use that has been defined in getOption("mcradds.precision.default"). So if you want to change the second decimal precision, you can alter it manually with option().

Examples

data(adsl_sub)

# Compute the default statistics of AGE by TRTP group
adsl_sub %>%
  descvar(
    var = "AGE",
    bygroup = "TRTP"
  )

# Compute the specific statistics of BMI by TRTP group, adding total column
adsl_sub %>%
  descvar(
    var = "BMIBL",
    bygroup = "TRTP",
    stats = c("N", "MEANSD", "MEDIAN", "RANGE", "IQR"),
    addtot = TRUE
  )

# Set extra decimal to define precision
adsl_sub %>%
  descvar(
    var = "BMIBL",
    bygroup = "TRTP",
    stats = c("N", "MEANSD", "MEDIAN", "RANGE", "IQR"),
    autodecimal = FALSE,
    decimal = 2,
    addtot = TRUE
  )

# Set multiple variables together
adsl_sub %>%
  descvar(
    var = c("AGE", "BMIBL", "HEIGHTBL"),
    bygroup = "TRTP",
    stats = c("N", "MEANSD", "MEDIAN", "RANGE", "IQR"),
    autodecimal = TRUE,
    addtot = TRUE
  )

Description

Creates a 2x2 contingency table from the data frame or matrix for the qualitative performance and reader precision of downstream analysis.

Usage

diagTab(
  formula = ~.,
  data,
  bysort = NULL,
  dimname = NULL,
  levels = NULL,
  rep = FALSE,
  across = NULL
)

Arguments

Value

A object MCTab contains the 2x2 contingency table.

Note

To be attention that if you would like to generate the 2x2 contingency table for reproducibility analysis, the original data should be long structure and using the corresponding formula.

See Also

Summary() for object to calculate diagnostic accuracy criteria.

Examples

# For qualitative performance with wide data structure
data("qualData")
qualData %>% diagTab(formula = ~ CandidateN + ComparativeN)
qualData %>%
  diagTab(
    formula = ~ CandidateN + ComparativeN,
    levels = c(1, 0)
  )

# For qualitative performance with long data structure
dummy <- data.frame(
  id = c("1001", "1001", "1002", "1002", "1003", "1003"),
  value = c(1, 0, 0, 0, 1, 1),
  type = c("Test", "Ref", "Test", "Ref", "Test", "Ref")
)
dummy %>%
  diagTab(
    formula = type ~ value,
    bysort = "id",
    dimname = c("Test", "Ref"),
    levels = c(1, 0)
  )

# For Between-Reader precision performance
data("PDL1RP")
reader <- PDL1RP$btw_reader
reader %>%
  diagTab(
    formula = Reader ~ Value,
    bysort = "Sample",
    levels = c("Positive", "Negative"),
    rep = TRUE,
    across = "Site"
  )

Description

Help function detects the potential outlier with Dixon method, following the rules of EP28A3 and NMPA guideline for establishment of reference range.

Usage

dixon_outlier(x)

Arguments

Value

A list contains outliers and vector without outliers.

Examples

x <- c(13.6, 44.4, 45.9, 11.9, 41.9, 53.3, 44.7, 95.2, 44.1, 50.7, 45.2, 60.1, 89.1)
dixon_outlier(x)

Description

Perform Rosner's generalized extreme Studentized deviate (ESD) test, which assumes that the distribution is normal (Gaussian), can be used when the number of outliers is unknown, and becomes more robust as the number of samples increases.

Usage

ESD_test(x, alpha = 0.05, h = 5)

Arguments

Value

A list class containing the results of the ESD test.

• stat a data frame contains the several statistics about ESD test that includes the index(i), Mean, SD, raw data(x), the location(Obs) in x, ESD statistics(ESDi), Lambda and Outliers(TRUE or FALSE).

• ord a vector with the order index of outliers that is equal to Obs in the stat data frame.

