Lessons and exercises follow the school system and stay in its language.Les leçons et les exercices suivent le système scolaire et restent dans sa langue.Lektionen und Übungen folgen dem Schulsystem und bleiben in seiner Sprache.
Every lesson of the chapter, ready for paper. Exercise sets are lettered A, B, C… and answered at the end.
To save a PDF, choose “Save as PDF” in the print dialog.
Statistics (AP-aligned)
Collecting data
NicknameDate
Scan to open onlineenglish.sedifier.com/en-us/us-ma-2017/statistics/us.stats.collecting-data/
1. Populations, samples, parameters and statistics
Warm-up
Three quick questions from earlier lessons.
A survey of 23 students records the following. Tick all the categorical variables.
Eye color
ZIP code
Takes the bus to school (yes/no)
Height in cm
Number of siblings
Area codes such as 770 are numbers. Is the area code of a phone number a quantitative variable?
No: it is categorical, a label that only looks like a number
Yes: its values are numbers
Yes, a discrete quantitative variable
A study measures the resting heart rate of 29 runners. What are the cases (observational units)?
The 29 runners
The heart rates
The number 29
Discover
A poll of 1,000 voters finds 52% support for a candidate. Is 52% the support among all voters?
Not exactly: it estimates it
Yes
Key idea
We study a sample to learn about a population.
The population is the whole group of interest; a sample is the part we actually observe. A parameter is a number describing the population (usually unknown); a statistic is a number computed from the sample, used to estimate the parameter.
Worked example
A factory tests 200 of today's 10,000 bulbs; 3% are faulty.
Population: the 10,000 bulbs
Everything produced today.
Sample: the 200 bulbs
Those tested.
3% is a statistic estimating the faulty rate today
Computed from the sample.
Your turn, guided
Your turn: how many faulty bulbs were found in the sample?
6
3% of 200.
Practice ★
A researcher measures the sleep of 376 randomly chosen teenagers and finds a mean of 7.1 hours. What is 7.1?
A statistic: it describes the sample
A parameter: it describes all teenagers
The population
To learn how much US college students spend on books, a team surveys 671 students at 20 colleges. What is the population?
All US college students
The 671 students surveyed
The 20 colleges
Watch out!
Practice ★★
Census records show that 52% of all households in a town own a car. What is 52%?
A parameter: it describes the whole population
A statistic
A sample proportion
Exit ticket
Three questions to check you have got it.
A researcher measures the sleep of 376 randomly chosen teenagers and finds a mean of 7.1 hours. What is 7.1?
A statistic: it describes the sample
A parameter: it describes all teenagers
The population
A researcher measures the sleep of 288 randomly chosen teenagers and finds a mean of 7.1 hours. What is 7.1?
A statistic: it describes the sample
A parameter: it describes all teenagers
The population
A researcher measures the sleep of 121 randomly chosen teenagers and finds a mean of 7.1 hours. What is 7.1?
A statistic: it describes the sample
A parameter: it describes all teenagers
The population
Summary card
Population and sample
Population → parameter (usually unknown).
Sample → statistic (an estimate).
Watch out: a number from the sample is a statistic.
One more step is optional: a challenge. Try it, or finish the lesson now.
Challenge ★★★
In a random sample of students from a school of 300 students, 26% walk to school. Estimate how many students in the whole school walk.
A researcher measures the sleep of 376 randomly chosen teenagers and finds a mean of 7.1 hours. What is 7.1?
A statistic: it describes the sample
A parameter: it describes all teenagers
The population
To learn how much US college students spend on books, a team surveys 671 students at 20 colleges. What is the population?
All US college students
The 671 students surveyed
The 20 colleges
Census records show that 52% of all households in a town own a car. What is 52%?
A parameter: it describes the whole population
A statistic
A sample proportion
Discover
A school has 600 juniors and 400 seniors. You want a sample of 50 that reflects both grades. How many juniors?
30
25
Key idea
Random sampling methods.
Simple random sample (SRS): every group of n individuals is equally likely. Stratified: split into similar groups (strata) and take an SRS from each. Cluster: split into groups (clusters), choose some clusters at random, take everyone in them. Systematic: a random start, then every kth individual.
Worked example
A list of 2,400 members; a systematic sample of 80.
