Package 'calidad'

Assess the quality of mean estimations

Description

assess evaluates the quality of mean estimations using the methodology created by INE Chile, which considers sample size, degrees of freedom, and coefficient of variation.

Usage

assess(
  table,
  publish = FALSE,
  scheme = c("chile", "eclac_2020", "eclac_2023", "chile_economics"),
  domain_info = FALSE,
  low_df_justified = FALSE,
  table_n_obj = NULL,
  ratio_between_0_1 = TRUE,
  ...
)

Arguments

table	dataframe created by crear_insumos_media.
publish	boolean indicating if the evaluation of the complete table must be added. If TRUE, the function adds a new column to the dataframe.
scheme	character variable indicating the evaluation protocol to use. Options are "chile", "eclac_2020", "eclac_2023", "chile_economics".
domain_info	Logical. If TRUE, indicates that the study domain information is available and will be used for assessment. This affects how the evaluation is conducted, leveraging specific domain-level data to refine the assessment results. When FALSE, domain-specific adjustments are omitted, and a generalized assessment is performed.
low_df_justified	Logical. If TRUE the low degrees of freedom are justified and will be used for assessment. By default FALSE.
table_n_obj	Default NULL. Dataframe with the target sample size column n_obj and columns with the domains to evaluate. Its important check the domain columns type with table.
ratio_between_0_1	boolean. If TRUE, indicates that the estimator is a ratio between 0 and 1.
...	additional parameters for the evaluation. The complete list of parameters is: 1. General Parameters df degrees of freedom. Default: 9. n sample size. Default for chile scheme: 60. Default for CEPAL schemes: 100. Default for chile economic standard scheme: 30. 2. chile Parameters cv_lower_ine lower limit for CV. Default: 0.15. cv_upper_ine upper limit for CV. Default: 0.3. 3. CEPAL 2020 Parameters cv_cepal limit for CV. Default: 0.2. ess effective sample size. Default: 140. unweighted unweighted count. Default: 50. log_cv logarithmic coefficient of variation. Default: 0.175. 4. CEPAL 2023 Parameters cv_lower_cepal lower limit for CV. Default: 0.2. cv_upper_cepal upper limit for CV. Default: 0.3. ess effective sample size. Default: 60. cvlog_max maximum logarithmic coefficient of variation. Default: 0.175. CCNP_b unweighted count before adjustment. Default: 50. CCNP_a unweighted count after adjustment. Default: 30. 5. Chile Economic Survey Standard Parameters cv_lower_econ lower limit for CV. Default: 0.2. cv_upper_econ upper limit for CV. Default: 0.3.

Value

dataframe with all the columns included in the input table, plus a new column containing a label indicating the evaluation of each estimation: reliable, bit reliable, or unreliable.

Examples

dc <- survey::svydesign(ids = ~varunit, strata = ~varstrat, data = epf_personas, weights = ~fe)
assess(create_mean("gastot_hd", domains = "zona+sexo", design = dc))

---

Encuesta de Caracterización Socioeconómica Nacional 2020 - CASEN en Pandemia 2020

Description

CASEN data for the year 2020. Contains only a few variables.

Usage

casen

Format

dataframe with 185.437 rows y 6 columns

folio

household id

sexo

1 = man; 2 = woman

edad

age

activ

Economic activity status

ing_aut_hog

Household Income

pobreza

poverty status: 1 = extreme poverty, 2 = non-extreme poverty, 3 = non-poverty

expr

regional sample weights

estrato

strata

cod_upm

PSU

Source

http://observatorio.ministeriodesarrollosocial.gob.cl/encuesta-casen-en-pandemia-2020

Examples

data(casen)

---

Create html table with the results of the evaluation

Description

Create html table with the results of the evaluation

Usage

create_html(table)

Arguments

table

dataframe generated by evaluate function

Value

html table

Examples

library(survey)
library(dplyr)

hogar <- epf_personas %>%
  group_by(folio) %>%
  slice(1)
dc <- survey::svydesign(ids = ~varunit, strata = ~varstrat, data = hogar, weights = ~fe)
table <- assess(create_prop("ocupado", domains = "zona+sexo", design = dc))

---

Create the inputs to evaluate the quality of mean estimations

Description

create_mean generates a dataframe with the following elements: mean, degrees of freedom, sample size, and coefficient of variation. The function allows grouping in several domains.

