Practical Biostatistics with R

Install the core R software and the R Studio Desktop IDE to enable using R, with platform-specific download links for Linux, Mac OS, and Windows.

Explore the RStudio interface—script, console, terminal, environment, plots, and help panes—and learn to create new projects, manage packages, and use git for version control and GitHub repositories.

Store data in variables, overwrite values as needed, and use hash comments to explain code; follow descriptive names and valid R assignment rules.

Explore how R functions encapsulate ready-made instructions, using the mean and correlation to analyze vectors like age, and learn how to pass arguments such as na.rm and access function help.

Explore how vectors in R store multiple values as a collection, create them with the c function, and build a data frame from age and purchase vectors.

Explore core R data types—numeric, integer, logical, and character—and how vectors coerce mixed values, plus data frames, matrices, and tibbles in base and tidyverse datasets.

Learn to manipulate data frames in R using the air quality data example, including extracting columns, subsetting, filtering, computing means and maximum values, and creating new columns with conditional logic.

Import data in R using a bookstore.csv example with read.csv, inspect structure with str, and export data using write.csv, including Excel import via the Open Excel library.

Convert vectors to factors to handle categorical data in r, inspect with table, and define levels and ordering, including dropping, reordering, and combining levels to create ordered factors.

Learn core math operations in R, including absolute values, square roots, logs, exponentiation, trig and exponential functions, pi, modulo division, factorial, dot and vector sums, and the choose function.

Identify data types and apply the right statistical methods for primary and secondary data, including qualitative (nominal and ordinal) and quantitative (interval and ratio) measurements from surveys and hospital records.

Define nominal scale data as unordered categories without numerical magnitude and show how to count frequencies to derive proportions for variables like male, female, blood group, and marital status.

Explore ordinal scale data as a ranked extension of nominal scales, with examples like cancer stage and education levels, and learn about ordered factors in R.

Explore interval scale concepts by examining measurements expressed in numbers, with arbitrary starting points and no absolute zero, using temperature, IQ scores, and pH as examples.

Explain the ratio scale, its true zero point and interval structure, with examples like weight, height, age, and blood pressure, and how ratio scales relate to ordinal classifications.

Identify how variables are defined and classified as categorical or numerical, including nominal, ordinal, interval, and ratio, with examples like height, weight, IQ, and patient temperature.

Visualize biostatistical data with charts to communicate insights clearly, using histograms, bar charts, box plots, pie charts, scatter plots, and line graphs, and practice in a lab.

Visualize histograms showing the distribution of discrete or continuous data with bins, revealing frequency, shape, and left- or right-skewed patterns in weight data.

Learn bar charts for categorical data, using horizontal or vertical bars to compare categories like sleep time by mammalian order, and contrast with histograms by data type and spacing.

Explore box plots, known as box and whisker plots, to visualize central tendency—mean, median, and mode—from numerical data, where the red dot shows median and the box indicates interquartile range.

Explain how pie charts, a circular graph with slices, depict the frequency of categorical data and 100 percent total, using hypertension 37.5 percent and depression 6.2 percent as an example.

Use scatter plots to compare two continuous variables and explore their relationship, such as height and weight.

Explore how line graphs in R visualize quantitative data that changes over time, such as city population over decades or airline passengers from 1949 to 1960, plotting values by time.

Explore how a frequency polygon visualizes the distribution of a continuous variable, like a histogram, and how it can be derived from a histogram by joining plotted points.

Explore data visualization in R using ggplot2 to build histograms, bar charts, box plots, and pie charts, with dplyr for data summaries like mean sleep by order and top five.

Understand descriptive statistics as the data summary using measures of central tendency—mean, median, mode—and variability—range, variance, standard deviation, and interquartile range—often illustrated by box plots.

Master the mean, or average, including arithmetic, geometric, and harmonic means, with practical examples and a discussion of advantages, demerits, and when to use each.

Explain how the median is the middle value in sorted data, with odd observations yielding a middle value and even observations averaging the two middle numbers, especially with extreme values.

