Type:	Package
Title:	Statistics for International Large-Scale Assessments (ILSA)
Version:	0.4.0
Maintainer:	Andrés Christiansen <andres.christiansen@iea-hamburg.de>
Description:	Calculates point estimates and standard errors using replicate weights and plausible values for International Large-Scale Assessments (ILSA), including: means, proportions, quantiles, correlations, singlelevel regressions, and multilevel regressions.
Encoding:	UTF-8
LazyData:	true
LazyDataCompression:	xz
RoxygenNote:	7.3.2
Suggests:	wCorr, lme4, MuMIn, WeMix
Depends:	R (≥ 3.5.0)
License:	GPL (≥ 3)
NeedsCompilation:	no
Packaged:	2025-07-15 23:28:09 UTC; andreschristiansen
Author:	Andrés Christiansen [aut, cre], Andrés Strello [ctb]
Repository:	CRAN
Date/Publication:	2025-07-15 23:40:08 UTC

ILSA information

Description

ILSA information

Survey Weighted Mixed-Effects Models with Plausible Values

Description

Fits a linear mixed-effects model using mix and plausible values.

Usage

WeMixPV(formula, data = NULL, weights = NULL, pvs, relatedpvs = TRUE, ...)

Arguments

Value

a list.

Examples

# Prepare data weights
repdata2 <- repdata
repdata2$wt1 <- repdata2$wt # weight level 1
repdata2$wt2 <- 1 # weight level 2


# Null model - with PVs
## Named list, with element names matching formula variables
pvs = list(MATH = paste0("Math",1:5))


m1 <- WeMixPV(formula = MATH ~ 1 + (1|GROUP), # Intercept varies across GROUP
             pvs = pvs, # Named list
             data = repdata2, # Data frame
             weights = c("wt1","wt2")) # Weights vector
m1

## Fixed effects
m1$fixef

## Random effects
m1$ranef

## Models for each PV
summary(m1$models)

# Multiple regression
## Named list, with element names matching formula variables
pvs = list(MATH = paste0("Math",1:5))


m2 <- WeMixPV(formula = MATH ~ 1 + GENDER + SES + schoolSES + (1|GROUP),
             pvs = pvs, # Named list
             data = repdata2, # Data frame
             weights = c("wt1","wt2")) # Weights vector
m2

Centering

Description

Centers a vector, a matrix or a data frame to the grand mean or the group mean.

Usage

center(X, group = NULL, grandmean = NULL, groupmean = NULL, wt = NULL)

grand.mean(x, wt = NULL)

group.mean(x, group, wt = NULL)

getgroup.mean(x, group, wt = NULL)

Arguments

Value

a data frame, or a vector.

Examples

# Less data for shorter example
repdata2 <- repdata[1:10,c(1:3,6:10,51)]

### One variable ----

# grand-mean
grand.mean(repdata2$item01)
grand.mean(repdata2$item01,wt = repdata2$wt)

# group-mean
group.mean(repdata2$item01,group = repdata2$GROUP)
group.mean(repdata2$item01,group = repdata2$GROUP,wt = repdata2$wt)

### More than one variable with the same rule ----

# grand-mean
grand.mean(repdata2[,4:8])
grand.mean(repdata2[,4:8],wt = repdata2$wt)

# group-mean
group.mean(repdata2[,4:8],group = repdata2$GROUP)
group.mean(repdata2[,4:8],group = repdata2$GROUP,wt = repdata2$wt)

### More than one variable with different rules ----
center(repdata2, group = repdata2$GROUP, grandmean = 4:5, groupmean = 6:8, wt = repdata2$wt)
center(repdata2, group = repdata2$GROUP, grandmean = 6:8, groupmean = 4:5, wt = repdata2$wt)

center(repdata2, group = repdata2$GROUP, wt = repdata2$wt,
       grandmean = paste0("item0",1:3), groupmean = paste0("item0",4:5))
center(repdata2, group = repdata2$GROUP, wt = repdata2$wt,
       grandmean = paste0("item0",4:5), groupmean = paste0("item0",1:3))

Intraclass Correlation Coefficient

Description

Calculates the intraclass correlation coefficient (ICC) fitting a linear mixed-effects model using lmer.

Usage

icc(x, PV = FALSE, group, data, weights = NULL, ...)

Arguments

Value

a numeric value or a list.

Examples

# ICC of one variable
icc(x = "Math1",group = "GROUP", weights = repdata$wt, data = repdata)


# ICC of more than one variable
icc(x = c("Math1","Math2","Math3","Math4","Math5","SES"),
    group = "GROUP", weights = repdata$wt, data = repdata)


# ICC of PVs
icc(x = c("Math1","Math2","Math3","Math4","Math5"), PV = TRUE,
    group = "GROUP", weights = repdata$wt, data = repdata)

Linear Mixed-Models with Plausible Values

Description

Fits a linear mixed-effects model using lmer and plausible values.

