Math I · S-ID.9

Distinguishing Correlation from Causation

This objective protects students from one of the most common reasoning errors in the modern world: seeing two things move together and assuming one must cause the other.

Concept Statistics and Probability
Domain Interpreting Categorical and Quantitative Data
Read time 10 minutes

What this learning objective is really asking you to learn

This learning objective asks students to separate two ideas that people confuse constantly. Correlation means two variables are associated: they move together in some pattern. Causation means a change in one variable produces a change in another. Correlation is about relationship. Causation is about mechanism and influence.

If a data set shows that students who spend more hours studying tend to score higher on exams, there is a positive association. It may be tempting to say studying causes higher scores. That might be partly true, and it is consistent with common sense. But the data alone may not prove it. Students who study more may also have better attendance, more prior knowledge, quieter homes, stronger motivation, or more support. Those other variables may contribute to the relationship. To make a causal claim, we need stronger evidence than the association alone.

A lurking variable or confounding variable is an unmeasured factor that may influence the variables being studied. For example, suppose ice cream sales and drowning incidents are positively correlated. It would be absurd to claim that ice cream causes drowning. A third variable, hot weather, helps explain both: people buy more ice cream in hot weather and also swim more, which can increase drowning risk. The correlation is real, but the causal story is different.

There can also be reverse causation. Suppose a data set shows that people who visit doctors more often have worse health. It would be wrong to conclude that doctor visits cause poor health. More likely, people with worse health visit doctors more often. The direction of cause may run opposite the careless interpretation.

Sometimes two variables are correlated by coincidence. With enough data sets, strange associations will appear by chance. A graph may show two quantities rising together over time simply because both have long-term trends. For example, the number of people using smartphones and the price of some unrelated product might both increase over a decade. That does not mean one causes the other.

The objective does not say correlation is useless. Correlation is valuable. It can reveal patterns, generate hypotheses, support prediction, and motivate investigation. Many scientific discoveries begin with observed associations. But correlation is a starting point, not the finish line. Causal claims require asking: What is the mechanism? Could another variable explain the relationship? Was the study observational or experimental? Were participants randomly assigned? Is there supporting evidence from other sources? Does the timing make sense? Is the relationship consistent across settings?

Why students should learn this math

Students should learn this objective because false causal claims shape real decisions. People buy products, change diets, vote for policies, judge schools, accept medical advice, and form beliefs based on data claims. Many of those claims rest on confusing association with cause. A student who understands the distinction becomes less vulnerable to manipulation.

Advertising often uses correlation-like reasoning. A company may imply that people who use its product are healthier, happier, richer, or more successful. But maybe successful people are more likely to buy the product in the first place. Maybe the product is associated with a lifestyle, income level, or social group that explains the outcome. Without careful study design, the causal claim is weak.

News stories also need scrutiny. A headline might say that people who eat a certain food have lower rates of a disease. That could be important. But it could also reflect income, access to healthcare, exercise habits, age, geography, or many other factors. A responsible reader asks whether the study controlled for confounders, whether it was observational, whether the sample was large and representative, and whether the claim has been replicated.

Education data can be especially tricky. Suppose students in a tutoring program improve more than students not in the program. Did tutoring cause the improvement? Maybe. But perhaps students who joined the program were more motivated, had more family support, or started at a different level. A well-designed study would try to compare similar students or use random assignment when ethical and practical. The point is not to dismiss tutoring; the point is to demand evidence that matches the strength of the claim.

Public policy depends on causal reasoning. Cities want to know whether a new traffic rule reduces accidents, whether a housing policy lowers rent, whether a health campaign reduces disease, or whether a job-training program increases employment. Correlations can inform these questions, but policy decisions need causal evidence because actions have costs and consequences.

This objective is also deeply personal. Students make choices about sleep, study habits, exercise, screen time, spending, social life, and health. They will encounter many claims about what causes success or failure. Some are supported by strong evidence. Some are oversimplified. Some are marketing. Some are wishful thinking. Distinguishing correlation from causation is a survival skill for thinking clearly.

The historical machinery behind causal reasoning

The question of causation is older than statistics. Philosophers have long asked what it means for one thing to cause another. David Hume famously argued that we do not directly observe causation itself; we observe patterns of events, such as one event regularly following another, and we infer cause. This philosophical problem remains relevant. Data can show patterns, but interpretation requires reasoning.

