Warning: package 'skimr' was built under R version 4.4.1Warning: package 'brms' was built under R version 4.4.1Warning: package 'tidybayes' was built under R version 4.4.1Warning: package 'gtsummary' was built under R version 4.4.1Two Parameters
We have data from a National Health and Nutrition Examination survey done by the CDC from 2009 to 2011 with 15 variables. We want to know 3 things, the probability that the next man met is taller than 180 cm, the probability that among the next 4 men, the tallest is at least 10 cm taller than the shortest, and the posterior probability of the 3rd tallest man out of the next 100 men. We want to make a model of the height of adult men. To find this, we have filtered the data and plotted it into a graph. We then addressed the assumptions of stability, representativeness and unconfoundedness. We are doubting the assumption of stability as the average heights within a population can change due to outside forces such as immigration of taller people over time. Despite this, we will assume it is stable. We are using a bayesian regression model . The dependent variable, height is modeled using an intercept-only regression. The chance of the next individual being taller than 180 cm is around 30%, though this may not apply to the whole world, as the data was from the US. The average height of an adult man in America in 2024 is 176 cm with a 7.48 cm standard deviation.
Characteristic |
Beta |
95% CI 1 |
|---|---|---|
| (Intercept) | 176 | 176, 176 |
| 1
CI = Credible Interval |
||
# A tibble: 1 × 2
.row odds
<int> <dbl>
1 1 0.284