Step k=30
2,400 ÷ 80.
Start at, say, member 17
Random start among the first 30.
17, 47, 77, … up to 80 members
Then add 30 each time.
Your turn, guided
Your turn: 900 members, systematic sample of 45. The step.
k=20
900 ÷ 45.
Practice ★
A school has 600 juniors and 300 seniors. A stratified sample of 90 students is taken in proportion to grade. How many juniors are in the sample?
A school has 500 juniors and 600 seniors. A stratified sample of 110 students is taken in proportion to grade. How many juniors are in the sample?
A systematic sample of 28 customers is taken from a list of 140: a random start, then every kth name. What is k?
Watch out!
Practice ★★
A district has 60 classrooms. Five are chosen at random and every student in them is surveyed. Which sampling method is this?
Cluster sampling
Stratified sampling
A simple random sample of students
Exit ticket
Three questions to check you have got it.
A school has 600 juniors and 300 seniors. A stratified sample of 90 students is taken in proportion to grade. How many juniors are in the sample?
A school has 500 juniors and 600 seniors. A stratified sample of 110 students is taken in proportion to grade. How many juniors are in the sample?
A school has 900 juniors and 800 seniors. A stratified sample of 170 students is taken in proportion to grade. How many juniors are in the sample?
Summary card
Sampling methods
SRS · stratified (some from every group) · cluster (all from some groups) · systematic (every kth).
Watch out: proportional allocation in stratified samples.
One more step is optional: a challenge. Try it, or finish the lesson now.
Challenge ★★★
A district has 50 classrooms of 20 students. A cluster sample picks 7 classrooms at random and surveys every student in them. How many students are surveyed?
3. Bias in sampling
Warm-up
Three quick questions from earlier lessons.
A school has 600 juniors and 300 seniors. A stratified sample of 90 students is taken in proportion to grade. How many juniors are in the sample?
A systematic sample of 28 customers is taken from a list of 140: a random start, then every kth name. What is k?
A district has 60 classrooms. Five are chosen at random and every student in them is surveyed. Which sampling method is this?
Cluster sampling
Stratified sampling
A simple random sample of students
Discover
A TV show asks viewers to text in their opinion; 50,000 do. Is that a better sample than 1,000 randomly chosen adults?
No, the random 1,000 is better
Yes, it is 50 times bigger
Key idea
Bias is a systematic error from how data are collected.
Voluntary response: people choose to respond. Convenience sampling: easy-to-reach individuals. Undercoverage: part of the population cannot be chosen. Nonresponse: chosen people do not answer. Response bias: wording or setting distorts answers. A larger sample does not reduce bias.
Worked example
A survey by phone at 2 p.m. on weekdays.
Working adults are rarely reached
Who is home?
Undercoverage
They cannot be in the sample.
The bias does not shrink with more calls
The estimate leans towards people at home.
Your turn, guided
Your turn: of 1,200 people chosen, 300 answered. The response rate as a fraction:
41
300 ÷ 1,200: a high risk of nonresponse bias.
Practice ★
A news website asks readers to vote online; 4824 vote and 80% favor a new law. What is the main problem?
Voluntary response bias: people with strong opinions choose to respond
The sample is too small
None: 4824 responses are representative
A survey of 115 adults is done by calling landline numbers. What kind of bias is most likely?
Undercoverage: people without landlines cannot be chosen
Response bias from the wording
None, if the numbers are chosen at random
Watch out!
Practice ★★
A biased survey of 238 people is repeated with 10 times as many people, chosen the same way. What happens to the bias?
It stays: a larger sample reduces random variability, not bias
It disappears
It becomes 10 times smaller
A biased survey of 402 people is repeated with 10 times as many people, chosen the same way. What happens to the bias?
It stays: a larger sample reduces random variability, not bias
It disappears
It becomes 10 times smaller
Exit ticket
Three questions to check you have got it.
A news website asks readers to vote online; 4824 vote and 80% favor a new law. What is the main problem?
Voluntary response bias: people with strong opinions choose to respond
The sample is too small
None: 4824 responses are representative
A news website asks readers to vote online; 1714 vote and 80% favor a new law. What is the main problem?