Usage

create_mean(
  var,
  domains = NULL,
  subpop = NULL,
  design,
  ci = FALSE,
  ess = FALSE,
  ajuste_ene = FALSE,
  standard_eval = FALSE,
  rm.na = FALSE,
  deff = FALSE,
  rel_error = FALSE,
  unweighted = FALSE,
  eclac_input = FALSE
)

Arguments

var	numeric variable within the dataframe.
domains	domains to be estimated separated by the + character.
subpop	integer dummy variable to filter the dataframe.
design	complex design created by survey package.
ci	boolean indicating if the confidence intervals must be calculated.
ess	boolean effective sample size.
ajuste_ene	boolean indicating if an adjustment for the sampling-frame transition period must be used.
standard_eval	boolean indicating if the function is wrapped inside another function, if TRUE avoid lazy eval errors.
rm.na	boolean remove NA values if required.
deff	boolean design effect.
rel_error	boolean relative error.
unweighted	boolean add non-weighted count if required.
eclac_input	boolean return eclac inputs.

Value

dataframe that contains the inputs and all domains to be evaluated.

Examples

dc <- survey::svydesign(ids = ~varunit, strata = ~varstrat, data = epf_personas, weights = ~fe)
create_mean("gastot_hd", "zona+sexo", design = dc)

---

Create the inputs to evaluate the quality of proportion estimations

Description

create_prop generates a dataframe with the following elements: sum, degrees of freedom, sample size, standard error, and coefficient of variation. The function allows grouping in several domains.

Usage

create_prop(
  var,
  denominator = NULL,
  domains = NULL,
  subpop = NULL,
  design,
  ci = FALSE,
  deff = FALSE,
  ess = FALSE,
  ajuste_ene = FALSE,
  rel_error = FALSE,
  log_cv = FALSE,
  unweighted = FALSE,
  standard_eval = FALSE,
  eclac_input = FALSE,
  ci_logit = FALSE,
  scheme = c("eclac_2020", "eclac_2023")
)

Arguments

var	numeric variable within the dataframe, is the numerator of the ratio to be calculated.
denominator	numeric variable within the dataframe, is the denominator of the ratio to be calculated. If the var parameter is dummy, it can be NULL.
domains	domains to be estimated separated by the + character.
subpop	integer dummy variable to filter the dataframe.
design	complex design created by survey package.
ci	boolean indicating if the confidence intervals must be calculated.
deff	boolean design effect.
ess	boolean effective sample size.
ajuste_ene	boolean indicating if an adjustment for the sampling-frame transition period must be used.
rel_error	boolean relative error.
log_cv	boolean logarithmic coefficient of variation.
unweighted	boolean add non-weighted count if required.
standard_eval	boolean indicating if the function is wrapped inside another function, if TRUE avoid lazy eval errors.
eclac_input	boolean return eclac inputs
ci_logit	boolean indicating if interval confidence is logit, only available for proportions.
scheme	character variable indicating the evaluation protocol to use for CEPAL standard. Options are "eclac_2020" and "eclac_2023". The "eclac_2020" option does not support ratio estimation.

Value

dataframe that contains the inputs and all domains to be evaluated.