Usage

lmerPV(
  formula,
  data = NULL,
  weights = NULL,
  pvs,
  relatedpvs = TRUE,
  grandmean = NULL,
  groupmean = NULL,
  group = NULL,
  nullmodel = FALSE,
  ...
)

Arguments

Value

a list.

Examples

# Null model - with PVs
## Named list, with element names matching formula variables
pvs = list(MATH = paste0("Math",1:5))


m1 <- lmerPV(formula = MATH ~ 1 + (1|GROUP), # Intercept varies across GROUP
      pvs = pvs, # Named list
      data = repdata, # Data frame
      weights = repdata$wt) # Weights vector
m1

## Fixed effects
m1$fixef

## Random effects
m1$ranef

## Models for each PV
summary(m1$models)

# Multiple regression
## Named list, with element names matching formula variables
pvs = list(MATH = paste0("Math",1:5))


m2 <- lmerPV(formula = MATH ~ 1 + GENDER + SES + schoolSES + (1|GROUP),
             pvs = pvs, # Named list
             data = repdata, # Data frame
             weights = repdata$wt) # Weights vector
m2

# Multiple regression with grandmean centering
## Named list, with element names matching formula variables
pvs = list(MATH = paste0("Math",1:5))


m3 <- lmerPV(formula = MATH ~ 1 + GENDER + SES + schoolSES + (1|GROUP),
             pvs = pvs, # Named list
             data = repdata, # Data frame
             weights = repdata$wt,
             grandmean = c("SES","schoolSES"))
m3

# Multiple regression with groupmean centering
## Named list, with element names matching formula variables
pvs = list(MATH = paste0("Math",1:5))


m4 <- lmerPV(formula = MATH ~ 1 + GENDER + SES + schoolSES + (1|GROUP),
             pvs = pvs, # Named list
             data = repdata, # Data frame
             weights = repdata$wt,
             grandmean = "schoolSES",
             groupmean = "SES",
             group = repdata$GROUP)
m4

My Wrapper Function

Description

My Wrapper Function

Usage

myfunc(x, method = formals(repse)$method, setup = formals(repse)$setup, ...)

Arguments

Value

Description of return value

Creation of Replicate Weights

Description

Creates replicate weights given jackknife replicates and jackknife zones.

Usage

repcreate(df, wt, jkzone, jkrep, repwtname = "RWT", reps = NULL, method)

repcreateILSA(study, year, df, repwtname = "RWT")

Arguments

Value

a data frame.

Examples

head(repdata)

# Creation of replicate weights
RW <- repcreate(df = repdata, # the data frame with all the information
                 wt = "wt", # the total weights column name
                 jkzone = "jkzones", # the jkzones column name
                 jkrep = "jkrep", # the jkreps column name
                 repwtname = "REPWT", # the desired name for the rep weights
                 reps = 50, # the number of replications
                 method = "ICILS") # the name of the method aka the study name

head(RW)

Simulated data with 5000 cases

Description

Simulated data with 5000 cases

Generalized Linear Models with Replicate Weights

Description

Fits a generalized linear model using glm for replicate weights. For a detailed explanation on how the standard errors are estimated see repse.

Usage

repglm(
  formula,
  family = stats::gaussian,
  pvs = NULL,
  relatedpvs = TRUE,
  quiet = FALSE,
  summarize = TRUE,
  setup = NULL,
  df,
  wt,
  repwt,
  group = NULL,
  exclude = NULL,
  na.action = getOption("na.action"),
  method
)

Arguments

Value

a list with the standard errors and the total weights models.

Examples

# Less data for shorter example
repdata2 <- repdata[1:1000,]

RW <- repcreate(df = repdata2, # the data frame with all the information
                 wt = "wt", # the total weights column name
                 jkzone = "jkzones", # the jkzones column name
                 jkrep = "jkrep", # the jkreps column name
                 repwtname = "REPWT", # the desired name for the rep weights
                 reps = 50, # the number of replications
                 method = "ICILS") # the name of the method aka the study name

### No groups ----

# Simple regression - weights within df
replm(formula = Math1 ~ 1 + GENDER,
      wt = "wt", # Name of total weight column within df
      repwt = "REPWT", # Common names of replicate weights within df
      df = cbind(repdata2,RW), # Data frame
      method = "ICILS") # the name of the method aka the study name

# Simple regression - weights as a separate data frame
replm(formula = Math1 ~ 1 + GENDER,
       wt = "wt", # Name of total weight column within df
       repwt = RW, # Data frame of weights
       df = repdata2, # Data frame
       method = "ICILS") # the name of the method aka the study name

# Multiple regression
replm(formula = Math1 ~ 1 + GENDER + Reading1,
       wt = "wt", # Name of total weight column within df
       repwt = RW, # Data frame of weights
       df = repdata2, # Data frame
       method = "ICILS") # the name of the method aka the study name

# Multiple regression - with PVs
## Named list, with element names matching formula variables
pvs = list(Math = paste0("Math",1:3))
pvs

replm(formula = Math ~ 1 + GENDER + Reading1, # Math1 now is "Math"
       wt = "wt", # Name of total weight column within df
       repwt = RW, # Data frame of weights
       df = repdata2, # Data frame
       pvs = pvs, # Named list
       method = "ICILS") # the name of the method aka the study name