Voluntary response bias: people with strong opinions choose to respond
The sample is too small
None: 1714 responses are representative
A news website asks readers to vote online; 3716 vote and 80% favor a new law. What is the main problem?
Voluntary response bias: people with strong opinions choose to respond
Watch out: a bigger biased sample is still biased.
One more step is optional: a challenge. Try it, or finish the lesson now.
Challenge ★★★
A phone survey of a town of 2200 adults can only reach the 52% who have a listed number. How many adults can never be chosen (undercoverage)?
4. Observational studies, experiments and confounding
Warm-up
Three quick questions from earlier lessons.
A researcher measures the sleep of 376 randomly chosen teenagers and finds a mean of 7.1 hours. What is 7.1?
A statistic: it describes the sample
A parameter: it describes all teenagers
The population
To learn how much US college students spend on books, a team surveys 671 students at 20 colleges. What is the population?
All US college students
The 671 students surveyed
The 20 colleges
Census records show that 52% of all households in a town own a car. What is 52%?
A parameter: it describes the whole population
A statistic
A sample proportion
Discover
Cities with more firefighters at a fire have more damage. Do firefighters cause damage?
No, bigger fires explain both
Yes, the data show it
Key idea
Only experiments can show cause and effect.
In an observational study we record what happens without intervening; in an experiment we impose treatments. A confounding variable is related to both the explanatory and the response variable, so its effect cannot be separated. Observational studies show associations, not causation.
Worked example
Students who take music lessons have higher grades.
Observational study
Nobody assigned the lessons.
Possible confounder: family income
Affects both lessons and grades.
Conclusion: association only
To test cause, assign lessons at random.
Your turn, guided
Your turn: 80 volunteers are split at random, 40 per group. How many get the treatment?
40
Half of 80.
Practice ★
Researchers randomly assign 66 volunteers to drink coffee or water, then test their reaction times. What kind of study is it?
An experiment: the researchers assign the treatment
An observational study
A sample survey
Children with bigger shoes read better (16% higher scores). What is the most likely explanation?
A confounding variable: age affects both shoe size and reading
Bigger feet improve reading
It must be pure chance
Watch out!
Practice ★★
An observational study of 3416 adults finds that those who eat breakfast weigh less. Does this show that eating breakfast causes lower weight?
No: other differences between the groups could explain it
Yes, because the sample is large
Yes, if the association is strong
An observational study of 5700 adults finds that those who eat breakfast weigh less. Does this show that eating breakfast causes lower weight?
No: other differences between the groups could explain it
Yes, because the sample is large
Yes, if the association is strong
Exit ticket
Three questions to check you have got it.
Researchers randomly assign 66 volunteers to drink coffee or water, then test their reaction times. What kind of study is it?
An experiment: the researchers assign the treatment
An observational study
A sample survey
Researchers randomly assign 166 volunteers to drink coffee or water, then test their reaction times. What kind of study is it?
An experiment: the researchers assign the treatment
An observational study
A sample survey
Researchers randomly assign 46 volunteers to drink coffee or water, then test their reaction times. What kind of study is it?
An experiment: the researchers assign the treatment
An observational study
A sample survey
Summary card
Studies
Observational: record. Experiment: assign.
Confounding hides cause in observational data.
Watch out: association is not causation.
One more step is optional: a challenge. Try it, or finish the lesson now.
Challenge ★★★
In an experiment, 200 randomly chosen people get a drug and 200 get a placebo. 73 and 58 people improve. By how many percentage points is the drug group's rate higher?
Researchers randomly assign 66 volunteers to drink coffee or water, then test their reaction times. What kind of study is it?
An experiment: the researchers assign the treatment
An observational study
A sample survey
Children with bigger shoes read better (16% higher scores). What is the most likely explanation?
A confounding variable: age affects both shoe size and reading
Bigger feet improve reading
It must be pure chance
An observational study of 3416 adults finds that those who eat breakfast weigh less. Does this show that eating breakfast causes lower weight?
No: other differences between the groups could explain it
Yes, because the sample is large
Yes, if the association is strong
Discover
To compare two fertilizers, you put fertilizer A on the sunny half of a field and B on the shady half. A grows better. What is the flaw?
Sunlight, not the fertilizer, could explain the difference
There is no flaw
Key idea
Principles of experimental design.