Examples

library(survey)
library(dplyr)

epf <- mutate(epf_personas, gasto_zona1 = if_else(zona == 1, gastot_hd, 0))
dc <- svydesign(ids = ~varunit, strata = ~varstrat, data = epf, weights = ~fe)
old_options <- options()
options(survey.lonely.psu = "certainty")

create_prop(var = "gasto_zona1", denominator = "gastot_hd", design = dc)

enusc <- filter(enusc, Kish == 1)

dc <- svydesign(ids = ~Conglomerado, strata = ~VarStrat, data = enusc, weights = ~Fact_Pers)
options(survey.lonely.psu = "certainty")
create_prop(var = "VP_DC", denominator = "hom_insg_taxi", design = dc)
options(old_options)

---

internal function to calculate proportion estimations

Description

internal function to calculate proportion estimations

Usage

create_prop_internal(
  var,
  domains = NULL,
  subpop = NULL,
  disenio,
  ci = FALSE,
  deff = FALSE,
  ess = FALSE,
  ajuste_ene = FALSE,
  rel_error = FALSE,
  log_cv = FALSE,
  unweighted = FALSE,
  standard_eval = TRUE,
  rm.na = FALSE,
  env = parent.frame(),
  ci_logit = FALSE
)

Arguments

var	integer dummy variable within the dataframe
domains	domains to be estimated separated by the + character.
subpop	integer dummy variable to filter the dataframe
disenio	complex design created by survey package
ci	boolean indicating if the confidence intervals must be calculated
deff	boolean Design effect
ess	boolean Effective sample size
ajuste_ene	boolean indicating if an adjustment for the sampling-frame transition period must be used
rel_error	boolean Relative error
log_cv	boolean indicating if the log cv must be returned
unweighted	boolean Add non weighted count if it is required
standard_eval	boolean indicating if the function is inside another function, by default it is TRUE, avoid problems with lazy eval.
rm.na	boolean indicating if NA values must be removed
env	parent environment to get some variables
ci_logit	boolean indicating if interval confidence is logit

Value

dataframe that contains the inputs and all domains to be evaluated

---

internal function to calculate ratios estimations

Description

internal function to calculate ratios estimations

Usage

create_ratio_internal(
  var,
  denominator,
  domains = NULL,
  subpop = NULL,
  disenio,
  ci = FALSE,
  deff = FALSE,
  ess = FALSE,
  ajuste_ene = FALSE,
  unweighted = FALSE,
  rel_error = FALSE,
  log_cv = FALSE,
  rm.na = FALSE
)

Arguments

var	numeric variable within the dataframe, is the numerator of the ratio to be calculated.
denominator	numeric variable within the dataframe, is the denominator of the ratio to be calculated.
domains	domains to be estimated separated by the + character.
subpop	integer dummy variable to filter the dataframe
disenio	complex design created by survey package
ci	boolean indicating if the confidence intervals must be calculated
deff	boolean Design effect
ess	boolean Effective sample size
ajuste_ene	boolean indicating if an adjustment for the sampling-frame transition period must be used
unweighted	boolean Add non weighted count if it is required
rel_error	boolean Relative error
log_cv	boolean indicating if the log cv must be returned. Used for ratios between 0 and 1.
rm.na	boolean indicating if NA values must be removed

Value

dataframe that contains the inputs and all domains to be evaluated

---

Create the inputs to evaluate the quality of total estimations

Description

create_size generates a dataframe with the following elements: sum, degrees of freedom, sample size, and coefficient of variation. The function allows grouping in several domains.

Usage

create_size(
  var,
  domains = NULL,
  subpop = NULL,
  design,
  ci = FALSE,
  ess = FALSE,
  ajuste_ene = FALSE,
  standard_eval = FALSE,
  rm.na = FALSE,
  deff = FALSE,
  rel_error = FALSE,
  unweighted = FALSE,
  df_type = c("chile", "eclac"),
  eclac_input = FALSE
)

