we have data about people, their heights, and other covariates. We want to find the proportion of men with different heights. However, we can’t assume validity since the measurements might have varied (like if they were wearing shoes or not).However, stability may not hold since an influx of immigrants may change the height average.We modeled the dependent variable, height, using an intercept-only regression.
nhanes |>
filter(sex == "Male", age >= 18) |>
select(height) |>
drop_na() |>
ggplot(aes(x = height)) +
geom_histogram(bins = 50) +
labs(
title = "Male Adult Height in the US in 2010",
x = "Height (cm)",
y = "Count",
caption = "Source: National Health and Nutrition Examination Servey")
Warning: Rows containing NAs were excluded from the model.Characteristic |
Beta |
95% CI 1 |
|---|---|---|
| (Intercept) | 162 | 161, 162 |
| 1
CI = Credible Interval |
||
# A tibble: 1 × 2
.row odds
<int> <dbl>
1 1 0.185