Introduction to Data Science & Statistics

AnS 500 - Fall 2025

Author

Iowa State University

Published

November 15, 2025

Welcome

Welcome to Introduction to Data Science & Statistics (AnS 500) for Fall 2025!

Course Overview

This comprehensive 16-week course is divided into two parts, providing a complete foundation in data science and statistical methods for animal and agricultural sciences. All examples and exercises use R and Quarto for reproducible analysis.

Duration: 16 weeks (8 weeks per part) Format: 2 hours lecture per week + homework assignments Tools: R + Quarto exclusively Prerequisites: None (we start from the basics!)

Part 1: Introduction to Data Science (Weeks 1-8)

The first half introduces you to modern data science practices using R, RStudio, and the tidyverse ecosystem. You’ll learn to import, clean, transform, visualize, and communicate data effectively.

What You’ll Learn in Part 1

Foundations: Data science workflow, best practices, project organization
R & RStudio: Getting started, reading data (CSV, Excel)
Data Manipulation: dplyr for transforming and summarizing data
Visualization: ggplot2 for creating publication-quality plots
Advanced Topics: Reshaping data, joining datasets, iteration with purrr

Part 1 Chapters

Foundations of Data Science - What is data science? Best practices, R/RStudio/Quarto intro, Git/GitHub
R, RStudio & Reading Data - Interface, projects, packages, importing CSV/Excel
Data Types & Strings - Types, string manipulation, regex, intro to dplyr
Data Manipulation with dplyr - mutate, arrange, group_by, summarise, handling NAs
Introduction to ggplot2 - Grammar of Graphics, essential plot types, themes
Advanced ggplot2 - Faceting, statistical layers, combining plots
Reshaping & Joining - Tidy data, pivoting, joins, functional programming
Special Formats & Wrap-up - SAS/SPSS/Stata, Excel, janitor, complete workflow

Part 2: Introduction to Statistics (Weeks 9-16)

The second half builds on your data science skills to conduct statistical analyses. You’ll learn frequentist inference, hypothesis testing, and regression modeling.

What You’ll Learn in Part 2

Statistical Foundations: P-values, study design, experimental vs observational
Descriptive Statistics: Measures of central tendency and variability, EDA
Probability & Inference: Normal distribution, Central Limit Theorem, confidence intervals
Hypothesis Testing: t-tests, ANOVA, power, Type I/II errors
Regression: Simple and multiple linear regression, model diagnostics

Part 2 Chapters

Statistical Foundations - Frequentist vs Bayesian, p-values, RCTs, confounding
Descriptive Statistics - Mean, median, variance, SD, visualization, outliers
Probability Distributions - Normal distribution, CLT, sampling distributions
Hypothesis Testing - t-tests, null/alternative hypotheses, power
ANOVA - One-way ANOVA, post-hoc tests, multiple comparisons
Categorical Data - Chi-square, Fisher’s exact, odds ratios
Simple Linear Regression - Correlation, least squares, diagnostics
Multiple Regression - Multiple predictors, model comparison, variable selection

R Packages Used

This course makes extensive use of R packages from the tidyverse ecosystem and beyond.

Part 1 Packages (Data Science)

# Core tidyverse
install.packages("tidyverse")

# Additional Part 1 packages
install.packages(c(
  "readxl",      # Read Excel files
  "writexl",     # Write Excel files
  "haven",       # Read SAS/SPSS/Stata files
  "janitor",     # Data cleaning
  "lubridate",   # Date/time manipulation
  "cowplot",     # Combining plots
  "patchwork",   # Combining plots (alternative)
  "here",        # Project-relative paths
  "glue"         # String interpolation
))

Part 2 Packages (Statistics)

install.packages(c(
  "broom",       # Tidy statistical output
  "car",         # Companion to Applied Regression
  "effsize",     # Effect size calculations
  "ggpubr",      # Publication-ready plots
  "rstatix",     # Pipe-friendly statistical tests
  "gt",          # Grammar of Tables
  "emmeans"      # Estimated marginal means
))

Course Philosophy

This course emphasizes:

Tidyverse-first approach: Modern R practices from day one
Reproducible research: Every analysis in Quarto
Real-world data: Animal and agricultural science datasets with real messiness
Best practices early: Project organization, naming conventions, version control
Statistical thinking: Understanding over button-pushing
Build incrementally: Each week builds on previous skills

Getting Started

Navigate through the chapters using the sidebar on the left. Each chapter includes:

Lecture content with conceptual explanations
R code examples you can run and modify
Visualizations to build intuition
Practice exercises and homework assignments

Let’s begin your statistical journey!