Note

The algorithm for determining the number of outliers is as follows:

• Compare ESDi with Lambda. If ESDi > Lambda then the observations will be regards as outliers.

• The order index corresponds to the available x data that has been removed the missing (NA) value.

• As we should compare if the ESD(h) and ESD(h+1) are equal, the h+1 ESD values will be shown. If they are identical, both of them can not be regarded as outliers.

References

CLSI EP09A3 Appendix B. Detecting Aberrant Results (Outliers).

Examples

data("platelet")
res <- blandAltman(x = platelet$Comparative, y = platelet$Candidate)
ESD_test(x = res@stat$relative_diff)

Description

A helper function to find the lambda for all potential outliers in each iteration.

Usage

esd.critical(alpha, N, i)

Arguments

Value

a lambda value calculated from the formula.

Examples

esd.critical(alpha = 0.05, N = 100, i = 1)

Description

Provides a concise summary of the content of MCTab objects. Computes sensitivity, specificity, positive and negative predictive values and positive and negative likelihood ratios for a diagnostic test with reference/gold standard. Computes positive/negative percent agreement, overall percent agreement and Kappa when the new test is evaluated by comparison to a non-reference standard. Computes average positive/negative agreement when the both tests are all not the reference, such as paired reader precision.

Usage

getAccuracy(object, ...)

## S4 method for signature 'MCTab'
getAccuracy(
  object,
  ref = c("r", "nr", "bnr"),
  alpha = 0.05,
  r_ci = c("wilson", "wald", "clopper-pearson"),
  nr_ci = c("wilson", "wald", "clopper-pearson"),
  bnr_ci = "bootstrap",
  bootCI = c("perc", "norm", "basic", "stud", "bca"),
  nrep = 1000,
  rng.seed = NULL,
  digits = 4,
  ...
)

Arguments

Value

A data frame contains the qualitative diagnostic accuracy criteria with three columns for estimated value and confidence interval.

• sens: Sensitivity refers to how often the test is positive when the condition of interest is present.

• spec: Specificity refers to how often the test is negative when the condition of interest is absent.

• ppv: Positive predictive value refers to the percentage of subjects with a positive test result who have the target condition.

• npv: Negative predictive value refers to the percentage of subjects with a negative test result who do not have the target condition.

• plr: Positive likelihood ratio refers to the probability of true positive rate divided by the false negative rate.

• nlr: Negative likelihood ratio refers to the probability of false positive rate divided by the true negative rate.

• ppa: Positive percent agreement, equals to sensitivity when the candidate method is evaluated by comparison with a comparative method, not reference/gold standard.

• npa: Negative percent agreement, equals to specificity when the candidate method is evaluated by comparison with a comparative method, not reference/gold standard.

• opa: Overall percent agreement.

• kappa: Cohen's kappa coefficient to measure the level of agreement.

• apa: Average positive agreement refers to the positive agreements and can be regarded as weighted ppa.

• ana: Average negative agreement refers to the negative agreements and can be regarded as weighted npa.

Examples

# For qualitative performance
data("qualData")
tb <- qualData %>%
  diagTab(
    formula = ~ CandidateN + ComparativeN,
    levels = c(1, 0)
  )
getAccuracy(tb, ref = "r")
getAccuracy(tb, ref = "nr", nr_ci = "wilson")

# For Between-Reader precision performance
data("PDL1RP")
reader <- PDL1RP$btw_reader
tb2 <- reader %>%
  diagTab(
    formula = Reader ~ Value,
    bysort = "Sample",
    levels = c("Positive", "Negative"),
    rep = TRUE,
    across = "Site"
  )
getAccuracy(tb2, ref = "bnr")
getAccuracy(tb2, ref = "bnr", rng.seed = 12306)

Description

A copy from mcr::getCoefficients in mcr package

Usage

getCoefficients(...)