Arguments

var	numeric variable within the dataframe. When the domain parameter is not used, it is possible to include more than one variable using the + separator. When a value is introduced in the domain parameter, the estimation variable must be a dummy variable.
domains	domains to be estimated separated by the + character.
subpop	integer dummy variable to filter the dataframe.
design	complex design created by survey package.
ci	boolean indicating if the confidence intervals must be calculated.
ess	boolean effective sample size.
ajuste_ene	boolean indicating if an adjustment for the sampling-frame transition period must be used.
standard_eval	boolean indicating if the function is wrapped inside another function, if TRUE avoid lazy eval errors.
rm.na	boolean remove NA values if required.
deff	boolean design effect.
rel_error	boolean relative error.
unweighted	boolean add non-weighted count if required.
df_type	character use degrees of freedom calculation approach from INE Chile or CEPAL. Options are "chile" or "eclac".
eclac_input	boolean return eclac inputs

Value

dataframe that contains the inputs and all domains to be evaluated.

Examples

dc <- survey::svydesign(ids = ~varunit, strata = ~varstrat, data = epf_personas, weights = ~fe)
create_size("ocupado", "zona+sexo", design = dc)

---

Create the inputs to evaluate the quality of the sum of continuous variables

Description

create_total generates a dataframe with the following elements: sum, degrees of freedom, sample size, and coefficient of variation. The function allows grouping in several domains.

Usage

create_total(
  var,
  domains = NULL,
  subpop = NULL,
  design,
  ci = FALSE,
  ess = FALSE,
  ajuste_ene = FALSE,
  standard_eval = FALSE,
  rm.na = FALSE,
  deff = FALSE,
  rel_error = FALSE,
  unweighted = FALSE,
  eclac_input = FALSE
)

Arguments

var	numeric variable within the dataframe.
domains	domains to be estimated separated by the + character.
subpop	integer dummy variable to filter the dataframe.
design	complex design created by survey package.
ci	boolean indicating if the confidence intervals must be calculated.
ess	boolean effective sample size.
ajuste_ene	boolean indicating if an adjustment for the sampling-frame transition period must be used.
standard_eval	boolean indicating if the function is wrapped inside another function, if TRUE avoid lazy eval errors.
rm.na	boolean remove NA values if required.
deff	boolean design effect.
rel_error	boolean relative error.
unweighted	boolean add non-weighted count if required.
eclac_input	boolean return eclac inputs

Value

dataframe that contains the inputs and all domains to be evaluated.

Examples

dc <- survey::svydesign(ids = ~varunit, strata = ~varstrat, data = epf_personas, weights = ~fe)
create_total("gastot_hd", "zona+sexo", subpop = "ocupado", design = dc)

---

Turn on all the indicators needed for the eclac standard

Description

This function activates the appropriate indicators based on the selected eclac standard and whether proportion indicators are needed.

Usage

eclac_standard(eclac, env = parent.frame(), proportion = FALSE)

Arguments

eclac	A logical value indicating the eclac standard.
env	The environment from which to retrieve the existing indicator values. Defaults to the parent frame.
proportion	A logical value indicating whether proportion indicators should be turned on. Defaults to FALSE.

Value

A list of logical values indicating which indicators are turned on.

---

Encuesta Longitudinal de Empresas

Description

ELE data for the year 2022. Contains only a few variables.

Usage

ELE7

Format

dataframe with 6.592 rows y 13 columns

rol_ficticio

Company ID

cod_actividad

Economic activity

cod_tamano

Company size by sales

tramo

Inclusion range

fe_transversal

Cross-sectional weights

fe_longitudinal

Longitudinal weights

panel

Panel sample

estrato

Strata

pob

Finite population correction

VA_2022

Value added 2022, difference between production value and intermediate consumption

VA_2022f

VA_2022f is an adjusted version of VA_2022, where negative values are replaced with 0, while non-negative values remain unchanged.

EMP

Total personnel employed and hired by the company on a monthly basis

REMP_TOTAL

Total gross remuneration of personnel hired by the company

Source

https://www.ine.gob.cl/docs/default-source/encuesta-longitudinal-de-empresas/bbdd/ele-2022/base-de-datos-ele7.csv?sfvrsn=1504c58d_4&download=true

Examples

data(ELE7)

---

Tamano muestra objetivo Encuesta Longitudinal de Empresas

Description

Target cross-sectional sample size ELE data for the year 2022.