Modern science developed methods for strengthening causal claims. Controlled experiments became powerful because they try to isolate the effect of one variable. If two groups are similar except for one treatment, and outcomes differ, the treatment becomes a more plausible cause. Random assignment is especially important because it helps balance both known and unknown factors between groups. This is why randomized experiments are often considered strong evidence for causation when they are ethical and well-designed.

Medicine illustrates the importance of causal reasoning. Observational data can suggest that a behavior or exposure is associated with disease, but researchers must consider confounding variables. The history of smoking and lung cancer is a major example of moving from association to causal conclusion through multiple lines of evidence: strong correlations, dose-response patterns, biological mechanisms, animal studies, time ordering, and replication across populations. Causation was not established by one scatter plot. It was established through a body of evidence.

Agriculture and manufacturing also shaped experimental design. Researchers such as Ronald Fisher developed methods for randomized experiments to test treatments, fertilizers, and conditions while accounting for variation. These methods influenced modern statistics deeply. Later, causal inference developed tools for observational settings where random assignment is not possible. Scientists and statisticians created methods to compare similar groups, adjust for confounders, use natural experiments, and analyze time patterns.

At the Math I level, students do not need advanced causal inference formulas. They need the core logic: association alone is not proof. A causal claim is stronger when the cause comes before the effect, alternative explanations are addressed, a plausible mechanism exists, and the result is supported by a careful design or multiple forms of evidence.

Technical execution: how to evaluate a causal claim

A good routine begins by identifying the variables. What is the supposed cause? What is the supposed effect? What data show the relationship? Is the claim based on a scatter plot, a two-way table, a regression line, a correlation coefficient, or a comparison of groups?

Next, describe the association without overclaiming. For example: “There is a positive association between exercise time and reported energy level.” That is safer and more accurate than “exercise causes higher energy” unless the study design supports causation. Students should practice using language such as associated with, related to, linked to, predicts, or tends to occur with when causation is not established.

Then ask whether the data come from an observational study or an experiment. In an observational study, researchers observe or measure variables without assigning treatments. Observational studies can reveal important associations, but they are vulnerable to confounding. In an experiment, researchers impose a treatment or condition, often using random assignment. Experiments can provide stronger evidence for causation because they are designed to isolate effects.

Next, look for confounding variables. A confounder is a variable that may influence both the supposed cause and the supposed effect. For a relationship between screen time and sleep, possible confounders include age, school schedule, stress, homework load, household rules, mental health, and device purpose. For a relationship between income and health, possible confounders include education, neighborhood, access to healthcare, diet, job conditions, and environmental exposure.

Also consider reverse causation. If people who use a certain app report more loneliness, does the app cause loneliness, or are lonely people more likely to use the app? If people who take more medicine have worse health, does medicine cause poor health, or do sicker people take more medicine? Direction matters.

Check time order. A cause must happen before its effect. If the supposed cause occurs after the effect, the causal claim fails. Time order alone is not enough, but it is necessary.

Ask about mechanism. Is there a plausible explanation for how the cause could produce the effect? A mechanism does not prove causation by itself, but it strengthens the claim. Without a plausible mechanism, skepticism is reasonable.

Finally, ask what evidence would make the claim stronger. Could there be a randomized experiment? Could researchers compare similar groups? Could they collect data over time? Could they control for confounders? Could they replicate the result? A student does not need to design a full research study, but they should know what kind of evidence is missing.

A concrete example

Suppose a school survey finds that students who participate in after-school clubs have higher average grades than students who do not. The association is positive. It might be tempting to conclude that clubs cause higher grades.

A careful student says: the data show an association between club participation and grades, but they do not prove that clubs cause higher grades. Possible confounders include motivation, time-management skills, parental support, teacher relationships, transportation, and prior academic achievement. It is possible that students who already have strong grades are more likely to join clubs. It is also possible that clubs build belonging and responsibility, which may help grades. The association is worth investigating, but causation is not proven by the survey alone.

What would strengthen the causal claim? Researchers could compare students with similar prior grades, attendance, and background variables. They could track changes over time. They could study a program that randomly offers club access when demand exceeds capacity, if ethical. They could gather qualitative evidence about mechanisms. The point is not to reject the claim; the point is to match the conclusion to the evidence.

