CASEN 2024 in 3 spoonfuls: without a fine-grained territorial reading, social policy moves blind

In Chile, La Araucanía records 13.0% extreme poverty; Magallanes, 4.2%. That is 8.8 percentage points of difference - and if a public agency at the central or local level (regional governments / municipalities) designs its intervention using only the national average (6.9%), or disregarding regional differences, it could get the allocation of resources or the distribution of its components wrong. This post documents a reproducible analysis of CASEN 2024 in Julia, with cross-validation of official public figures against BIDAT and good traceability of the flow in the repo. Three findings to start with - statistically robust: - Extreme poverty: La Araucanía 13.0% 95% CI [11.8%, 14.1%] versus Magallanes 4.2% [3.1%, 5.2%] - a gap of 8.8 pp with non-overlapping CIs. - FONASA coverage: La Araucanía 91.1% [90.2%, 92.0%] versus Metropolitana 75.9% [75.0%, 76.7%] - a gap of 15.2 pp with non-overlapping CIs. - Completed higher education: Metropolitana 34.9% [34.0%, 35.7%] versus Maule 20.4% [19.2%, 21.6%] - a gap of 14.5 pp with non-overlapping CIs. The CIs are 95% and were computed by Taylor linearization (wiki) for CASEN's complex sampling design (stratified two-stage, expr weights). That the CIs do not overlap implies these regional differences are statistically significant at the conventional level. Tolerance to contrast, or checking against official data All results were checked against the official tables available in BIDAT. Table 1 - Official validation results (BIDAT, CASEN 2024) | Parameter | Value | |---|---| | Validation status (national + regional, % + expanded) | PASS | | Maximum tolerance in percentage points | 1×10⁻⁵ pp | | Maximum tolerance in expanded values | 1×10⁻⁶ | | Observed difference (pp) | 2.98×10⁻⁶ pp | | Observed difference (expanded) | 0.0 | | National rows compared | 16 | | Regional rows compared | 256 | The maximum observed difference is below 3 millionths of a percentage point and within the preset tolerance. The results match the official tables within the predefined tolerances. Spoonful 1: sampling design and expansion without shortcuts CASEN 2024 has a probabilistic stratified two-stage design (BIDAT methodological note). For regional-level estimates, the correct factor is expr ; for the municipal level expc is required - they are not interchangeable. This analysis uses expr and reports estimates by region with 95% CIs computed by Taylor linearization over the complex design (strata, PSU/UPM and weights/factors). Population represented in this run (sum of expr ): 20.13 million people (a pending task is to assess the impact of the new 2024 Census instead of projections over the 2017 Census). # CASEN 2024 sampling design specification design = ( weight = :expr, # regional expansion factor strata = :estrato, # sampling stratum psu = :cod_upm, # primary sampling unit (PSU) domain = :region, # estimation domain ) Coverage by analyzed dimension: Table 2 - CASEN 2024 variables used and target population | Dimension | CASEN variable | Target population | |---|---|---| | Education | educc | People ≥ 18 years | | Health | s13 | Total population | | Poverty | pobreza | Total population | Weighted national results The following percentages correspond to proportions weighted with expr , validated against official data in BIDAT. The difference from the official values is cd casen2024/julia_viz julia --project=. -e "using Pkg; Pkg.instantiate()" julia --project=. scripts/run_all.jl The flow generates plenty of artifacts (CSV tables, PNG charts, audit logs for each input). The Manifest.toml file pins the exact versions of all dependencies (I used Julia 1.10). Spoonful 3: visual evidence National composition (Charts 1-3) Each waffle represents 100 cells allocated by largest remainder over the weighted proportions. Regional gaps (Charts 4-6) Each panel uses an axis fitted to the range of its own category (not a shared global scale), which makes it possible to visualize differences that flatten out if all categories share the same axis. The horizontal bars are 95% CIs computed by Taylor linearization; the dashed vertical line marks the national estimate and the pale grey band its 95% CI. Gaps with 95% CIs - all statistically robust Table 4 - Regional gaps with 95% CIs by Taylor linearization (CASEN 2024) | Dimension | Category | Gap (pp) | Maximum | 95% CI | Minimum | 95% CI | |---|---|---|---|---|---|---| | Poverty | Non-poverty | 18.6 pp | Magallanes 90.0% | [88.5%, 91.5%] | La Araucanía 71.4% | [69.8%, 73.0%] | | Health | Isapre | 16.3 pp | Metropolitana 20.6% | [19.8%, 21.5%] | Maule 4.3% | [3.7%, 5.0%] | | Health | FONASA | 15.2 pp | La Araucanía 91.1% | [90.2%, 92.0%] | Metropolitana 75.9% | [75.0%, 76.7%] | | Education | Complete higher education | 14.5 pp | Metropolitana 34.9% | [34.0%, 35.7%] | Maule 20.4% | [19.2%, 21.6%] | | Poverty | Extreme poverty | 8.8 pp | La Araucanía 13.0% | [11.8%, 14.1%] | Magallanes 4.2% | [3.1%, 5.2%] | In every case the CIs do not overlap: the gaps are statistically significant at 5%. CIs computed by Taylor linearization over the complex design (strata, PSU/UPM, expr ). Closing: three questions for those who use the survey If you use CASEN 2024 for territorial characterization or other uses where regional-level variables matter, think twice before using a point estimate (without its confidence interval): - Are your results validated against BIDAT and do they carry design-based CIs? A difference greater than 1×10⁻⁵ pp from the official tables is not technical: it is a process issue. And without complex-design CIs, an 8 pp gap can look like evidence when it is noise in small regions. - Are you using the correct expansion factor? expr is the right one for regions;expc for municipalities. They are not interchangeable, and using the wrong one biases coverage estimates. - Is your analysis reproducible? A flow that cannot be audited cannot be defended before a technical counterpart, nor updated when CASEN 2026 is released. The CIs incorporated here are complex-design (Taylor linearization), not simple asymptotic ones. They cover sampling variance but not non-response error or undercoverage. Causal inference between subpopulations requires additional design. Top comments (0)