Arguments

Examples

data(platelet)
fit <- mcreg(
  x = platelet$Comparative, y = platelet$Candidate,
  method.reg = "Deming", method.ci = "jackknife"
)
getCoefficients(fit)

Description

Detect the potential outliers from the absolute and relative differences in BAsummary object with 4E and ESD method.

Usage

getOutlier(object, ...)

## S4 method for signature 'BAsummary'
getOutlier(
  object,
  method = c("ESD", "4E"),
  difference = c("abs", "rel"),
  alpha = 0.05,
  h = 5
)

Arguments

Value

A list contains the statistics results (stat), outliers' ord id (ord), sample id (sid), matrix with outliers (outmat) and matrix without outliers (rmmat).

Note

Bland-Altman analysis is used as the input data regardless of the 4E and ESD method because it's necessary to determine the absolute and relative differences beforehand. For the 4E method, both of the absolute and relative differences are required to be define, and the bias exceeds the 4 fold of the absolute and relative differences. However for the ESD method, only one of them is necessary (the latter is more recommended), and the bias needs to meet the ESD test.

Examples

data("platelet")
# Using `blandAltman` function with default arguments
ba <- blandAltman(x = platelet$Comparative, y = platelet$Candidate)
getOutlier(ba, method = "ESD", difference = "rel")

# Using sample id as input
ba2 <- blandAltman(x = platelet$Comparative, y = platelet$Candidate, sid = platelet$Sample)
getOutlier(ba2, method = "ESD", difference = "rel")

# Using `blandAltman` function when the `tyep2` is 2 with `X vs. (Y-X)/X` difference
ba3 <- blandAltman(x = platelet$Comparative, y = platelet$Candidate, type2 = 4)
getOutlier(ba3, method = "ESD", difference = "rel")

# Using "4E" as the method input
ba4 <- blandAltman(x = platelet$Comparative, y = platelet$Candidate)
getOutlier(ba4, method = "4E")

Description

This data set consists of the Glucose intermediate precision data in the CLSI EP05-A3 guideline.

Usage

glucose

Format

A glucose data set contains 80 observations and 3 variables.

day

day number

run

run number

value

measurement value

Source

CLSI-EP05A3 Table A1. Glucose Precision Evaluation Measurements (mg/dL) is cited in this data set.

References

EP05A3: Evaluation of Precision of Quantitative Measurement Procedures.

Description

Helper function computes the difference with specific type.

Usage

h_difference(x, y, type)

Arguments

Value

a matrix contains the x and y measurement data and corresponding difference.

Examples

h_difference(x = c(1.1, 1.2, 1.5), y = c(1.2, 1.3, 1.4), type = 5)

Description

Helper function factor inputs in order of appearance, or per the levels that you provide.

Usage

h_factor(df, var, levels = NULL, ...)

Arguments

Value

A factor variable

Examples

df <- data.frame(a = c("aa", "a", "aa"))
h_factor(df, var = "a")
h_factor(df, var = "a", levels = c("aa", "a"))

Description

Help function to format the count and percent into one string.

Usage

h_fmt_count_perc(cnt, perc = NULL, format, ...)

Arguments

Value

A character vector of formatted counts and percents.

Examples

h_fmt_count_perc(cnt = c(5, 9, 12, 110, 0), format = "xx")
h_fmt_count_perc(
  cnt = c(5, 9, 12, 110, 0),
  perc = c(0.0368, 0.0662, 0.0882, 0.8088, 0),
  format = "xx (xx.x%)"
)

Description

Help function to format numeric data as strings and concatenate into a single character.

Usage

h_fmt_est(num1, num2, digits = c(2, 2), width = c(6, 6))

Arguments

Value

A single character.

See Also

h_fmt_num()

Examples

h_fmt_est(num1 = 3.14, num2 = 3.1415, width = c(4, 4))

Description

Help function to format numeric data with formatC function.

Usage

h_fmt_num(x, digits, width = digits + 4)

Arguments

Value

A character object with specific digits and width.