# Multiple regression - with more than one related PV variable
## Named list, with element names matching formula variables
pvs = list(Math = paste0("Math",1:3),
           Reading = paste0("Reading",1:3))
pvs

replm(formula = Math ~ 1 + GENDER + Reading, # Reading1 now is "Reading"
       wt = "wt", # Name of total weight column within df
       repwt = RW, # Data frame of weights
       df = repdata2, # Data frame
       pvs = pvs, # Named list
       method = "ICILS") # the name of the method aka the study name

# Multiple regression - with more than UNrelated PV variables
## Named list, with element names matching formula variables
pvs = list(Math = paste0("Math",1:3),
           Reading = paste0("Reading",1:3))
pvs

replm(formula = Math ~ 1 + GENDER + Reading, # Reading1 now is "Reading"
       wt = "wt", # Name of total weight column within df
       repwt = RW, # Data frame of weights
       df = repdata2, # Data frame
       pvs = pvs, # Named list
       relatedpvs = FALSE, # Unrelated PVs
       method = "ICILS") # the name of the method aka the study name


### Groups ----

# Simple regression - weights within df
replm(formula = Math1 ~ 1 + GENDER,
      wt = "wt", # Name of total weight column within df
      repwt = "REPWT", # Common names of replicate weights within df
      df = cbind(repdata2,RW), # Data frame
      group = "GROUP",
      method = "ICILS") # the name of the method aka the study name

# Simple regression - weights as a separate data frame
replm(formula = Math1 ~ 1 + GENDER,
      wt = "wt", # Name of total weight column within df
      repwt = RW, # Data frame of weights
      df = repdata2, # Data frame
      group = "GROUP",
      method = "ICILS") # the name of the method aka the study name

# Multiple regression
replm(formula = Math1 ~ 1 + GENDER + Reading1,
      wt = "wt", # Name of total weight column within df
      repwt = RW, # Data frame of weights
      df = repdata2, # Data frame
      group = "GROUP",
      method = "ICILS") # the name of the method aka the study name

# Multiple regression - with PVs
## Named list, with element names matching formula variables
pvs = list(Math = paste0("Math",1:3))
pvs

replm(formula = Math ~ 1 + GENDER + Reading1, # Math1 now is "Math"
      wt = "wt", # Name of total weight column within df
      repwt = RW, # Data frame of weights
      df = repdata2, # Data frame
      pvs = pvs, # Named list
      group = "GROUP",
      method = "ICILS") # the name of the method aka the study name

# Multiple regression - with more than one related PV variable
## Named list, with element names matching formula variables
pvs = list(Math = paste0("Math",1:3),
           Reading = paste0("Reading",1:3))
pvs

replm(formula = Math ~ 1 + GENDER + Reading, # Reading1 now is "Reading"
      wt = "wt", # Name of total weight column within df
      repwt = RW, # Data frame of weights
      df = repdata2, # Data frame
      pvs = pvs, # Named list
      group = "GROUP",
      method = "ICILS") # the name of the method aka the study name

# Multiple regression - with UNrelated PV variables
## Named list, with element names matching formula variables
pvs = list(Math = paste0("Math",1:3),
           Reading = paste0("Reading",1:3))
pvs

replm(formula = Math ~ 1 + GENDER + Reading, # Reading1 now is "Reading"
      wt = "wt", # Name of total weight column within df
      repwt = RW, # Data frame of weights
      df = repdata2, # Data frame
      pvs = pvs, # Named list
      relatedpvs = FALSE, # Unrelated PVs
      group = "GROUP",
      method = "ICILS") # the name of the method aka the study name

Linear Models with Replicate Weights

Description

Fits a linear model using lm for replicate weights. For a detailed explanation on how the standard errors are estimated see repse.

Usage

replm(
  formula,
  pvs = NULL,
  relatedpvs = TRUE,
  quiet = FALSE,
  summarize = TRUE,
  setup = NULL,
  df,
  wt,
  repwt,
  group = NULL,
  exclude = NULL,
  na.action = getOption("na.action"),
  method
)

Arguments

Value

a list.

Examples

# Less data for shorter example
repdata2 <- repdata[1:1000,]

RW <- repcreate(df = repdata2, # the data frame with all the information
                 wt = "wt", # the total weights column name
                 jkzone = "jkzones", # the jkzones column name
                 jkrep = "jkrep", # the jkreps column name
                 repwtname = "REPWT", # the desired name for the rep weights
                 reps = 50, # the number of replications
                 method = "ICILS") # the name of the method aka the study name

### No groups ----

# Simple regression - weights within df
replm(formula = Math1 ~ 1 + GENDER,
      wt = "wt", # Name of total weight column within df
      repwt = "REPWT", # Common names of replicate weights within df
      df = cbind(repdata2,RW), # Data frame
      method = "ICILS") # the name of the method aka the study name

