---
title: "Session 18 — Confounding intro (aid)"
author: "Prof. Dae-Jin Lee (daelee@faculty.ie.edu)"
output: html_document
---

```{r setup, message=FALSE, warning=FALSE}
library(tidyverse)
aid <- read_csv("data/aid_observational.csv")
```

```{r}
ggplot(aid, aes(aid_per_capita, economic_growth_pct)) +
  geom_point(alpha = 0.7) +
  geom_smooth(method = "lm", se = FALSE) +
  labs(
    title = "Aid and growth (observational)",
    x = "Aid per capita",
    y = "Economic growth (%)"
  )

m1 <- lm(economic_growth_pct ~ aid_per_capita, data = aid)
summary(m1)
```

**Interpret without causal language.** Which confounders might explain the slope? (Session 19 adjusts.)