Identify the mode as the most frequently occurring value in a data set. Recognize bimodal, trimodal, and multimodal patterns when multiple values share the highest frequency.

Identify positive and negative skewness and interpret how mean, median, and mode diverge in symmetric versus skewed distributions with right and left tails.

Explore how to calculate central tendency measures in R using the birthweight data, including arithmetic, geometric, and harmonic means, plus mode, median, and skewness with packages mass, psych, and E1071.

Explore measures of partition by examining quartiles, including Q1, Q2 (median), and Q3, along with percentiles, and compute the interquartile range and semi interquartile range to describe data spread.

Explore percentiles, which divide a data set into 100 equal parts, with examples of the 25th, 50th, and 75th percentiles and the idea of a 90th percentile indicating high scores.

Deciles partition a data set into ten parts. Identify q1 as the second decile, the median as the fifth, and q3 as the seventh decile, highlighting high and low observations.

Load the nh dataset, clean missing bmi values with na.omit, and compute bmi quartiles and deciles using base R's quantile with the props argument, then categorize bmi into four groups.

Explore measures of dispersion and how observations deviate from the center. Understand the range as the difference between the highest and lowest values and its sensitivity to extreme values.

The variance measures how far observations spread from the mean, with the standard deviation as its square root. It is sensitive to outliers, units, and normality assumptions.

Use R to calculate standard deviation, the square root of the variance (sigma), and interpret its limitations with extreme values in real data; compare variability with the coefficient of variation.

Compare dispersion across units using the coefficient of variation, which divides the standard deviation by the mean and expresses it as a percentage.

In this lab, calculate and interpret spread using range, variance, and standard deviation for glucose data, and compare variability across units using the coefficient of variation.

Explore probability as a tool for inference in biostatistics, quantify uncertainty, and assess statistical significance while understanding how trial factors influence vaccine safety and effectiveness.

Define probability as the measure of the likelihood that an event occurs, ranging from 0 to 1. Differentiate classical, empirical, and subjective probability with examples like dice, coins, and weather.

Define core probability terms: experiment, trial, outcome, sample space, and equally likely; explain simple and compound events, mutually exclusive and independent events, plus complements, unions, and intersections.

Explore types of probability, including joint probability and mutual exclusivity, and apply conditional probability with examples like A given B. Distinguish independent and marginal probabilities for events A and B.

Apply the addition and multiplication rules of probability to compute the chance of disease A or B, including intersection. Compare mutually exclusive and independent events with example probabilities.

Explore classical and empirical probability through vaccine trials in R, using simulations, sample spaces, and probability rules (multiplication, addition, conditional) with ggplot visualizations.

Explore probability distributions by defining a distribution as the probabilities of all possible outcomes of a random variable, with examples like coin tosses, dice, and family birth data.

Explore random variables, their discrete and continuous forms, and how probability distributions describe outcomes with the probability mass function, probability density function, cumulative distribution function, and the expected value (mean).

explore binomial distribution for discrete outcomes, modeling the number of successes in n independent trials with two outcomes and constant probability p, and understand its mean and variability.

learn how the Poisson distribution models counts in a fixed interval using lambda as the average number of occurrences, especially for rare events, with mean equal to variance.

Understand the normal (gaussian) distribution, its bell shape and symmetry about the mean, apply the empirical rule with z-scores, and use the standard normal in R.

Explore practical biostatistics with R by applying binomial, Poisson, and normal distributions to real-world problems. Learn to compute exact and range probabilities and standardize data with z-scores and scale function.

Learn how statistical inference derives population conclusions from samples, using random, representative, homogeneous samples to estimate parameters and test hypotheses with measures like mean and standard deviation.

Explore point estimates for population parameters using the sample mean and sample proportion, and understand sampling distributions, the central limit theorem, and standard error in biostatistics.

Combine a point estimate with the standard error to form an interval estimate, producing a 95% confidence interval that bounds the population parameter and informs interpretations of zero or one.

load ggplot2 and dplyr, set a seed, generate normally distributed values, sample from the population, and visualize sampling distributions, confidence intervals, and standard errors via the central limit theorem.