# Simple regression - weights as a separate data frame
replm(formula = Math1 ~ 1 + GENDER,
       wt = "wt", # Name of total weight column within df
       repwt = RW, # Data frame of weights
       df = repdata2, # Data frame
       method = "ICILS") # the name of the method aka the study name

# Multiple regression
replm(formula = Math1 ~ 1 + GENDER + Reading1,
       wt = "wt", # Name of total weight column within df
       repwt = RW, # Data frame of weights
       df = repdata2, # Data frame
       method = "ICILS") # the name of the method aka the study name

# Multiple regression - with PVs
## Named list, with element names matching formula variables
pvs = list(Math = paste0("Math",1:3))
pvs

replm(formula = Math ~ 1 + GENDER + Reading1, # Math1 now is "Math"
       wt = "wt", # Name of total weight column within df
       repwt = RW, # Data frame of weights
       df = repdata2, # Data frame
       pvs = pvs, # Named list
       method = "ICILS") # the name of the method aka the study name

# Multiple regression - with more than one related PV variable
## Named list, with element names matching formula variables
pvs = list(Math = paste0("Math",1:3),
           Reading = paste0("Reading",1:3))
pvs

replm(formula = Math ~ 1 + GENDER + Reading, # Reading1 now is "Reading"
       wt = "wt", # Name of total weight column within df
       repwt = RW, # Data frame of weights
       df = repdata2, # Data frame
       pvs = pvs, # Named list
       method = "ICILS") # the name of the method aka the study name

# Multiple regression - with more than UNrelated PV variables
## Named list, with element names matching formula variables
pvs = list(Math = paste0("Math",1:3),
           Reading = paste0("Reading",1:3))
pvs

replm(formula = Math ~ 1 + GENDER + Reading, # Reading1 now is "Reading"
       wt = "wt", # Name of total weight column within df
       repwt = RW, # Data frame of weights
       df = repdata2, # Data frame
       pvs = pvs, # Named list
       relatedpvs = FALSE, # Unrelated PVs
       method = "ICILS") # the name of the method aka the study name


### Groups ----

# Simple regression - weights within df
replm(formula = Math1 ~ 1 + GENDER,
      wt = "wt", # Name of total weight column within df
      repwt = "REPWT", # Common names of replicate weights within df
      df = cbind(repdata2,RW), # Data frame
      group = "GROUP",
      method = "ICILS") # the name of the method aka the study name

# Simple regression - weights as a separate data frame
replm(formula = Math1 ~ 1 + GENDER,
      wt = "wt", # Name of total weight column within df
      repwt = RW, # Data frame of weights
      df = repdata2, # Data frame
      group = "GROUP",
      method = "ICILS") # the name of the method aka the study name

# Multiple regression
replm(formula = Math1 ~ 1 + GENDER + Reading1,
      wt = "wt", # Name of total weight column within df
      repwt = RW, # Data frame of weights
      df = repdata2, # Data frame
      group = "GROUP",
      method = "ICILS") # the name of the method aka the study name

# Multiple regression - with PVs
## Named list, with element names matching formula variables
pvs = list(Math = paste0("Math",1:3))
pvs

replm(formula = Math ~ 1 + GENDER + Reading1, # Math1 now is "Math"
      wt = "wt", # Name of total weight column within df
      repwt = RW, # Data frame of weights
      df = repdata2, # Data frame
      pvs = pvs, # Named list
      group = "GROUP",
      method = "ICILS") # the name of the method aka the study name

# Multiple regression - with more than one related PV variable
## Named list, with element names matching formula variables
pvs = list(Math = paste0("Math",1:3),
           Reading = paste0("Reading",1:3))
pvs

replm(formula = Math ~ 1 + GENDER + Reading, # Reading1 now is "Reading"
      wt = "wt", # Name of total weight column within df
      repwt = RW, # Data frame of weights
      df = repdata2, # Data frame
      pvs = pvs, # Named list
      group = "GROUP",
      method = "ICILS") # the name of the method aka the study name

# Multiple regression - with UNrelated PV variables
## Named list, with element names matching formula variables
pvs = list(Math = paste0("Math",1:3),
           Reading = paste0("Reading",1:3))
pvs

replm(formula = Math ~ 1 + GENDER + Reading, # Reading1 now is "Reading"
      wt = "wt", # Name of total weight column within df
      repwt = RW, # Data frame of weights
      df = repdata2, # Data frame
      pvs = pvs, # Named list
      relatedpvs = FALSE, # Unrelated PVs
      group = "GROUP",
      method = "ICILS") # the name of the method aka the study name

Mean, Variance and Standard Deviation with Replicate Weights

Description

Estimates the mean, variance and standard deviation with replicate weights for a variable or a group of variables and for one or more populations. For a detailed explanation on how the standard errors are estimated see repse.

Usage

repmean(
  x,
  PV = FALSE,
  setup = NULL,
  repwt,
  wt,
  df,
  method,
  var = c("unbiased", "ML"),
  group = NULL,
  by = NULL,
  exclude = NULL,
  aggregates = c("pooled", "composite"),
  zones = NULL
)

Arguments

Value

a data frame or a list.