Correlation still matters

Some students overcorrect and think “correlation is not causation” means correlation is worthless. That is wrong. Correlation is often the first clue. If two variables are not associated at all, a causal relationship may be less likely, though not impossible in complex systems. Associations help researchers find questions worth studying. They help build predictive models. They help detect risk factors. They help monitor systems.

For example, a strong correlation between a machine's vibration pattern and future failure may be extremely useful even before the exact cause is understood. A correlation between weather conditions and crop yield can help farmers plan. A correlation between early warning signs and medical outcomes can help doctors decide what to monitor. Prediction and causation are related but different goals. A variable can be useful for prediction even if it is not the cause.

The mature view is this: correlation is evidence of association. It can support prediction. It can suggest hypotheses. It can contribute to a causal argument. But by itself, it does not settle cause. Students who understand this can use correlation without worshiping it.

Where this objective fits on the full map of mathematics

This objective is the final learning item in Integrated Math I, and that placement is meaningful. Math I begins with creating equations and modeling relationships. It moves through linear systems, functions, sequences, transformations, congruence, coordinate geometry, units, data displays, scatter plots, residuals, fitted lines, slope, intercept, and correlation. Objective 059 closes the course by asking students to think about evidence itself.

The big map is not just algebra, geometry, and statistics as separate islands. It is a network of reasoning tools. Algebra helps express relationships. Geometry helps represent structure. Statistics helps interpret variation. Modeling connects math to the world. Causal reasoning asks whether the model supports action.

This objective also prepares students for later probability and inference. In Math II, students will study probability and conditional probability, which help describe uncertainty and dependence. In Math III, they will study statistical inference, including sampling, experiments, observational studies, margins of error, and evaluating reports based on data. Correlation versus causation is the conceptual seed for all of that later work.

It also prepares students for adult data literacy. Many modern debates are not about whether a calculation was done, but whether the conclusion follows. A graph can be accurate and the claim can still be too strong. A correlation can be real and the causal story can still be wrong. Mathematics includes the discipline to stop where the evidence stops.

Common misconceptions and how to fix them

One misconception is that a strong correlation proves causation. It does not. A strong association can still be caused by a lurking variable, reverse causation, selection bias, or coincidence. Another misconception is that weak correlation proves no causation. A relationship might be non-linear, hidden by measurement error, or different across subgroups.

A third misconception is that experiments always prove causation perfectly. Experiments can provide strong evidence, but they can still be flawed by poor design, small samples, measurement problems, noncompliance, or lack of generalizability. A fourth misconception is that observational studies are useless. They are not. They can be very important, especially when experiments are unethical or impossible. But causal claims from observational data require extra care.

A fifth misconception is that saying “correlation is not causation” is a way to dismiss any evidence someone dislikes. That is lazy skepticism. The right response is not automatic rejection. The right response is careful evaluation: What is the evidence? What alternative explanations exist? What design was used? What would make the causal claim stronger?

Mastery looks like this

A student has mastered this objective when they can read a data-based claim and separate what the data show from what the speaker claims. They can say, “This shows an association, not necessarily causation.” They can name possible confounders. They can consider reverse causation. They can describe why random assignment matters. They can suggest what additional evidence would strengthen a causal claim. They can avoid both gullibility and lazy dismissal.

This objective is one of the most important “why” objectives in the entire high-school sequence. It teaches students that mathematics is not just computation. Mathematics is disciplined belief. It helps us decide what conclusions we are entitled to draw from evidence. That skill matters in school, work, science, health, politics, media, and everyday life.

Problem Library

Problems in the App From This Objective

147 problems across 12 archetypes in the app.

distinguish association language from cause-effect language.
12 problems Warmup Practice Mixed Review Assessment
Problem 1

Classify claim Students who sleep more tend to have higher scores. as correlational or causal.

Problem 2

Classify claim Extra sleep causes higher scores. as correlational or causal.

Problem 3

Classify claim Cities with more parks are associated with higher activity levels. as correlational or causal.

Problem 4

Classify claim The new fertilizer increased plant growth in the randomized experiment. as correlational or causal.

Problem 5

Classify claim People who meditate regularly report lower stress levels. as correlational or causal.

Problem 6

Classify claim A specific vaccine prevents the spread of the virus. as correlational or causal.