Comparison of treatments (often with a control or placebo group); random assignment of units to treatments; replication on enough units; blocking groups similar units first and randomizes within each block. With several factors, the treatments are all combinations of their levels.
Worked example
Test 2 doses × 3 diets on 60 rats.
Treatments: 2×3=6
Each combination.
10 rats per treatment
Replication.
Shuffle the rats into the 6 groups
Random assignment.
Your turn, guided
Your turn: 3 temperatures × 4 times. Number of treatments.
12
3 × 4.
Practice ★
Why are 196 subjects assigned to the treatments at random?
To balance other variables between the groups, so differences can be blamed on the treatment
So the results apply to the whole population
To give every subject the same chance of being in the study
An experiment tests 2 fertilizer types at 3 watering levels, with every combination used. How many treatments are there?
An experiment tests 9 fertilizer types at 12 watering levels, with every combination used. How many treatments are there?
Watch out!
Practice ★★
A test of two diets on 115 adults first splits them into men and women, then randomizes diets within each group. What is this design?
A randomized block design, blocking by sex
A stratified random sample
A completely randomized design
Exit ticket
Three questions to check you have got it.
An experiment tests 2 fertilizer types at 3 watering levels, with every combination used. How many treatments are there?
An experiment tests 9 fertilizer types at 12 watering levels, with every combination used. How many treatments are there?
An experiment tests 8 fertilizer types at 9 watering levels, with every combination used. How many treatments are there?
Watch out: blocks (experiments) vs strata (samples).
One more step is optional: a challenge. Try it, or finish the lesson now.
Challenge ★★★
An experiment crosses 2 fertilizers with 2 watering levels, and each treatment is used on 3 plants. How many plants are needed?
6. Scope of inference: generalization and causation
Warm-up
Three quick questions from earlier lessons.
A school has 600 juniors and 300 seniors. A stratified sample of 90 students is taken in proportion to grade. How many juniors are in the sample?
A systematic sample of 28 customers is taken from a list of 140: a random start, then every kth name. What is k?
A district has 60 classrooms. Five are chosen at random and every student in them is surveyed. Which sampling method is this?
Cluster sampling
Stratified sampling
A simple random sample of students
Discover
A randomized experiment on 50 volunteer athletes shows a supplement improves sprint times. Can you say it helps all adults?
No, only for these volunteers
Yes, it was a randomized experiment
Key idea
Two kinds of randomness, two kinds of conclusions.
Random sampling → results can be generalized to the population. Random assignment → differences can be attributed to the treatment (cause and effect). Both → causal conclusions about the population. Blinding (single or double) and placebos keep expectations from affecting the results.
Worked example
Four studies.
Volunteers, no assignment: association in these people only
Neither.
Random sample, no assignment: association in the population
Sampling only.
Volunteers, random assignment: cause, in these subjects
Assignment only.
Your turn, guided
Your turn: how many of the four combinations (sampling yes/no × assignment yes/no) allow a causal conclusion about the whole population?
1
Only both random sampling and random assignment.
Practice ★
A random sample of 493 adults in a city shows that those who walk to work report less stress. No treatment was assigned. What can be concluded?
The association can be generalized to adults in the city, but not cause and effect
Walking causes less stress for adults in the city
Nothing beyond the 493 people sampled
147 volunteers are randomly assigned to a new or old teaching method; the new method scores higher. What can be concluded?
The method caused the difference for these volunteers; generalizing beyond them is risky
The new method works better for all students
Nothing, because there was no random sample
Watch out!
Practice ★★
In a drug trial with 64 patients, neither the patients nor the doctors who assess them know who receives the drug. What is this called?
A double-blind experiment
A placebo
Blocking
Exit ticket
Three questions to check you have got it.
A random sample of 493 adults in a city shows that those who walk to work report less stress. No treatment was assigned. What can be concluded?
The association can be generalized to adults in the city, but not cause and effect
Walking causes less stress for adults in the city
Nothing beyond the 493 people sampled
A random sample of 530 adults in a city shows that those who walk to work report less stress. No treatment was assigned. What can be concluded?
The association can be generalized to adults in the city, but not cause and effect
Walking causes less stress for adults in the city
Nothing beyond the 530 people sampled
A random sample of 712 adults in a city shows that those who walk to work report less stress. No treatment was assigned. What can be concluded?