Examples

# Creation of replicate weights
RW <- repcreate(df = repdata, # the data frame with all the information
                 wt = "wt", # the total weights column name
                 jkzone = "jkzones", # the jkzones column name
                 jkrep = "jkrep", # the jkreps column name
                 repwtname = "REPWT", # the desired name for the rep weights
                 reps = 50, # the number of replications
                 method = "ICILS") # the name of the method aka the study name

### No groups ----

# One variable - weights within df
repmean(x = c("item01"),
        PV = FALSE,
        repwt = "REPWT", wt = "wt", df = cbind(repdata,RW),
        method = "ICILS",var = "ML",zones = "jkzones")

# One variable - weights as a separate data frame
repmean(x = c("item01"),
        PV = FALSE,
        repwt = RW, wt = "wt", df = repdata,
        method = "ICILS",var = "ML",zones = "jkzones")

# Multiple variables
repmean(x = c("item01","item02","item03"),
        PV = FALSE,
        repwt = RW, wt = "wt", df = repdata,
        method = "ICILS",var = "ML",zones = "jkzones")

# One PV variable
repmean(x = paste0("Math",1:5),
        PV = TRUE, # if set to TRUE, PVs will be treated as separate variables
        repwt = RW, wt = "wt", df = repdata,
        method = "ICILS",var = "ML",zones = "jkzones")

### Groups ----

# One variable
repmean(x = c("item01"),
        PV = FALSE,
        repwt = RW, wt = "wt", df = repdata,
        method = "ICILS",var = "ML",zones = "jkzones",
        group = "GROUP",
        exclude = "GR2") # GR2 will not be used for Pooled nor Composite

# Multiple variables
repmean(x = c("item01","item02","item03"),
        PV = FALSE,
        repwt = RW, wt = "wt", df = repdata,
        method = "ICILS",var = "ML",zones = "jkzones",
        group = "GROUP",
        exclude = "GR2") # GR2 will not be used for Pooled nor Composite

# One PV variable
repmean(x = paste0("Math",1:5),
        PV = TRUE, # if set to TRUE, PVs will be treated as separate variables
        repwt = RW, wt = "wt", df = repdata,
        method = "ICILS",var = "ML",zones = "jkzones",
        group = "GROUP",
        exclude = "GR2") # GR2 will not be used for Pooled nor Composite

### Groups and By ----

# One variable
repmean(x = c("item01"),
        PV = FALSE,
        repwt = RW, wt = "wt", df = repdata,
        method = "ICILS",var = "ML",zones = "jkzones",
        group = "GROUP",
        by = "GENDER", # results will be separated by GENDER
        exclude = "GR2") # GR2 will not be used for Pooled nor Composite

# One PV variable
repmean(x = paste0("Math",1:5),
        PV = TRUE, # if set to TRUE, PVs will be treated as separate variables
        repwt = RW, wt = "wt", df = repdata,
        method = "ICILS",var = "ML",zones = "jkzones",
        group = "GROUP",
        by = "GENDER", # results will be separated by GENDER
        exclude = "GR2") # GR2 will not be used for Pooled nor Composite

Mean Difference of Independent Samples with Replicate Weights

Description

Estimates the mean difference for a single variable with replicate weights. For a detailed explanation on how the standard errors are estimated see repse.

Usage

repmeandif(x)

Arguments

Value

a data frame or a list.

Examples

# Creation of replicate weights
RW <- repcreate(df = repdata, # the data frame with all the information
                 wt = "wt", # the total weights column name
                 jkzone = "jkzones", # the jkzones column name
                 jkrep = "jkrep", # the jkreps column name
                 repwtname = "REPWT", # the desired name for the rep weights
                 reps = 50, # the number of replications
                 method = "ICILS") # the name of the method aka the study name


### Groups ----

# One variable
reme <- repmean(x = c("item01"),
                PV = FALSE,
                repwt = RW, wt = "wt", df = repdata,
                method = "ICILS",var = "ML",zones = "jkzones",
                group = "GROUP",
                exclude = "GR2") # GR2 will not be used for Pooled nor Composite

repmeandif(reme)


# One PV variable
reme <- repmean(x = paste0("Math",1:5),
                PV = TRUE, # if set to TRUE, PVs will be treated as separate variables
                repwt = RW, wt = "wt", df = repdata,
                method = "ICILS",var = "ML",zones = "jkzones",
                group = "GROUP",
                exclude = "GR2") # GR2 will not be used for Pooled nor Composite

repmeandif(reme)

### Groups and By ----

# One variable
reme <- repmean(x = c("item01"),
                PV = FALSE,
                repwt = RW, wt = "wt", df = repdata,
                method = "ICILS",var = "ML",zones = "jkzones",
                group = "GROUP",
                by = "GENDER", # results will be separated by GENDER
                exclude = "GR2") # GR2 will not be used for Pooled nor Composite

repmeandif(reme)

# One PV variable
reme <- repmean(x = paste0("Math",1:5),
                PV = TRUE, # if set to TRUE, PVs will be treated as separate variables
                repwt = RW, wt = "wt", df = repdata,
                method = "ICILS",var = "ML",zones = "jkzones",
                group = "GROUP",
                by = "GENDER", # results will be separated by GENDER
                exclude = "GR2") # GR2 will not be used for Pooled nor Composite

repmeandif(reme)

Proportions with Replicate Weights

Description

Estimates proportions using replicate weights for a variable or a group of plausible values variables and for one or more populations. For a detailed explanation on how the standard errors are estimated see repse.

