<b>Rendimento </b><b><i>per capita</i></b><b> municipal: estimativa com aprendizado de máq

A dataset of per capita income estimates for Brazilian municipalities, generated using a hybrid model that integrates Small Area Estimation and Machine Learning. The model uses administrative records from CadÚnico, DIRPF, RAIS, and INSS, calibrated to the direct estimates from the Continuous PNAD survey. The results demonstrate high predictive capacity, temporal stability, and a strong correlation with the 2022 Demographic Census income data.

Use Cases

• Mapping socioeconomic vulnerability based on estimated per capita income at the municipal level.
• Analyzing regional inequality in Brazil using small-area estimates for intercensal periods.
• Benchmarking traditional linear models against the described hybrid machine learning approach for income estimation.
• Informing local public policy planning with consistent, intercensal income estimates.

Strengths

• Model demonstrates high predictive capacity and temporal stability according to the description.
• Estimates show strong correlation with 2022 Demographic Census income data.
• Methodology integrates multiple national administrative records (CadÚnico, DIRPF, RAIS, INSS) with survey data.

Limitations

• Column-level documentation is absent; field semantics must be inferred after download.
• Row count is unknown, which may limit suitability assessment.
• Data may reflect geographic or source bias inherent to the administrative records used.

Provenance

Source

Author: RAFAEL GIACOMIN. Platform: figshare.

Collection Method

Generated via a hybrid model combining Small Area Estimation and Machine Learning (boosting algorithms), calibrated to PNAD Contínua survey strata.

Freshness

Last updated 2026-04-14 02:17:14; freshness should be verified.

Geography

Brazilian municipalities.