Open in simulator
Problem 7

Classify claim Countries with higher GDP per capita often have longer life expectancies. as correlational or causal.

Problem 8

Classify claim The new teaching method improved student test scores in the controlled study. as correlational or causal.

Problem 9

Classify claim Eating breakfast is correlated with better concentration in school. as correlational or causal.

Problem 10

Classify claim Removing sugar from the diet can decrease the risk of type 2 diabetes. as correlational or causal.

Problem 11

Classify claim Individuals with higher education levels typically earn more. as correlational or causal.

Problem 12

Classify claim Exposure to sunlight increases vitamin D production in the body. as correlational or causal.

identify possible confounding variables or reverse causation.
15 problems Warmup Practice Mixed Review Assessment
Problem 13

Explain why correlation in ice cream sales and drowning incidents rise together in summer does not prove causation.

Problem 14

Explain why correlation in students with more tutoring have lower scores does not prove causation.

Problem 15

Explain why correlation in neighborhoods with more gyms have healthier residents does not prove causation.

Problem 16

Explain why correlation in cities with more churches tend to have higher crime rates does not prove causation.

Problem 17

Explain why correlation in more firefighters at a fire often leads to more damage does not prove causation.

Problem 18

Explain why correlation in children with larger shoe sizes tend to have better reading ability does not prove causation.

Problem 19

Explain why correlation in people who drink more coffee have a higher risk of heart disease does not prove causation.

Problem 20

Explain why correlation in people who wear coats more often tend to get more colds does not prove causation.

Open in simulator
Problem 21

Explain why correlation in regions with more storks tend to have higher birth rates does not prove causation.

Problem 22

Explain why correlation in children who watch more TV tend to be more obese does not prove causation.

Problem 23

Explain why correlation in people who use more sunscreen tend to have a higher risk of skin cancer does not prove causation.

Problem 24

Explain why correlation in students who get less sleep tend to have lower grades does not prove causation.

Problem 25

Explain why correlation in countries with higher economic growth often have higher carbon emissions does not prove causation.

Problem 26

Explain why correlation in people who floss daily tend to have better heart health does not prove causation.

Problem 27

Explain why correlation in areas with more police officers often have higher crime rates does not prove causation.

propose a third factor affecting both variables.
12 problems Warmup Practice Mixed Review Assessment
Problem 28

Identify a possible lurking variable in scenario people who buy more sunscreen have more sunburns.

Problem 29

Identify a possible lurking variable in scenario students with more books at home tend to score higher.

Problem 30

Identify a possible lurking variable in scenario cities with more firefighters have more fire damage.

Problem 31

Identify a possible lurking variable in scenario people who exercise more tend to sleep better.

Problem 32

Identify a possible lurking variable in scenario ice cream sales increase as shark attacks increase.

Problem 33

Identify a possible lurking variable in scenario the more often a person brushes their teeth, the higher their risk of heart disease.

Problem 34

Identify a possible lurking variable in scenario countries with more internet users have higher life expectancy.

Open in simulator
Problem 35

Identify a possible lurking variable in scenario the number of storks in an area is positively correlated with the birth rate.

Problem 36

Identify a possible lurking variable in scenario shoe size is positively correlated with reading ability in children.

Problem 37

Identify a possible lurking variable in scenario people who own more luxury cars tend to have better health.

Problem 38

Identify a possible lurking variable in scenario the more often a person uses a dictionary, the higher their vocabulary score.

Problem 39

Identify a possible lurking variable in scenario as the number of churches in a city increases, so does the crime rate.

recognize direction of cause may be reversed.
12 problems Warmup Practice Mixed Review Assessment
Problem 40

Identify reverse causation as an alternative explanation for Using a budgeting app causes people to save more because app users have higher savings.

Problem 41

Identify reverse causation as an alternative explanation for Tutoring causes low test scores because tutored students scored lower.

Open in simulator
Problem 42

Identify reverse causation as an alternative explanation for More doctor visits cause worse health because people with more visits report worse health.

Problem 43

Identify reverse causation as an alternative explanation for Owning a luxury car causes people to be wealthy because luxury car owners have higher net worth.

Problem 44

Identify reverse causation as an alternative explanation for Eating organic food causes better health because people who eat organic food report fewer illnesses.