Usage

repprop(
  x,
  categories = NULL,
  setup = NULL,
  repwt,
  wt,
  df,
  method,
  group = NULL,
  exclude = NULL
)

Arguments

Value

a list.

Examples

# Creation of replicate weights
RW <- repcreate(df = repdata, # the data frame with all the information
                 wt = "wt", # the total weights column name
                 jkzone = "jkzones", # the jkzones column name
                 jkrep = "jkrep", # the jkreps column name
                 repwtname = "REPWT", # the desired name for the rep weights
                 reps = 50, # the number of replications
                 method = "ICILS") # the name of the method aka the study name

### No groups ----

# One variable - weights within df
repprop(x = c("item01"),
        repwt = "REPWT", wt = "wt", df = cbind(repdata,RW),
        method = "ICILS")

# One variable - weights weights as a separate data frame
repprop(x = c("item01"),
        repwt = RW, wt = "wt", df = repdata,
        method = "ICILS")

# Multiple variables - PVs are assumed
repprop(x = c("CatMath1","CatMath2","CatMath3"),
        repwt = RW, wt = "wt", df = repdata,
        method = "ICILS")

### Groups ----

# One variable - weights within df
repprop(x = c("item01"),
        group = "GROUP",
        repwt = "REPWT", wt = "wt", df = cbind(repdata,RW),
        method = "ICILS")

# One variable - weights weights as a separate data frame
repprop(x = c("item01"),
        group = "GROUP",
        repwt = RW, wt = "wt", df = repdata,
        method = "ICILS")

# Multiple variables - PVs are assumed
repprop(x = c("CatMath1","CatMath2","CatMath3"),
        group = "GROUP",
        repwt = RW, wt = "wt", df = repdata,
        method = "ICILS")

# Multiple variables - excluding one group
repprop(x = c("CatMath1","CatMath2","CatMath3"),
        group = "GROUP",
        exclude = "GR2",
        repwt = RW, wt = "wt", df = repdata,
        method = "ICILS")

Quantiles with Replicate Weights

Description

Estimates quantiles with replicate weights for a variable or a group of variables and for one or more populations. For a detailed explanation on how the standard errors are estimated see repse.

Usage

repquant(
  x,
  qtl = c(0.05, 0.25, 0.75, 0.95),
  PV = FALSE,
  setup = NULL,
  repwt,
  wt,
  df,
  method,
  group = NULL,
  by = NULL,
  exclude = NULL
)

Arguments

Value

a data frame or a list.

Examples

RWT <- repcreate(df = repdata, # the data frame with all the information
                 wt = "wt", # the total weights column name
                 jkzone = "jkzones", # the jkzones column name
                 jkrep = "jkrep", # the jkreps column name
                 repwtname = "REPWT", # the desired name for the rep weights
                 reps = 50, # the number of replications
                 method = "ICILS") # the name of the method aka the study name

### No groups ----

# One variable - weights within df
repquant(x = c("item01"),
        qtl = c(0.05, 0.25, 0.75, 0.95),
        PV = FALSE,
        repwt = "REPWT", wt = "wt", df = cbind(repdata,RWT),
        method = "ICILS")

# One variable - weights as a separate data frame
repquant(x = c("item01"),
        qtl = c(0.05, 0.25, 0.75, 0.95),
        PV = FALSE,
        repwt = RWT, wt = "wt", df = repdata,
        method = "ICILS")

# One PV variable
repquant(x = paste0("Math",1:5),
        qtl = c(0.05, 0.25, 0.75, 0.95),
        PV = TRUE, # if set to TRUE, PVs will be treated as separate variables
        repwt = RWT, wt = "wt", df = repdata,
        method = "ICILS")

### Groups ----

# One variable
repquant(x = c("item01"),
        qtl = c(0.05, 0.25, 0.75, 0.95),
        PV = FALSE,
        repwt = RWT, wt = "wt", df = repdata,
        method = "ICILS",
        group = "GROUP",
        exclude = "GR2") # GR2 will not be used for Pooled nor Composite


# One PV variable
repquant(x = paste0("Math",1:5),
        qtl = c(0.05, 0.25, 0.75, 0.95),
        PV = TRUE, # if set to TRUE, PVs will be treated as separate variables
        repwt = RWT, wt = "wt", df = repdata,
        method = "ICILS",
        group = "GROUP",
        exclude = "GR2") # GR2 will not be used for Pooled nor Composite