Usage

ELE7_n_obj

Format

dataframe with 59 rows y 4 columns

cod_tamano

Company size by sales

cod_actividad_letra

Economic activity

cod_actividad

Economic activity ID

n_obj

Target sample size

Source

https://www.ine.gob.cl/docs/default-source/encuesta-longitudinal-de-empresas/metodologias/ele-2022/informe-de-calidad-ele7.pdf?sfvrsn=6ca73eb5_4

Examples

data(ELE7_n_obj)

---

Encuesta Nacional de Empleo - ENE. 2020-efm

Description

Reduced version of the ENE database. Contains some sociodemographic variables and the necessary information to work with complex design

Usage

ene

Format

dataframe with 87.842 rows y 7 columns

sexo

1 = man; 2 = woman

region

region

cae_especifico

Economic activity status

fe

sample weights

varunit

PSU

varstrat

strata

fdt

It shows if the person belongs to labour force: 1 = yes; 0 = no

ocupado

1 = employed; 0 = non-employed

desocupado

1 = non-employed; 0 = employed

Source

https://www.ine.cl/estadisticas/sociales/mercado-laboral/ocupacion-y-desocupacion

Examples

data(ene)

---

Encuesta Nacional Urbana de Seguridad Ciudadana 2019 - ENUSC 2019

Description

ENUSC data for the year 2019. Contains only a few variables.

Usage

enusc

Format

dataframe with 24.465 rows y 22 columns

rph_sexo

1 = man; 2 = woman

region

16 regions

Fact_Pers

person sample weights

Fact_Hog

household sample weights

Conglomerado

PSU

VarStrat

strata

VP_DC

Individual victimization. It works combined with Fact_Pers

VA_DC

Household victimization. It works combined with Fact_Hog

rph_edad

age

P3_1_1

Perception of increased crime in the country. It works combined with Fact_Pers

P8_1_1

Cause of increased crime in the neighborhood. It works combined with Fact_Pers

muj_insg_taxi

Female perception of insecurity inside taxis. Variable elaborated with variables P9 and rph_sexo . It works combined with Fact_Pers

hom_insg_taxi

Male perception of insecurity inside taxis. Variable elaborated with variables P9 and rph_sexo. It works combined with Fact_Pers

muj_insg_micro

Female perception of insecurity inside buses. Variable elaborated with variables P9 and rph_sexo. It works combined with Fact_Pers

hom_insg_micro

Male perception of insecurity inside buses. Variable elaborated with variables P9 and rph_sexo. It works combined with Fact_Pers

muj_insg_centr.com

Female perception of insecurity inside malls. Variable elaborated with variables P9 and rph_sexo. It works combined with Fact_Pers

hom_insg_centr.com

Male perception of insecurity inside malls. Variable elaborated with variables P9 and rph_sexo. It works combined with Fact_Pers

muj_insg_loc.col

Female perception of insecurity public transport. Variable elaborated with variables P9 and rph_sexo. It works combined with Fact_Pers

hom_insg_loc.col

Male perception of insecurity public transport. Variable elaborated with variables P9 and rph_sexo. It works combined with Fact_Pers

muj_insg_barrio

Female perception of insecurity neighborhood. Variable elaborated with variables P9 and rph_sexo. It works combined with Fact_Pers

hom_insg_barrio

Male perception of insecurity neighborhood. Variable elaborated with variables P9 and rph_sexo. It works combined with Fact_Pers

Source

https://www.ine.cl/docs/default-source/seguridad-ciudadana/bbdd/2019/base-de-datos—xvi-enusc-2019-(csv).csv?sfvrsn=d3465758_2&download=true

Examples

data(enusc)

---

Encuesta Nacional Urbana de Seguridad Ciudadana 2023 - ENUSC 2023

Description

ENUSC data for the year 2023. Contains only a few variables.