Problem 45

Identify reverse causation as an alternative explanation for Watching violent TV shows causes aggression because children who watch more violent TV shows exhibit more aggressive behavior.

Problem 46

Identify reverse causation as an alternative explanation for Living near a hospital causes people to be sicker because residents near hospitals have higher rates of chronic illness.

Problem 47

Identify reverse causation as an alternative explanation for Having a large vocabulary causes people to read more because people with large vocabularies read more books.

Problem 48

Identify reverse causation as an alternative explanation for People who listen to classical music are smarter because classical music listeners score higher on intelligence tests.

Problem 49

Identify reverse causation as an alternative explanation for Attending private schools causes higher academic achievement because private school students have higher test scores.

Problem 50

Identify reverse causation as an alternative explanation for Using a specific brand of athletic shoes causes better running performance because professional athletes wear these shoes.

Problem 51

Identify reverse causation as an alternative explanation for Having more fire trucks causes more fires because cities with more fire trucks have more fires.

distinguish observational studies from randomized experiments.
12 problems Warmup Practice Mixed Review Assessment
Problem 52

Decide whether study design randomly assign plants to fertilizer or no fertilizer and compare growth can support causal conclusions.

Problem 53

Decide whether study design survey students about breakfast habits and compare scores can support causal conclusions.

Open in simulator
Problem 54

Decide whether study design compare neighborhoods with and without parks using existing data can support causal conclusions.

Problem 55

Decide whether study design randomly assign one of two practice methods to similar groups can support causal conclusions.

Problem 56

Decide whether study design randomly assign patients with a specific condition to receive either a new medication or a standard treatment and track their recovery can support causal conclusions.

Problem 57

Decide whether study design observe a group of individuals who regularly consume coffee and compare their alertness levels to a group who do not drink coffee can support causal conclusions.

Problem 58

Decide whether study design assign students by lottery to either a new online learning platform or traditional classroom instruction and compare test scores can support causal conclusions.

Problem 59

Decide whether study design analyze existing government data on countries with high and low literacy rates to see if there's a correlation with economic development can support causal conclusions.

Problem 60

Decide whether study design randomly select half of a city's neighborhoods to receive enhanced street lighting and measure crime rates in those areas versus the control neighborhoods can support causal conclusions.

Problem 61

Decide whether study design interview parents about their children's screen time habits and compare these findings with the children's reported sleep quality can support causal conclusions.

Problem 62

Decide whether study design randomly assign different types of soil amendments to plots of land and measure the subsequent crop yield can support causal conclusions.

Problem 63

Decide whether study design compare the job satisfaction of employees who voluntarily participate in a wellness program with those who do not can support causal conclusions.

use precise cautious language.
12 problems Warmup Practice Mixed Review Assessment
Problem 64

Rewrite causal claim More screen time causes lower sleep quality. as a correlation-only claim.

Problem 65

Rewrite causal claim Drinking the supplement improves test scores. as a correlation-only claim.

Problem 66

Rewrite causal claim Park access makes residents exercise more. as a correlation-only claim.

Problem 67

Rewrite causal claim Higher advertising spending causes higher sales. as a correlation-only claim.

Problem 68

Rewrite causal claim Studying more leads to better grades. as a correlation-only claim.

Problem 69

Rewrite causal claim Eating breakfast improves concentration. as a correlation-only claim.

Problem 70

Rewrite causal claim Regular exercise reduces stress levels. as a correlation-only claim.

Problem 71

Rewrite causal claim Using this new fertilizer increases crop yield. as a correlation-only claim.

Problem 72

Rewrite causal claim Listening to classical music makes you smarter. as a correlation-only claim.

Problem 73

Rewrite causal claim Higher education causes higher income. as a correlation-only claim.

Problem 74

Rewrite causal claim Lack of sleep impairs driving ability. as a correlation-only claim.

Problem 75

Rewrite causal claim Reading to children improves their vocabulary. as a correlation-only claim.

Open in simulator
cite design, random assignment, and confounding concerns.
12 problems Warmup Practice Mixed Review Assessment
Problem 76

Evaluate whether evidence randomly assigned students to two study methods and compared final scores supports causal claim method A causes higher scores than method B.

Problem 77

Evaluate whether evidence survey found students who exercise more also report better sleep supports causal claim exercise causes better sleep.