See Also

formatC()

Examples

h_fmt_num(pi * 10^(-2:2), digits = 2, width = 6)

Description

Help function to format numeric data as strings and concatenate into a single character range.

Usage

h_fmt_range(num1, num2, digits = c(2, 2), width = c(6, 6))

Arguments

Value

A single character.

See Also

h_fmt_num()

Examples

h_fmt_range(num1 = 3.14, num2 = 3.14, width = c(4, 4))

Description

Help function summarizes the statistics as needed.

Usage

h_summarize(x, conf.level = 0.95)

Arguments

Value

a verctor contains several statistics, such as n, mean, median, min, max, q25, q75, sd, se, limit of agreement of limit and confidence interval .

Examples

h_summarize(1:50)

Description

This data set consists the measurements of low-density lipoprotein (LDL), oxidized low-density lipoprotein (OxLDL) and the corresponding diagnosis. OxLDL is thought to be the active molecule in the process of atherosclerosis, so its proponents believe that its serum concentration should provide more accurate risk stratification than the traditional LDL assay.

Usage

ldlroc

Format

A ldlroc data set contains 50 observations and 3 variables.

Diagnosis

the diagnosis, 1 represents a subject has the disease or condition of interest is present, 0 is absent

OxLDL

oxidized low-density lipoprotein(OxLDL) measurement value

LDL

low-density lipoprotein(LDL) measurement value

Source

CLSI-EP24A2 Table D1. OxLDL and LDL Assay Values (in U/L) for 50 Subjects.

References

EP24A2 Assessment of the Diagnostic Accuracy of Laboratory Tests Using Receiver Operating Characteristic Curves.

Description

A copy from mcr::mcreg in mcr package

Usage

mcreg(...)

Arguments

Value

A regression fit model.

See Also

mcr::mcreg()

Examples

data(platelet)
fit <- mcreg(
  x = platelet$Comparative, y = platelet$Candidate,
  method.reg = "Deming", method.ci = "jackknife"
)
printSummary(fit)
getCoefficients(fit)

Description

The MCTab class serves as the store for 2x2 contingency table

Usage

MCTab(data, tab, levels)

Arguments

Value

An object of class MCTab.

Slots

data

data

tab

candidate

levels

levels

Description

This data shows the rank number for computing the confidence interval of nonparametric reference limit when the samples within 119-1000 values. But the reference interval must be 95% and the confidence interval is 90%.

Usage

nonparRanks

Format

A nonparRanks data set contains 882 observations and 3 variables.

SampleSize

sample size

Lower

lower rank

Upper

upper rank

Source

CLSI-EP28A3 Table 8. is cited in this data set.

References

EP28-A3c: Defining, Establishing, and Verifying Reference Intervals in the Clinical Laboratory.

Description

This nonparametric method is used to calculate the reference interval when the distribution is skewed and the sample size is above to 120 observations.

Usage

nonparRI(x, ind = 1:length(x), conf.level = 0.95)

Arguments

Value

a vector of nonparametric reference interval

Examples

data("calcium")
x <- calcium$Value
nonparRI(x)

Description

This dummy data set is from a PD-L1 HE stained study to estimate the reproducibility of one assay in determining the PD-L1 status of NSCLC tissue specimens. It contains three sub-data to compute the reproducibility within reader (one pathologists, also called reader here, scores one specimen three times), between reader (three readers scores the same specimen) and between site (one reader in three sites scores the same specimens). These data sets don't have the reference for the each score so it can be only used in the pairwise comparison to calculate the APA, ANA and OPA which don't reply on the reference.

Usage

PDL1RP

Format

A PDL1RP data set contains 3 sub set, each sub set includes 150 specimens, 450 observations and 4 variables.

Sample

Sample id

Site

Site id

Order

Order of reader scoring

Reader

Reader id, the first character represents the site id, and the second character is the reader number

Value

Result of scoring, Positive or Negative

Description

Adjust the cor.test function so that it can define the specific H0 as per your request, that is based on Fisher's Z transformation of the correlation.

