Home ›
AP Statistics ›
Unit 1 ›
Visual Review
AP Statistics Unit 1 Visual Review
A topic-by-topic visual walkthrough of Unit 1: Exploring One-Variable Data and Collecting Data — variables, graphs, summary statistics, sampling, and experimental design.
← Back to Unit 1 hub
TOPIC 1.1
What Can We Learn from Data?
Statistics turns data into insight
Data are values collected about
individuals — but they always VARY.
Statistics is the science of learning from
data in the presence of that variability.
A good investigative question
A statistical question ANTICIPATES
variability in the answers.
"How tall are students here?" (varies) ✓
"How tall am I?" (one answer) ✗
The statistical process
1. Ask a question → 2. Collect data → 3. Analyze the data → 4. Draw a conclusion (in context).
Every unit of this course is a step in this cycle.
Statistics learns from data amid variability ; good questions anticipate it.
The Review Hub · AP Statistics Unit 1
TOPIC 1.2
Variables
Categorical variables
Values are LABELS / groups, not numbers
you do arithmetic on.
Examples: eye color, brand, yes/no,
grade level (as a category).
Summarize with counts & proportions.
Quantitative variables
NUMERICAL values you can do arithmetic
on (mean, etc.).
DISCRETE: countable (number of pets).
CONTINUOUS: measured (height, time).
Summarize with mean, median, SD.
The variable type decides the tools
A ZIP code looks numeric but is CATEGORICAL — you'd never average ZIP codes. Always ask what the number means.
Categorical = labels; quantitative = numbers you do arithmetic on.
The Review Hub · AP Statistics Unit 1
TOPIC 1.3
One Categorical Variable: Tables
FREQUENCY TABLE — favorite fruit
Apple 18 45%
Banana 14 35%
Cherry 8 20%
Total 40 100%
Frequency vs. relative frequency
FREQUENCY = the count in each category.
rel. freq = count / total
Relative frequency = the PROPORTION
(a %), useful for comparing groups.
18/40 = 0.45 = 45%
Proportions add to 1 (100%)
Relative frequencies of a single categorical variable always sum to 100% — a quick check on your table.
Summarize a category with counts and relative frequencies (count/total) .
The Review Hub · AP Statistics Unit 1
TOPIC 1.4
One Categorical Variable: Graphs
Apple Banana Cherry
bar chart (bars have gaps)
Bar charts & pie charts
BAR CHART: bar height = count or percent.
Bars have GAPS (categories are separate).
PIE CHART: slices show parts of a whole.
Describe what you see
Name the most/least common category and
compare their frequencies IN CONTEXT.
Bar order can be sorted for a cleaner display.
Show categories with bar charts (gaps) or pie charts .
The Review Hub · AP Statistics Unit 1
TOPIC 1.5
One Quantitative Variable: Graphs
histogram (bars touch)
value (binned) →
Graphs for numbers
HISTOGRAM: bars over intervals, TOUCHING
(the scale is continuous).
Also: dotplot, stemplot, boxplot.
Histogram vs. bar chart
Histogram = QUANTITATIVE, bars TOUCH.
Bar chart = CATEGORICAL, bars have GAPS.
Bin width changes the histogram's appearance.
Show quantitative data with a histogram (touching bars) , dotplot, or stemplot.
The Review Hub · AP Statistics Unit 1
TOPIC 1.6
Describing a Distribution
Describe SHAPE, CENTER, SPREAD — and OUTLIERS (in context)
Always mention all four when describing a quantitative distribution, and tie them to the real variable.
"SOCS": Shape, Outliers, Center, Spread.
Shape
symmetric
skewed right
Center & spread
CENTER: mean or median.
SPREAD: range, IQR, or SD.
Skewed → use MEDIAN + IQR.
Symmetric → use MEAN + SD.
Skew pulls the mean
Right-skew: mean > median.
Left-skew: mean < median.
The mean chases the tail;
the median resists it.
Describe Shape, Center, Spread, Outliers — skew pulls the mean toward the tail.
The Review Hub · AP Statistics Unit 1
TOPIC 1.7
Summary Statistics
// key formulas (on the AP formula sheet)
mean x̄ = (Σxᵢ) / n
std dev s = √( Σ(xᵢ − x̄)² / (n − 1) )
IQR = Q3 − Q1 range = max − min
Resistant vs. non-resistant
MEDIAN & IQR resist outliers.
MEAN & SD are pulled by outliers.
Use resistant measures for skewed data.
Worked example
Data 2, 4, 6, 8, 10: x̄ = 30/5 = 6.
s ≈ 3.16, median = 6, IQR = 8 − 4 = 4.
n − 1 in the SD denominator (sample SD).
x̄=Σx/n, s=√(Σ(x−x̄)²/(n−1)), IQR=Q3−Q1 ; median & IQR resist outliers.