Problem 78

Evaluate whether evidence scatter plot shows strong positive association between ad spending and sales supports causal claim advertising causes sales to increase.

Problem 79

Evaluate whether evidence randomized fertilizer experiment with controlled watering showed higher growth for treatment plants supports causal claim fertilizer caused increased growth.

Problem 80

Evaluate whether evidence patients were randomly assigned to receive either a new drug or a placebo, and the drug group showed significantly lower blood pressure supports causal claim the new drug causes a reduction in blood pressure.

Problem 81

Evaluate whether evidence cities with more parks tend to have lower crime rates supports causal claim more parks cause lower crime rates.

Open in simulator
Problem 82

Evaluate whether evidence website visitors were randomly shown one of two layouts (A or B), and layout A resulted in a 15% higher click-through rate supports causal claim layout A causes higher click-through rates than layout B.

Problem 83

Evaluate whether evidence a company implemented a new training program, and employee productivity increased by 10% in the following quarter supports causal claim the new training program caused the increase in employee productivity.

Problem 84

Evaluate whether evidence a poll found that people who prefer coffee over tea report feeling more alert in the mornings supports causal claim drinking coffee causes people to feel more alert than drinking tea.

Problem 85

Evaluate whether evidence in a controlled laboratory setting, different amounts of light were randomly assigned to identical plant samples, and plants with more light grew taller supports causal claim increased light causes plants to grow taller.

Problem 86

Evaluate whether evidence historical data shows that ice cream sales and shark attacks both increase during the summer months supports causal claim increased ice cream sales cause more shark attacks.

Problem 87

Evaluate whether evidence students who spent more time on social media also reported lower GPAs supports causal claim social media use causes lower GPAs.

describe association and avoid causal language.
12 problems Warmup Practice Mixed Review Assessment
Problem 88

Interpret scatter plot association strong positive association between homework time and quiz score without overclaiming causation.

Problem 89

Interpret scatter plot association weak negative association between distance from school and attendance without overclaiming causation.

Problem 90

Interpret scatter plot association no clear association between shoe size and reading score without overclaiming causation.

Problem 91

Interpret scatter plot association strong positive association between hours studied and exam grade without overclaiming causation.

Problem 92

Interpret scatter plot association moderate negative association between daily screen time and sleep duration without overclaiming causation.

Problem 93

Interpret scatter plot association no clear association between favorite color and IQ score without overclaiming causation.

Problem 94

Interpret scatter plot association weak positive association between daily coffee consumption and reaction time without overclaiming causation.

Open in simulator
Problem 95

Interpret scatter plot association strong negative association between temperature and hot chocolate sales without overclaiming causation.

Problem 96

Interpret scatter plot association moderate positive association between advertising budget and product sales without overclaiming causation.

Problem 97

Interpret scatter plot association no clear association between number of pets owned and favorite music genre without overclaiming causation.

Problem 98

Interpret scatter plot association weak negative association between hours of exercise and body mass index (BMI) without overclaiming causation.

Problem 99

Interpret scatter plot association strong positive association between years of education and annual income without overclaiming causation.

name plausible external drivers.
12 problems Warmup Practice Mixed Review Assessment
Problem 100

Identify a common-cause explanation for correlated variables ice cream sales and swimming accidents.

Problem 101

Identify a common-cause explanation for correlated variables number of firefighters at a fire and amount of fire damage.

Problem 102

Identify a common-cause explanation for correlated variables umbrella sales and traffic accidents.

Open in simulator
Problem 103

Identify a common-cause explanation for correlated variables city park spending and public health scores.

Problem 104

Identify a common-cause explanation for correlated variables shoe size and reading ability in children.

Problem 105

Identify a common-cause explanation for correlated variables number of storks and human birth rates in a region.

Problem 106

Identify a common-cause explanation for correlated variables electricity consumption and crime rates in a city.

Problem 107

Identify a common-cause explanation for correlated variables coffee consumption and lung cancer rates.

Problem 108

Identify a common-cause explanation for correlated variables wearing a coat and shivering.

Problem 109

Identify a common-cause explanation for correlated variables sales of sunscreen and sales of sunglasses.

Problem 110

Identify a common-cause explanation for correlated variables students' test scores and their parents' income.