Usage

pearsonTest(
  x,
  y,
  h0 = 0,
  conf.level = 0.95,
  alternative = c("two.sided", "less", "greater"),
  ...
)

Arguments

Value

a named vector contains correlation coefficient (cor), confidence interval(lowerci and upperci), Z statistic (Z) and p-value (pval)

References

NCSS correlation document

See Also

cor.test() to see the detailed arguments.

Examples

x <- c(44.4, 45.9, 41.9, 53.3, 44.7, 44.1, 50.7, 45.2, 60.1)
y <- c(2.6, 3.1, 2.5, 5.0, 3.6, 4.0, 5.2, 2.8, 3.8)
pearsonTest(x, y, h0 = 0.5, alternative = "greater")

Description

This example platelet can be used to create a data set comparing Platelet results from two analyzers in cells.

Usage

platelet

Format

A platelet data set contains 120 observations and 3 variables.

Sample

Sample id

Comparative

Measurements from comparative analyzer

Candidate

Measurements from candidate analyzer

Source

CLSI-EP09 A3 Appendix H, Table H2 is cited in this data set.

See Also

From mcr package, mcr::creatinine data set contains data with with serum and plasma creatinin measurements in mg/dL for each sample.

Description

A copy from mcr::printSummary in mcr package

Usage

printSummary(...)

Arguments

Examples

data(platelet)
fit <- mcreg(
  x = platelet$Comparative, y = platelet$Candidate,
  method.reg = "Deming", method.ci = "jackknife"
)
printSummary(fit)

Description

This simulated data qualData can be used to calculate the qualitative performance such as sensitivity and specificity.

Usage

qualData

Format

A qualData data set contains 200 observations and 3 variables.

Sample

Sample id

ComparativeN

Measurements from comparative analyzer with 1=positive and 0=negative

CandidateN

Measurements from candidate analyzer with 1=positive and 0=negative

See Also

platelet that contains quantitative data comparing platelet results from two analyzers.

Description

The RefInt class serves as the store for results in reference Interval calculation.

Usage

RefInt(call, method, n, data, outlier, refInt, confInt)

Arguments

Value

An object of class RefInt.

Slots

call

call

method

method

n

n

data

data

outlier

outlier

refInt

refInt

confInt

confInt

Description

This function is used to establish the reference interval for target population with parametric, non-parametric and robust methods that follows the CLSI-EP28A3 and NMPA guideline. In additional, it also provides the corresponding confidence interval for lower/upper reference limit if needed. Given that outliers should be identified beforehand, Tukey and Dixon methods can be applied depending on distribution of the data.

Usage

refInterval(
  x,
  out_method = c("doxin", "tukey"),
  out_rm = FALSE,
  RI_method = c("parametric", "nonparametric", "robust"),
  CI_method = c("parametric", "nonparametric", "boot"),
  refLevel = 0.95,
  bootCI = c("perc", "norm", "basic", "stud", "bca"),
  confLevel = 0.9,
  rng.seed = NULL,
  tol = 1e-06,
  R = 10000
)

Arguments

Value

A RefInt object contains relevant results in establishing of reference interval.

Note

There are some conditions of use to be aware of:

• If parametric method is used to calculate reference interval, confidence interval should be the same method as well.

• If non-parametric method is used to calculate the reference interval and the sample size is up to 120 observations, the non-parametric is suggested for confidence interval. Otherwise if the sample size is below to 120, the bootstrap method is the better choice. Beside the non-parametric method for confidence interval only allows the refLevel=0.95 and confLevel=0.9 arguments, if not the bootstrap methods will be used automatically.

• If robust method is used to calculate the reference interval, the method for confidence interval must be bootstrap.

Examples

data("calcium")
x <- calcium$Value
refInterval(x, RI_method = "parametric", CI_method = "parametric")
refInterval(x, RI_method = "nonparametric", CI_method = "nonparametric")
refInterval(x, RI_method = "robust", CI_method = "boot", R = 1000)

Description

This robust method is used to calculate the reference interval on small sample size (below to 120 observations).