### Groups and By ----

# One variable
repquant(x = c("item01"),
        qtl = c(0.05, 0.25, 0.75, 0.95),
        PV = FALSE,
        repwt = RWT, wt = "wt", df = repdata,
        method = "ICILS",
        group = "GROUP",
        by = "GENDER", # results will be separated by GENDER
        exclude = "GR2") # GR2 will not be used for Pooled nor Composite

# One PV variable
repquant(x = paste0("Math",1:5),
        qtl = c(0.05, 0.25, 0.75, 0.95),
        PV = TRUE, # if set to TRUE, PVs will be treated as separate variables
        repwt = RWT, wt = "wt", df = repdata,
        method = "ICILS",
        group = "GROUP",
        by = "GENDER", # results will be separated by GENDER
        exclude = "GR2") # GR2 will not be used for Pooled nor Composite

Correlations with Replicate Weights

Description

Estimates correlation coefficients using replicate weights. For a detailed explanation on how the standard errors are estimated see repse.

Usage

reprho(
  x = NULL,
  pv = NULL,
  pv2 = NULL,
  relatedpvs = TRUE,
  setup = NULL,
  repwt,
  wt,
  df,
  rho = c("pearson", "spearman", "polychoric"),
  method,
  group = NULL,
  exclude = NULL,
  aggregates = c("pooled", "composite")
)

Arguments

Value

a data frame.

Examples

# Creation of replicate weights
RW <- repcreate(df = repdata, # the data frame with all the information
                wt = "wt", # the total weights column name
                jkzone = "jkzones", # the jkzones column name
                jkrep = "jkrep", # the jkreps column name
                repwtname = "REPWT", # the desired name for the rep weights
                reps = 50, # the number of replications
                method = "ICILS") # the name of the method aka the study name


### No groups ----

# Non PVs
reprho(x = c("GENDER",paste0("Math",1:3)),
       pv = NULL,
       pv2 = NULL,
       rho = "pearson",
       repwt = RW,
       wt = "wt",
       df = repdata,
       method = "ICILS")

# X var and PVs
reprho(x = c("GENDER",paste0("Math",1:3)),
       pv = paste0("Reading",1:5),
       pv2 = NULL,
       rho = "pearson",
       repwt = RW,
       wt = "wt",
       df = repdata,
       method = "ICILS")

# PVs and PVs (related)
reprho(x = NULL,
       pv = paste0("Math",1:5),
       pv2 = paste0("Reading",1:5),
       rho = "pearson",
       repwt = RW,
       wt = "wt",
       df = repdata,
       method = "ICILS")

# PVs and PVs (UNrelated)
reprho(x = NULL,
       pv = paste0("Math",1:5),
       pv2 = paste0("Reading",1:5),
       relatedpvs = FALSE,
       rho = "pearson",
       repwt = RW,
       wt = "wt",
       df = repdata,
       method = "ICILS")


### Groups ----

# Non PVs
reprho(x = c("GENDER",paste0("Math",1:3)),
       pv = NULL,
       pv2 = NULL,
       rho = "pearson",
       repwt = RW,
       wt = "wt",
       df = repdata,
       group = "GROUP",
       method = "ICILS")

# X var and PVs
reprho(x = c("GENDER",paste0("Math",1:3)),
       pv = paste0("Reading",1:5),
       pv2 = NULL,
       rho = "pearson",
       repwt = RW,
       wt = "wt",
       df = repdata,
       group = "GROUP",
       method = "ICILS")

# PVs and PVs (related)
reprho(x = NULL,
       pv = paste0("Math",1:5),
       pv2 = paste0("Reading",1:5),
       rho = "pearson",
       repwt = RW,
       wt = "wt",
       df = repdata,
       group = "GROUP",
       method = "ICILS")

# PVs and PVs (UNrelated)
reprho(x = NULL,
       pv = paste0("Math",1:5),
       pv2 = paste0("Reading",1:5),
       relatedpvs = FALSE,
       rho = "pearson",
       repwt = RW,
       wt = "wt",
       df = repdata,
       group = "GROUP",
       method = "ICILS")

Standard Error for Estimates with Replicate Weights and Plausible Values

Description

Calculates the standard error given a vector or list of previous estimations.

Usage

repse(er, e0, setup = NULL, method)

repsecomp(se)

pvse(PVse, PVe0, df = FALSE)

Arguments

Details

The standard errors are calculated using a modifier m, for JK2-full: m = 0.5; for JK2-half: m = 1; and for FAY-0.5: \frac{1}{R(1-0.5)^2}. Depending on the statistic, one of the following formulas is used.

The standard error not involving plausible values is calculated by:

\sqrt{m\times \sum_{r=1}^{R}(\varepsilon_r-\varepsilon_0)^2}.

The standard error involving plausibles values and replicate weights is calculated by:

\sqrt{\left[ \sum_{p=1}^{P} \left( m\times \sum_{r=1}^{R}(\varepsilon_{rp}-\varepsilon_{0p})^2 \right) \dfrac{1}{P}\right]+ \left[ \left(1+ \dfrac{1}{P} \right) \dfrac{\sum_{p=1}^{P} (\varepsilon_{0p}-\overline{\varepsilon}_{0p})^{2}}{P-1} \right]}.