Usage

enusc_2023

Format

dataframe with 49.813 rows y 15 columns

enc_region

16 regions

enc_rpc

Code of region, province and commune

Fact_Pers_Reg

Person sample weights at region level

Fact_Pers_Com

Person sample weights at commune level

Fact_Hog_Reg

Household sample weights at region level

Fact_Hog_Com

Household sample weights at commune level

VarStrat

Strata

Conglomerado

PSU

VH_DV

Households victimized by violent crimes. It works combined with Fact_Hog_*

VH_DC

Household victimization. It works combined with Fact_Hog_*

VP_DV

People victimized by violent crimes. It works combined with Fact_Pers_*

VP_DC

Individual victimization. It works combined with Fact_Pers_*

PAD

Perception of increased crime in the country. It works combined with Fact_Pers_*

rph_sexo

1 = man; 2 = woman

rph_edad

Age

Source

https://www.ine.gob.cl/docs/default-source/seguridad-ciudadana/bbdd/2023/base-usuario-20-enusc-2023.csv?sfvrsn=34653b72_2&download=true

Examples

data(enusc_2023)

---

VIII Encuesta de Presupuestos Familiares

Description

Reduced version of the VIII EPF database. Contains some sociodemographic variables and the necessary information to work with complex design.

Usage

epf_personas

Format

dataframe compuesto por 48.308 observaciones y 8 variables

sexo

1 = male; 2 = female

zona

1 = metropolitan area; 2 = rest of the regional capitals

ecivil

marital status

fe

sample weights

varunit

PSU

varstrat

strata

gastot_hd

household expenditure

ocupado

1 = employed; 0 = non-employed

Source

https://www.ine.cl/estadisticas/sociales/ingresos-y-gastos/encuesta-de-presupuestos-familiares

Examples

data(epf_personas)

---

Get the coefficient of variation

Description

Receive a table created with survey and return the coefficient of variation for each cell

Usage

get_cv(table, design, domains, type_est = "all", env = parent.frame())

Arguments

table	dataframe with results
design	design
domains	vector with domains
type_est	type of estimation: all or size.
env	parent environment

Value

dataframe with results including including CV

---

Get degrees of freedom

Description

Receive data and domains. Returns a data frame with the psu (if available), strata and degrees of freedom (df) for each cell

Usage

get_df(data, domains, df_type = "eclac")

Arguments

data	dataframe
domains	string with domains
df_type	string Use degrees of freedom calculation approach from INE Chile or eclac, by default "chile".

Value

dataframe with results including degrees of freedom

---

Calculates multiple estimations. Internal wrapper for survey package

Description

Generates a table with estimates for a given aggregation

Usage

get_survey_table(
  var,
  domains,
  complex_design,
  estimation = "mean",
  env = parent.frame(),
  fun,
  denom = NULL,
  type_est = "all"
)

Arguments

var	string objective variable
domains	domains
complex_design	design from survey
estimation	string indicating if the mean must be calculated
env	parent environment
fun	function required regarding the estimation
denom	denominator. This parameter works for the ratio estimation
type_est	type of estimation: all or size

Value

dataframe containing main results from survey

---

Calcula el valor de una función cuadrática

Description

quadratic returns the output of a particular function created by INE Chile, which is assessed at the value of the estimated proportion from a sample. If the output of the function is higher than the standard error, it is interpreted as a signal that the estimation is not reliable.

Usage

quadratic(p)

Arguments

p	numeric vector with the values of the estimations for proportions

Value

numeric vector

---

standardize and sort column names

Description

Receive the survey table in raw state and sort it

Usage

standardize_columns(data, var, denom)

Arguments

data	dataframe with results
var	string with the objective variable
denom	denominator

Value

dataframe with standardized data

---

Standardize the name of design variables

Description

Rename design variables, so we can use the later

Usage

standardize_design_variables(design)

Arguments

design

dataframe

Value

design survey

---