Usage

robustRI(x, ind = 1:length(x), conf.level = 0.95, tol = 1e-06)

Arguments

Value

a vector of robust reference interval

References

This robust algorithm is referring to CLSI document EP28A3.

Examples

# This example data is taken from EP28A3 Appendix B. to ensure the result is in accordance.
x <- c(8.9, 9.2, rep(9.4, 2), rep(9.5, 3), rep(9.6, 4), rep(9.7, 5), 9.8, rep(9.9, 2), 10.2)
robustRI(x)

Description

The SampleSize class serves as the store for results and parameters in sample size calculation.

Usage

SampleSize(call, method, n, param)

Arguments

Value

An object of class SampleSize.

Slots

call

call

method

method

n

n

param

param

Description

A show method that displays essential information of objects.

Usage

## S4 method for signature 'SampleSize'
show(object)

## S4 method for signature 'MCTab'
show(object)

## S4 method for signature 'BAsummary'
show(object)

## S4 method for signature 'RefInt'
show(object)

## S4 method for signature 'tpROC'
show(object)

## S4 method for signature 'Desc'
show(object)

Arguments

Value

None (invisible NULL), only used for the side effect of printing to the console.

Examples

# Sample zie calculation
size_one_prop(p1 = 0.95, p0 = 0.9, alpha = 0.05, power = 0.8)
size_ci_corr(r = 0.9, lr = 0.85, alpha = 0.025, alternative = "greater")

# Get 2x2 Contingency Table
qualData %>% diagTab(formula = ~ CandidateN + ComparativeN)

# Bland-Altman analysis
data("platelet")
blandAltman(x = platelet$Comparative, y = platelet$Candidate)

# Reference Interval
data("calcium")
refInterval(x = calcium$Value, RI_method = "nonparametric", CI_method = "nonparametric")

# Comparing the Paired ROC when Non-inferiority margin <= -0.1
data("ldlroc")
aucTest(
  x = ldlroc$LDL, y = ldlroc$OxLDL, response = ldlroc$Diagnosis,
  method = "non-inferiority", h0 = -0.1
)
data(adsl_sub)

# Count multiple variables by treatment
adsl_sub %>%
  descfreq(
    var = c("AGEGR1", "SEX", "RACE"),
    bygroup = "TRTP",
    format = "xx (xx.x%)",
    addtot = TRUE,
    na_str = "0"
  )

# Summarize multiple variables by treatment
adsl_sub %>%
  descvar(
    var = c("AGE", "BMIBL", "HEIGHTBL"),
    bygroup = "TRTP",
    stats = c("N", "MEANSD", "MEDIAN", "RANGE", "IQR"),
    autodecimal = TRUE,
    addtot = TRUE
  )

Description

This function performs sample size computation for testing Pearson's correlation when a lower confidence interval is provided.

Usage

size_ci_corr(
  r,
  lr,
  alpha = 0.05,
  interval = c(10, 1e+05),
  tol = 1e-05,
  alternative = c("two.sided", "less", "greater")
)

Arguments

Value

an object of size class that contains the sample size and relevant parameters.

References

Fisher (1973, p. 199).

See Also

size_one_prop() size_ci_one_prop() size_corr()

Examples

size_ci_corr(r = 0.9, lr = 0.85, alpha = 0.025, alternative = "greater")

Description

This function performs sample size computation for testing a given lower confidence interval of one proportion with the using of the Simple Asymptotic(Wald), Wilson score, clopper-pearson and other methods.

Usage

size_ci_one_prop(
  p,
  lr,
  alpha = 0.05,
  interval = c(1, 1e+05),
  tol = 1e-05,
  alternative = c("two.sided", "less", "greater"),
  method = c("simple-asymptotic", "wilson", "wald", "clopper-pearson")
)

Arguments

Value

an object of size class that contains the sample size and relevant parameters.

