Getting started with enemduR

Purpose

enemduR is an analytical infrastructure package for reproducible work with Ecuador ENEMDU microdata.

The package is designed to support technical workflows: reading files, validating structure, deriving analytical variables, declaring the complex survey design, estimating indicators, assessing representativity, and producing stable outputs for downstream reporting.

It is not a dashboard and it is not a replacement for official statistical production systems. Quarto reports, dashboards, and other visual products are downstream consumers of the analytical outputs.

Data access

Official ENEMDU microdata must be obtained by the user from authorized sources. This vignette does not include, download, or request official microdata.

The paths below are placeholders. They are intended as workflow templates for local files that the user is authorized to use.

Supported file formats

enemdu_read_data() supports:

Format	Role
.sav	Operational primary format for recent official ENEMDU microdata workflows
.dta	Interoperability format
.csv	Interoperability format

Minimal workflow

A typical workflow starts by loading a local ENEMDU file.

library(enemduR)

microdata <- enemdu_read_data(
  path = "path/to/authorized/enemdu_persona_2026_03.sav",
  survey_type = "mensual",
  period = "2026-03"
)

Run a structural validation step before estimating indicators.

structure_report <- enemdu_validate_structure(microdata)
structure_report

Declare the ENEMDU complex survey design when a workflow needs a design object directly.

design <- enemdu_declare_design(
  data = microdata,
  ids = "upm",
  strata = "estrato",
  weights = "fexp"
)

Estimate an initial labor KPI table with the package labor module.

labor_kpis <- enemdu_kpi_employment(
  data = microdata,
  survey_type = "mensual",
  domain_scope = "design"
)

labor_kpis

Working by domain

For monthly ENEMDU files, area outputs can be requested with group_vars = "area" and domain_scope = "design".

labor_area <- enemdu_kpi_employment(
  data = microdata,
  survey_type = "mensual",
  group_vars = "area",
  domain_scope = "design"
)

For quarterly city-domain workflows, use the official comparison field available in the analytical workflow, such as dominio, rather than assuming that ciudad is equivalent to official published city domains.

quarterly_microdata <- enemdu_read_data(
  path = "path/to/authorized/enemdu_persona_2026_I_trimestre.sav",
  survey_type = "trimestral",
  period = "2026-I"
)

labor_city_domains <- enemdu_kpi_employment(
  data = quarterly_microdata,
  survey_type = "trimestral",
  group_vars = "dominio",
  domain_scope = "observed"
)

Output use

Most analytical outputs are long-format tables intended for downstream use in:

• Quarto documents;
• validation notebooks;
• dashboards;
• technical reports;
• institutional analytical pipelines.

The package keeps analytical computation separate from presentation. Reporting layers should consume the output tables rather than control how indicators are computed.

Next steps

After this introduction, read:

• the survey design and representativity vignette;
• the labor indicators vignette;
• the poverty, NBI, and IPM/TPM reproducibility vignette.