The standard error involving plausibles values without replicate weights is calculated by:

\sqrt{ \dfrac{\sum_{p=1}^{P} SE^2_{\varepsilon_{0P}}}{P}+ \left[ \left(1+ \dfrac{1}{P} \right) \dfrac{\sum_{p=1}^{P} (\varepsilon_{0p}-\overline{\varepsilon}_{0p})^{2}}{P-1} \right]}.

The standard error of the difference of two statistics (a and b) from independent samples is calculated by:

\sqrt{SE_a^{2}+SE_b^{2}}.

The standard error of the difference of two statistics (a and b) from dependent samples not involving plausible values is calculated by:

\sqrt{m\times \sum_{r=1}^R((a_r-b_r)-(a_0-b_0))^2}.

The standard error of the difference of two statistics (a and b) from dependent samples involving plausible values is calculated by:

\sqrt{\left[ \sum_{p=1}^{P} \left( m\times \sum_{r=1}^{R}((a_{rp}-b_{rp})-(a_{0p}-b_{0p}))^2 \right) \dfrac{1}{P}\right]+ \left[ \left(1+ \dfrac{1}{P} \right) \dfrac{\sum_{p=1}^{P} \left((a_{0p}-b_{0p})- ( \overline{a}_{0p}-\overline{b}_{0p}) \right)^{2}}{P-1} \right]}.

The standard error of a composite estimate is calculated by:

\sqrt{\dfrac{\sum_{c=1}^CSE^2_{\varepsilon_c}}{C^{2}}}.

The standard error of the difference between an element (a) of the composite and the composite is calculated by:

\sqrt{\dfrac{\sum_{c=1}^CSE^2_{\varepsilon_c}}{C^{2}}+\left(\dfrac{(C-1)^2-1}{C^2}\right)SE^2_a}.

Where \varepsilon represents a statistic of interest, the subindex 0 indicates an estimate using the total weights, r indicates a replicate from a total of R, p indicates a plausible value from a total of P, and c indicates an element in a composite estimate from value a total of C.

Value

the standard error.

Examples

# Creation of replicate weights
RW <- repcreate(df = repdata, # the data frame with all the information
                wt = "wt", # the total weights column name
                jkzone = "jkzones", # the jkzones column name
                jkrep = "jkrep", # the jkreps column name
                repwtname = "REPWT", # the desired name for the rep weights
                reps = 50, # the number of replications
                method = "ICILS") # the name of the method aka the study name

# Non-PVs ----

## Mean with total weights
E0 <- stats::weighted.mean(x = repdata$item01, w = repdata$wt, na.rm = TRUE)
E0

## Means by replication
ER <- as.vector(apply(RW,2,function(i){
  stats::weighted.mean(x = repdata$item01, w = i, na.rm = TRUE)
}))
ER

## Standard error by hand
repse(er = ER, e0 = E0, method = "ICILS")

## Standard error with repmean()
repmean(x = "item01",wt = "wt",repwt = RW,df = repdata, method = "ICILS")


# PVs ----

## Mean with total weights
E0 <- sapply(1:5,function(i){
  stats::weighted.mean(x = repdata[,paste0("Math",i)], w = repdata$wt,
                       na.rm = TRUE)
})
E0

## Means by replication
ER <- lapply(1:5, function(j){
  as.vector(apply(RW,2,function(i){
    stats::weighted.mean(x = repdata[,paste0("Math",j)], w = i, na.rm = TRUE)
  }))
})
ER

## Standard error by hand
repse(er = ER, e0 = E0, method = "ICILS")

## Standard error with repmean()
repmean(x = paste0("Math",1:5),wt = "wt",repwt = RW,df = repdata, method = "ICILS",PV = TRUE)

Setup for Analysis with Replicate Weights

Description

Creates a list with common arguments used for analysis with replicate weights.

Usage

repsetup(repwt, wt, df, method, group = NULL, exclude = NULL)

repsetupILSA(study, year, repwt, df, group = NULL, exclude = NULL)

Arguments

Value

a list to be used in other functions.

Examples

# Creation of replicate weights
RW <- repcreate(df = repdata, # the data frame with all the information
                 wt = "wt", # the total weights column name
                 jkzone = "jkzones", # the jkzones column name
                 jkrep = "jkrep", # the jkreps column name
                 repwtname = "REPWT", # the desired name for the rep weights
                 reps = 50, # the number of replications
                 method = "ICILS") # the name of the method aka the study name

### No groups ----
stp1 <- repsetup(repwt = RW, wt = "wt", df = repdata, method = "ICILS")
stp1

### Groups ----
stp2 <- repsetup(repwt = RW, wt = "wt", df = repdata, method = "ICILS",
                 group = "GROUP", exclude = "GR2")
stp2


### repmean ----

repmean(x = "Math1",setup = stp1)

repmean(x = "Math1",setup = stp2)