version 0.3.0

DESCRIPTION

@@ -0,0 +1,30 @@
+Package: gustave
+Type: Package
+Title: A User-Oriented Statistical Toolkit for Analytical Variance
+        Estimation
+Depends: R(>= 3.3.0)
+Imports: Matrix, methods, stats, MASS
+Suggests: testthat, sampling, vardpoor
+Version: 0.3.0
+Authors@R: person("Martin", "Chevalier", role = c("aut", "cre", "cph"), email = "martin.chevalier@insee.fr")
+Author: Martin Chevalier [aut, cre, cph]
+Maintainer: Martin Chevalier <martin.chevalier@insee.fr>
+URL: https://github.com/martinchevalier/gustave
+BugReports: https://github.com/martinchevalier/gustave/issues
+Description: 
+  Provides a toolkit for analytical variance estimation in survey sampling. Apart from
+  the implementation of standard variance estimators, its main feature is to help the
+  sampling expert produce easy-to-use variance estimation "wrappers", where systematic
+  operations (linearization, domain estimation) are handled in a consistent and transparent
+  way for the end user.
+License: GPL-3
+Collate: 'data.R' 'utils.R' 'define_variance_wrapper.R'
+        'variance_function.R' 'define_linearization_wrapper.R'
+        'linearization_wrapper_standard.R'
+Encoding: UTF-8
+LazyData: true
+RoxygenNote: 6.0.1
+NeedsCompilation: no
+Packaged: 2018-06-05 10:13:41 UTC; gc004y
+Repository: CRAN
+Date/Publication: 2018-06-06 10:57:54 UTC

MD5

@@ -0,0 +1,31 @@
+8f5c2260b6ccb083123baf75b8257fec *DESCRIPTION
+91880814741925e785cae8f2c41e08b2 *NAMESPACE
+51060c716262ae470bbbf42430a795fb *NEWS.md
+ebb51fb5b0e3f9b27e10eef41b7aae47 *R/data.R
+53633df58319bff6c34cd221e3950212 *R/define_linearization_wrapper.R
+102424bb8ef6c38253a3157b99e3baf6 *R/define_variance_wrapper.R
+a57e30f0051232e5bb29773062153416 *R/linearization_wrapper_standard.R
+750d4e4f6a16bb1cd3a84a432c894f8a *R/utils.R
+c96c290e003489983e7e4c02876fc183 *R/variance_function.R
+4d8d99c908b5ac4039581f7fec3d2292 *README.md
+0870fcf3d5172672081245da1c05b9c9 *data/ict_pop.RData
+8a70ef048c7396290cb84a16302e13a4 *data/ict_sample.RData
+49e1f4f2f2fdb31fa882fb621ea6bcdd *data/ict_survey.RData
+2a9261d3e2c6b9a2366d014ea8b0c09f *man/add0.Rd
+69ef4e74da05b417c7d53d9525f65287 *man/define_linearization_wrapper.Rd
+39762731288e7ddde26e2e2016837f70 *man/define_variance_wrapper.Rd
+288191ccf77d2678afdb4c8fbe22b03a *man/ict_pop.Rd
+d5ba39cc41aa667aa24a4d1f04d3c351 *man/ict_sample.Rd
+548f610bd1fc82fb9c557f709b8f5f40 *man/ict_survey.Rd
+cf1700c6e2420367d45321b063c41296 *man/linearization_wrapper_standard.Rd
+035009d9d873192075d924da70a52ac4 *man/rescal.Rd
+006505dd3d3bf9ae2e17061e62819cee *man/sumby.Rd
+74859be7486e481b83e3fa777228119c *man/varDT.Rd
+bde6a9e3b7e419a98a86f379d0fa2f90 *man/varSYG.Rd
+f5b5174836ed01a616bdcb59d427fe65 *man/var_pois.Rd
+b64a36634ff32b6814849e4d3f104669 *tests/testthat.R
+8fcc043daaecff41d7956b33733fcd28 *tests/testthat/test_data.R
+c429c11490868e5918bbc12f30020ea5 *tests/testthat/test_define_variance_wrapper.R
+96716fb61cb68d183d90356a35deda9c *tests/testthat/test_linearization_wrapper_standard.R
+5f05ba731848289a23bd61436db98acb *tests/testthat/test_utils.R
+23b39bbb1d0d25eefd76cad2c4249212 *tests/testthat/test_variance_function.R

NAMESPACE

@@ -0,0 +1,12 @@
+# Generated by roxygen2: do not edit by hand
+
+export(add0)
+export(define_linearization_wrapper)
+export(define_variance_wrapper)
+export(rescal)
+export(sumby)
+export(varDT)
+export(varSYG)
+export(var_pois)
+export(var_srs)
+import(Matrix)