The Review Hub · AP Statistics Unit 1
TOPIC 1.8
Boxplots & the Five-Number Summary
min Q1 median Q3 max outlier
The 1.5 × IQR outlier rule
outlier if x < Q1 − 1.5·IQR or x > Q3 + 1.5·IQR
The five-number summary is min, Q1, median, Q3, max. The box spans the IQR; whiskers reach the last non-outlier.
Boxplot shows the 5-number summary ; outliers are beyond Q1/Q3 ± 1.5·IQR.
The Review Hub · AP Statistics Unit 1
TOPIC 1.9
Comparing Distributions
Compare, don't just describe
When comparing two groups, use
COMPARATIVE language:
"Group A's median is HIGHER THAN B's."
Compare shape, center, spread, outliers
— explicitly, for BOTH groups.
Good tools for comparison
• SIDE-BY-SIDE boxplots
• Back-to-back stemplots
• Histograms on the SAME scale
Same axis scale makes fair comparison possible.
Always answer in context
A common FRQ loses points for describing groups separately instead of COMPARING them with words like "greater/less."
Use comparative language for shape, center, spread & outliers of both groups.
The Review Hub · AP Statistics Unit 1
TOPIC 1.10
Data Collection
Population vs. sample
POPULATION: the entire group of interest.
SAMPLE: the subset we actually study.
A PARAMETER describes the population;
a STATISTIC describes the sample.
parameter μ, p ← estimated by → statistic x̄, p̂
Census vs. sample
A CENSUS measures everyone — often too
costly or impossible.
A well-chosen sample lets us GENERALIZE
to the population — if it's random.
How we collect data decides what we can conclude.
Sampling vs. experiments
Random SAMPLING → generalize to a population. Random ASSIGNMENT (experiment) → establish cause and effect.
A parameter (μ, p) describes a population; a statistic (x̄, p̂) describes a sample.
The Review Hub · AP Statistics Unit 1
TOPIC 1.11
Random Sampling
Four random sampling methods
• SRS: every group of size n equally likely.
• STRATIFIED: split into similar strata,
SRS within each (boosts precision).
• CLUSTER: split into groups, randomly
pick whole clusters.
• SYSTEMATIC: pick every k-th individual
from a random start.
Randomness avoids bias & allows inference.
Why randomize?
Random selection makes the sample
REPRESENTATIVE in the long run and
removes human selection bias.
Only random samples justify generalizing
results to the whole population.
Stratified reduces variability by grouping
similar individuals together.
Larger samples shrink sampling variability.
Random sampling (SRS, stratified, cluster, systematic ) avoids bias & enables inference.
The Review Hub · AP Statistics Unit 1
TOPIC 1.12
Potential Problems with Sampling
Sources of bias
• UNDERCOVERAGE: some groups left out.
• NONRESPONSE: selected people don't reply.
• RESPONSE bias: untruthful/leading Qs.
• VOLUNTARY response: only strong opinions.
• CONVENIENCE: easiest-to-reach people.
Bias ≠ variability
BIAS = systematically off in one direction.
A bigger sample does NOT fix bias.
VARIABILITY = spread of estimates;
a larger sample DOES reduce it.
Fix bias with better METHOD, not more data.
Name the bias AND its direction
On the exam: identify the type of bias and say whether it makes the estimate too HIGH or too LOW.
Bias is systematic error a bigger sample can't fix; it only reduces variability.
The Review Hub · AP Statistics Unit 1
TOPIC 1.13
Experimental Design
Four principles
• CONTROL other variables (comparison).
• RANDOM ASSIGNMENT to treatments.
• REPLICATION (enough subjects).
• BLOCKING (group similar units, like
stratifying) when useful.
Key vocabulary
TREATMENT: what's applied to a group.
CONTROL group / PLACEBO: baseline.
BLIND: subjects don't know their group;
DOUBLE-BLIND: evaluators don't either.
CONFOUNDING: a variable tangled with the treatment.
Random assignment → causation
Only a randomized comparative EXPERIMENT can establish cause and effect. Observational studies only show association.
Experiments use control, random assignment, replication — random assignment proves causation.
The Review Hub · AP Statistics Unit 1
▤ Show all slides
How to use the visual review
Spend 30 seconds per slide before clicking next. Look at the graph, then ask yourself: "Could I describe this distribution with SOCS, or name this sampling method, from memory?"
Use the fullscreen button () on desktop for the best experience. Use arrow keys to navigate. Tap "Show all slides" to jump around.
This is great for review the night before the exam — fast, visual, and covers every display and idea you need to recognize in Unit 1.