# Welcome {.unnumbered} Welcome to **Introduction to Data Science & Statistics** (AnS 500) for Fall 2025! ## Course Overview This comprehensive 16-week course is divided into two parts, providing a complete foundation in data science and statistical methods for animal and agricultural sciences. All examples and exercises use R and Quarto for reproducible analysis. **Duration**: 16 weeks (8 weeks per part) **Format**: 2 hours lecture per week + homework assignments **Tools**: R + Quarto exclusively **Prerequisites**: None (we start from the basics!) --- ## Part 1: Introduction to Data Science (Weeks 1-8) The first half introduces you to modern data science practices using R, RStudio, and the tidyverse ecosystem. You'll learn to import, clean, transform, visualize, and communicate data effectively. ### What You'll Learn in Part 1 - **Foundations**: Data science workflow, best practices, project organization - **R & RStudio**: Getting started, reading data (CSV, Excel) - **Data Manipulation**: `dplyr` for transforming and summarizing data - **Visualization**: `ggplot2` for creating publication-quality plots - **Advanced Topics**: Reshaping data, joining datasets, iteration with `purrr` ### Part 1 Chapters 1. **Foundations of Data Science** - What is data science? Best practices, R/RStudio/Quarto intro, Git/GitHub 2. **R, RStudio & Reading Data** - Interface, projects, packages, importing CSV/Excel 3. **Data Types & Strings** - Types, string manipulation, regex, intro to dplyr 4. **Data Manipulation with dplyr** - mutate, arrange, group_by, summarise, handling NAs 5. **Introduction to ggplot2** - Grammar of Graphics, essential plot types, themes 6. **Advanced ggplot2** - Faceting, statistical layers, combining plots 7. **Reshaping & Joining** - Tidy data, pivoting, joins, functional programming 8. **Special Formats & Wrap-up** - SAS/SPSS/Stata, Excel, janitor, complete workflow --- ## Part 2: Introduction to Statistics (Weeks 9-16) The second half builds on your data science skills to conduct statistical analyses. You'll learn frequentist inference, hypothesis testing, and regression modeling. ### What You'll Learn in Part 2 - **Statistical Foundations**: P-values, study design, experimental vs observational - **Descriptive Statistics**: Measures of central tendency and variability, EDA - **Probability & Inference**: Normal distribution, Central Limit Theorem, confidence intervals - **Hypothesis Testing**: t-tests, ANOVA, power, Type I/II errors - **Regression**: Simple and multiple linear regression, model diagnostics ### Part 2 Chapters 1. **Statistical Foundations** - Frequentist vs Bayesian, p-values, RCTs, confounding 2. **Descriptive Statistics** - Mean, median, variance, SD, visualization, outliers 3. **Probability Distributions** - Normal distribution, CLT, sampling distributions 4. **Hypothesis Testing** - t-tests, null/alternative hypotheses, power 5. **ANOVA** - One-way ANOVA, post-hoc tests, multiple comparisons 6. **Categorical Data** - Chi-square, Fisher's exact, odds ratios 7. **Simple Linear Regression** - Correlation, least squares, diagnostics 8. **Multiple Regression** - Multiple predictors, model comparison, variable selection --- ## R Packages Used This course makes extensive use of R packages from the tidyverse ecosystem and beyond. ### Part 1 Packages (Data Science) ```r # Core tidyverse install.packages("tidyverse") # Additional Part 1 packages install.packages(c( "readxl", # Read Excel files "writexl", # Write Excel files "haven", # Read SAS/SPSS/Stata files "janitor", # Data cleaning "lubridate", # Date/time manipulation "cowplot", # Combining plots "patchwork", # Combining plots (alternative) "here", # Project-relative paths "glue" # String interpolation )) ``` ### Part 2 Packages (Statistics) ```r install.packages(c( "broom", # Tidy statistical output "car", # Companion to Applied Regression "effsize", # Effect size calculations "ggpubr", # Publication-ready plots "rstatix", # Pipe-friendly statistical tests "gt", # Grammar of Tables "emmeans" # Estimated marginal means )) ``` ## Course Philosophy This course emphasizes: - **Tidyverse-first approach**: Modern R practices from day one - **Reproducible research**: Every analysis in Quarto - **Real-world data**: Animal and agricultural science datasets with real messiness - **Best practices early**: Project organization, naming conventions, version control - **Statistical thinking**: Understanding over button-pushing - **Build incrementally**: Each week builds on previous skills ## Getting Started Navigate through the chapters using the sidebar on the left. Each chapter includes: - Lecture content with conceptual explanations - R code examples you can run and modify - Visualizations to build intuition - Practice exercises and homework assignments Let's begin your statistical journey!