Problem 111

Identify a common-cause explanation for correlated variables number of churches and crime rates in a city.

evaluate causation, reverse causation, and lurking-variable possibilities.
12 problems Warmup Practice Mixed Review Assessment
Problem 112

Compare explanations for correlation scenario students using tutoring have lower average scores.

Problem 113

Compare explanations for correlation scenario people who buy sunscreen have more sunburns.

Open in simulator
Problem 114

Compare explanations for correlation scenario higher ad spending and higher sales occur together.

Problem 115

Compare explanations for correlation scenario ice cream sales and crime rates both increase in summer.

Problem 116

Compare explanations for correlation scenario countries with more storks tend to have higher birth rates.

Problem 117

Compare explanations for correlation scenario people who own more books tend to have higher incomes.

Problem 118

Compare explanations for correlation scenario the more firefighters at a fire, the more damage is done.

Problem 119

Compare explanations for correlation scenario children who sleep with a night light are more likely to develop myopia.

Problem 120

Compare explanations for correlation scenario people who drink more coffee tend to live longer.

Problem 121

Compare explanations for correlation scenario cities with more churches tend to have higher crime rates.

Problem 122

Compare explanations for correlation scenario students who sit in the front rows of a lecture hall tend to get better grades.

Problem 123

Compare explanations for correlation scenario as shoe size increases, reading ability improves.

suggest experiment, randomization, control, or longitudinal evidence.
12 problems Warmup Practice Mixed Review Assessment
Problem 124

Decide what additional evidence would strengthen causal claim a new study app causes higher scores.

Problem 125

Decide what additional evidence would strengthen causal claim walking more causes lower blood pressure.

Open in simulator
Problem 126

Decide what additional evidence would strengthen causal claim a tutoring program causes graduation rates to rise.

Problem 127

Decide what additional evidence would strengthen causal claim fertilizer causes plants to grow taller.

Problem 128

Decide what additional evidence would strengthen causal claim eating breakfast causes better school performance.

Problem 129

Decide what additional evidence would strengthen causal claim listening to classical music causes increased intelligence.

Problem 130

Decide what additional evidence would strengthen causal claim a new teaching method causes students to learn faster.

Problem 131

Decide what additional evidence would strengthen causal claim regular exercise causes improved mood.

Problem 132

Decide what additional evidence would strengthen causal claim meditation causes reduced stress.

Problem 133

Decide what additional evidence would strengthen causal claim drinking coffee causes increased alertness.

Problem 134

Decide what additional evidence would strengthen causal claim wearing a specific brand of shoes causes faster running times.

Problem 135

Decide what additional evidence would strengthen causal claim using a particular software causes fewer coding errors.

identify overstatement and write a valid conclusion.
12 problems Warmup Practice Mixed Review Assessment
Problem 136

Correct invalid correlation-causation conclusion The scatter plot proves that studying more causes higher scores.

Problem 137

Correct invalid correlation-causation conclusion Since r=-0.8, more screen time causes less sleep.

Problem 138

Correct invalid correlation-causation conclusion The table shows students in sports have higher grades, so sports improve grades.

Problem 139

Correct invalid correlation-causation conclusion Ice cream sales cause drowning because they rise together.

Open in simulator
Problem 140

Correct invalid correlation-causation conclusion The study found that people who eat breakfast regularly have lower BMI, so eating breakfast causes lower BMI.

Problem 141

Correct invalid correlation-causation conclusion As the number of firefighters at a fire increases, the damage caused by the fire also increases. Therefore, firefighters cause more damage.

Problem 142

Correct invalid correlation-causation conclusion Countries with more Nobel laureates consume more chocolate. This proves that eating chocolate makes people smarter.

Problem 143

Correct invalid correlation-causation conclusion Students who take music lessons tend to have higher math scores, which means music lessons improve math ability.

Problem 144

Correct invalid correlation-causation conclusion The graph shows a rise in violent crime following the release of a new video game, indicating the game causes violence.

Problem 145

Correct invalid correlation-causation conclusion Since cities with more parks have lower rates of depression, parks reduce depression.

Problem 146

Correct invalid correlation-causation conclusion A survey revealed that employees who work longer hours report higher job satisfaction, so working longer hours makes employees happier.

Problem 147

Correct invalid correlation-causation conclusion The data indicates that students who use tutoring services get better grades, proving that tutoring causes better grades.