NEWS.md

@@ -0,0 +1,42 @@
+
+# 0.3.0
+
+- Simulated data added
+- Significant increase of unit tests
+- Documentation completed
+- Simplification of the structure of the main object processed by the variance wrapper
+- Removal of unnecessary arguments in linearization wrappers
+- Removal of the linerization wrappers for the Laeken indicators based on the vardpoor package (better integration in a future release)
+- Preparation for a first CRAN release
+
+# 0.2.7
+
+- Now linearization with all data parameters set to NULL are discarded from the estimation.
+
+# 0.2.6 
+
+- Bug fix: evaluation of variables can occur either in the data argument or in the evaluation environment (envir argument)
+
+# 0.2.3-0.2.5
+
+- Several attempts to output more metadata from linearization functions. 
+- At the end : ratio() gains two metadata slots, est_num and est_denom
+
+# 0.2.2
+
+- Minor bug fixes
+
+# 0.2.1
+
+- Beginning of the documentation
+- Renaming of numerous functions and arguments
+- Change the precalc structure in varDT
+- Normalize the treatment of weights
+- New linearization wrappers: gini() and arpr()
+
+# 0.1.3-0.1.7
+
+- No more dependency to package pryr
+- Add the generalized inverse in `varDT`
+- Other bug fixes
+

R/data.R

@@ -0,0 +1,71 @@
+
+
+#' Sampling frame of the Information and communication technologies (ICT)
+#' survey in the information and communication sector (NACE rev 2 J section)
+#'
+#' A (simulated) dataset containing basic identification information and
+#' auxiliary variables for the sampling of the Information and communication
+#' technologies (ICT) survey in the information and communication sector 
+#' (NACE rev 2 J section).
+#'
+#' @format A data frame with 7670 observations and 4 variables:
+#' \describe{
+#'   \item{firm_id}{identifier of the firm}
+#'   \item{division}{identifier of the economic sub-sector}
+#'   \item{employees}{number of employees}
+#'   \item{turnover}{firm turnover, in thousand euros}
+#' }
+#' 
+#' @seealso \code{\link{ict_sample}} \code{\link{ict_survey}}
+
+"ict_pop"
+
+
+#' Sample of the Information and communication technologies (ICT)
+#' survey in the information and communication sector (NACE rev 2 J section)
+#' 
+#' A (simulated) dataset containing sampling information about the sample 
+#' of the Information and communication technologies (ICT)
+#' survey in the information and communication sector (NACE rev 2 J section)
+#'
+#' @format A data frame with 650 observations and 8 variables:
+#' \describe{
+#'   \item{firm_id}{identifier of the firm}
+#'   \item{division}{identifier of the economic sub-sector}
+#'   \item{employees}{number of employees}
+#'   \item{turnover}{firm turnover, in euros}
+#'   \item{w_sample}{sampling weight}
+#'   \item{resp}{boolean indicating whether the firm did respond to the survey or not}
+#'   \item{hrg}{homogeneous response group used for the unit non-response correction}
+#'   \item{response_prob_est}{response probability of the unit estimated using homogeneous response groups}
+#'   \item{w_nr}{weight after unit non-response correction}
+#' }
+#' 
+#' @seealso \code{\link{ict_pop}} \code{\link{ict_survey}}
+"ict_sample"
+
+#' Survey data of the Information and communication technologies (ICT)
+#' survey in the information and communication sector (NACE rev 2 J section)
+#'
+#' A (simulated) dataset containing calibration and survey variables of the respondents 
+#' to the Information and communication technologies (ICT)
+#' survey in the information and communication sector (NACE rev 2 J section)
+#'
+#' @format A data frame with 612 observations and 25 variables:
+#' \describe{
+#'   \item{firm_id}{identifier of the firm}
+#'   \item{division}{identifier of the economic sub-sector}
+#'   \item{employees}{number of employees}
+#'   \item{turnover}{firm turnover, in euros}
+#'   \item{w_sample}{sampling weight}
+#'   \item{w_nr}{weight after unit non-response correction}
+#'   \item{N_58, N_59, N_60, N_61, N_62, N_63, turnover_58, turnover_59, turnover_60, turnover_61, turnover_62, turnover_63}{calibration variables (number of firms and turnover broken down by economic sub-sector)}
+#'   \item{w_calib}{calibrated weight}
+#'   \item{speed_quanti, speed_quanti_NA}{internet connection speed of the firm in Mbits, without or with missing values}
+#'   \item{speed_quali, speed_quali_NA}{internet connection speed of the firm recoded in classes, without or with missing values}
+#'   \item{big_data, big_data_NA}{use of big data analytics within the firm, without or with missing values}
+#' }
+#' 
+#' @seealso \code{\link{ict_pop}} \code{\link{ict_sample}}
+
+"ict_survey"