Tour and table of contents
A bit about this course and the history of this book. Learning in this era. Goals of this book. How to use this book.
An example mini chapter introducing Explanatory and response variables and Types of categorical and continuous variables.
An introduction to the goals of statistics and challenges faced while pursuing these goals. Goals of biostatistics. Sampling from populations. Models and Hypothesis Testing. Inferring cause
Getting you up and running in R, with the ultimate goal of being able to load and look at data. Coding for biostats. Why use R?. Observations and suggestions for learning R / computer stuff. Getting RStudio working. A tour of the Rstudio environment. Intro to R. Assigning variables in R. Using functions in R. R Packages. Loading data in R. Looking into your data. R scripts
RSimple things we commonly do to data. The Tidy data structure, Wrangling data in R, Modify data with mutate, Summarize data, Combine summarize with group_by() to summarize by groups. Change variable type with mutate, A simple mutate() to change class, Use Large Language Models to help you code.
How we summarize our data! Measures of location: Summarizing the location of our data in R, Summarizing shape of data, Skewness, Number of modes, Measures of width, Boxplots and Interquartile range (IQR), Variance, Standard Deviation & Coefficient of Variation, Parameters and estimates, Rounding
A quick intro to data visualization: Exploratory and explanatory visualizations, Centering plots on biology.
**The idea of ggplot: Mapping aesthetics onto variables – Scatterplots, A categorical explanatory variable. Small multiples.
We take estimates from samples because we (almost) never have access to the entire population.
Populations have parameters.
Estimate population parameters by sampling: (Avoiding) Sampling Bias, (Avoiding) non-independence of Samples, There is no avoiding sampling Error.
The sampling distribution, Building a sampling distribution, by repeatedly sampling, by simulation, or by math.
The Standard Error – Minimizing sampling error, Be wary of exceptional results from small samples, Small samples, overestimation, and the file drawer problem.
Describing uncertainty in our estimates, because we don’t have populations.
Review: We estimate population parameters from samples.
Estimation with uncertainty, Generating a sampling distribution, Resampling from our sample (Bootstrapping).
Estimating the standard error, The bootstrap standard error
Confidence intervals, The bootstrap confidence interval,
Visualizing uncertainty,
Common mathematical rules of thumb
R Review and pRactice.