📊 Descriptive Statistics in RStudio Using Base R — Part 7: Complete Descriptive Statistics Example
How do all the descriptive statistics we have learned come together in a real data analysis?
In Part 7 of our Descriptive Statistics in RStudio Using Base R series, we bring everything together by performing a complete descriptive analysis from beginning to end using a realistic student-performance dataset.
Rather than calculating individual statistics in isolation, this lesson demonstrates a systematic statistical workflow:
Inspect → Check Data Quality → Summarize → Compare → Interpret
Using Base R only, we examine the structure of the dataset, identify variable types, investigate missing observations, summarize quantitative and categorical variables, compare groups, and—most importantly—interpret the results in context.
💻 Topics covered in this video include:
• Inspecting a dataset before beginning statistical analysis
• Using `head()`, `str()`, `names()`, `dim()`, `nrow()`, and `ncol()`
• Distinguishing quantitative, categorical, and identifier variables
• Checking for missing observations before calculating statistics
• Using `is.na()`, `colSums()`, and `colMeans()` to examine missingness
• Using `summary()` for an initial quantitative summary
• Calculating the mean and median
• Calculating standard deviation and IQR
• Understanding center and variability together
• Reporting the effective sample size when observations are missing
• Creating frequency tables with `table()`
• Calculating proportions and percentages with `prop.table()`
• Including missing categories using `useNA = “ifany”`
• Comparing quantitative variables across groups with `tapply()`
• Comparing group means, medians, and standard deviations
• Creating two-way frequency tables
• Calculating within-group percentages
• Interpreting descriptive differences across groups
• Distinguishing descriptive analysis from statistical inference
• Communicating statistical results in context
⚠️ Descriptive Comparison ≠ Statistical Inference
If one group has a higher observed mean than another group, we can describe that difference in our dataset. However, descriptive statistics alone do not establish that the groups differ in a larger population, and they do not establish a causal relationship.
That requires additional statistical methods and appropriate study design.
📚 This video brings together the complete series:
Part 1 — Getting Started with Descriptive Statistics
Part 2 — Measures of Center: Mean, Median, and Mode
Part 3 — Measures of Variability: Range, Variance, Standard Deviation, and IQR
Part 4 — Quartiles, Quantiles, Percentiles, and the Five-Number Summary
Part 5 — Frequency Tables and Categorical Data
Part 6 — Missing Data and Descriptive Statistics
Part 7 — Complete Descriptive Statistics Example
💡 Key takeaway:
R calculates. You analyze. You interpret.
Learning R commands is important
source