The association can be generalized to adults in the city, but not cause and effect
Walking causes less stress for adults in the city
Nothing beyond the 712 people sampled
Summary card
Scope of inference
Random sampling → generalize.
Random assignment → cause.
Watch out: you need both for a causal claim about a population.
One more step is optional: a challenge. Try it, or finish the lesson now.
Challenge ★★★
In a random sample of 200 adults from a city of 17000, 50 walk to work. Estimate how many adults in the city walk to work.
7. Randomized response
Discover
A survey asks 'Have you ever cheated on a test?'. Many people would lie. Here is a trick: each person flips a coin in secret. Heads: answer truthfully. Tails: just say 'yes'. Can we still estimate the true rate?
Yes: we know half the 'yes' answers come from tails
No: the coin destroys the information
Key idea
Randomized response.
With a fair coin (heads: truth, tails: 'yes'):
P(yes)=21p+21, so p=2P(yes)−1,
where p is the true proportion. Randomness protects each person but not the overall estimate.
Worked example
62 % of the answers are 'yes'.
p=2×0.62−1
Use the formula.
p=0.24: about 24 %
Compute.
Your turn, guided
Your turn: 70 % 'yes'. Estimate p.
0.4
2×0.7−1.
Practice ★
Randomized response with a fair coin: 71 % of the answers are 'yes'. Estimate the true proportion (as a decimal).
Randomized response with a fair coin: 69 % of the answers are 'yes'. Estimate the true proportion (as a decimal).
Randomized response with a fair coin: 94 % of the answers are 'yes'. Estimate the true proportion (as a decimal).
Practice ★★
Randomized response: 500 people answer and 420 say 'yes'. About how many of them truly are 'yes' people?
Randomized response: 400 people answer and 216 say 'yes'. About how many of them truly are 'yes' people?
Exit ticket
Two questions to check.
Randomized response with a fair coin: 71 % of the answers are 'yes'. Estimate the true proportion (as a decimal).
Randomized response with a fair coin: 69 % of the answers are 'yes'. Estimate the true proportion (as a decimal).
Summary card
Randomized response
p=2P(yes)−1 with a fair coin.
Privacy for each person, accuracy for the group.
Statistics offices use variants of this idea to protect people's privacy.
8. History of experiments: Fisher at Rothamsted
Discover
At an agricultural station, a scientist wants to know if a new fertilizer works. Some plots get it, others don't. How should he choose which plots get it?
At random
Give it to the best-looking plots
Key idea
Experiments, from fields to medicine.
Step 11837: the Rothamsted station is founded to study soils and plant growth.
Step 2Ronald Fisher1890–1962Barry Eagel, 1952. Barry Eagel. CC BY-SA 4.01890: Ronald Fisher is born; at Rothamsted he introduces randomization.
Step 3Ronald Fisher1890–1962Barry Eagel, 1952. Barry Eagel. CC BY-SA 4.01935: Fisher's The Design of Experiments.
At the Rothamsted Agricultural Experiment Station (founded 1837), Ronald Fisher (1890–1962) studied the design of experiments, introducing randomization and the analysis of variance. He collected his methods in The Design of Experiments (1935).
Worked example
20 plots, 10 to get the fertilizer. How many different random assignments are possible?
(1020)
Choose 10 plots out of 20.
=184756 possible assignments
Compute.
Practice ★
What did Fisher introduce in the design of experiments at Rothamsted?
Randomization and the analysis of variance
Polls of voters
The normal curve
4 plots are split at random into a treatment group and a control group of 2 each. How many assignments are possible?
6 plots are split at random into a treatment group and a control group of 3 each. How many assignments are possible?
Like Fisher: 3 fertilizers are compared, each on 9 randomly chosen plots. How many plots are needed?
Summary card
Experiments today
Medical trials assign treatments at random.
Tech companies test website changes with random A/B splits.
Farmers still compare seeds and fertilizers on randomized plots.
Sources: MacTutor biography of Fisher (see "Sources and credits").
Answers: Collecting data
1. Populations, samples, parameters and statistics
A
Eye color · ZIP code · Takes the bus to school (yes/no)
No: it is categorical, a label that only looks like a number