References

Newcombe, R. G. 1998. 'Two-Sided Confidence Intervals for the Single Proportion: Comparison of Seven Methods.' Statistics in Medicine, 17, pp. 857-872.

See Also

size_one_prop() size_corr() size_ci_corr()

Examples

size_ci_one_prop(p = 0.85, lr = 0.8, alpha = 0.05, method = "wilson")
size_ci_one_prop(p = 0.85, lr = 0.8, alpha = 0.05, method = "simple-asymptotic")
size_ci_one_prop(p = 0.85, lr = 0.8, alpha = 0.05, method = "wald")

Description

This function performs sample size computation for testing Pearson's correlation, using uses Fisher's classic z-transformation to normalize the distribution of Pearson's correlation coefficient.

Usage

size_corr(
  r1,
  r0,
  alpha = 0.05,
  power = 0.8,
  alternative = c("two.sided", "less", "greater")
)

Arguments

Value

an object of size class that contains the sample size and relevant parameters.

References

Fisher (1973, p. 199).

See Also

size_one_prop() size_ci_one_prop() size_ci_corr()

Examples

size_corr(r1 = 0.95, r0 = 0.9, alpha = 0.025, power = 0.8, alternative = "greater")

Description

This function performs sample size computation for testing one proportion in accordance with Chinese NMPA's IVD guideline.

Usage

size_one_prop(
  p1,
  p0,
  alpha = 0.05,
  power = 0.8,
  alternative = c("two.sided", "less", "greater")
)

Arguments

Value

an object of size class that contains the sample size and relevant parameters.

References

Chinese NMPA's IVD technical guideline.

See Also

size_ci_one_prop() size_corr() size_ci_corr()

Examples

size_one_prop(p1 = 0.95, p0 = 0.9, alpha = 0.05, power = 0.8)

Description

Providing the confidence interval of Spearman's rank correlation by Bootstrap, and define the specific H0 as per your request, that is based on Fisher's Z transformation of the correlation but with the variance recommended by Bonett and Wright (2000), not the same as Pearson's.

Usage

spearmanTest(
  x,
  y,
  h0 = 0,
  conf.level = 0.95,
  alternative = c("two.sided", "less", "greater"),
  nrep = 1000,
  rng.seed = NULL,
  ...
)

Arguments

Value

a named vector contains correlation coefficient (cor), confidence interval(lowerci and upperci), Z statistic (Z) and p-value (pval)

References

NCSS correlation document

See Also

cor.test() boot::boot() to see the detailed arguments.

Examples

x <- c(44.4, 45.9, 41.9, 53.3, 44.7, 44.1, 50.7, 45.2, 60.1)
y <- c(2.6, 3.1, 2.5, 5.0, 3.6, 4.0, 5.2, 2.8, 3.8)
spearmanTest(x, y, h0 = 0.5, alternative = "greater")

Description

The tpROC class serves as the store for results in testing the AUC of paired two-sample assays.

Usage

tpROC(testROC, refROC, method, H0, stat)

Arguments

Value

An object of class tpROC.

Slots

testROC

testROC

refROC

refROC

method

method

stat

stat

Description

Help function detects the potential outlier with Tukey method where the number is below Q1-1.5*IQR and above Q3+1.5*IQR.

Usage

tukey_outlier(x)

Arguments

Value

A list contains outliers and vector without outliers.

Examples

x <- c(13.6, 44.4, 45.9, 14.9, 41.9, 53.3, 44.7, 95.2, 44.1, 50.7, 45.2, 60.1, 89.1)
tukey_outlier(x)

Description

A copy from VCA::VCAinference in VCA package

Usage

VCAinference(...)

Arguments

Value

object of VCAinference contains a series of statistics.

See Also

VCA::VCAinference()

Examples

data(glucose)
fit <- anovaVCA(value ~ day / run, glucose)
VCAinference(fit)