CLT · Quantitative Reasoning · Unit 04 Data and StatisticsData and Statistics: Unit Study Guide
04.01 Data Analysis
Data and probability questions (about 5 of the 40) cover mean, median, mode and range, spread and outliers, reading tables and graphs, scatterplots, counting and basic and conditional probability. All arithmetic is done by hand.
Center and Spread
Mean, median and mode describe the center; range, IQR and standard deviation describe the spread.
Key formulas| Mean | xˉ=n∑x |
| Weighted mean | xˉ=∑w∑wx |
| Median | middle value of the ordered data |
| Range | max−min |
| IQR | Q3−Q1 |
| Outlier rule | x<Q1−1.5IQR or x>Q3+1.5IQR |
Mean absolute deviation
Method. MAD = average distance from the mean.
Worked exampleWhat is the mean absolute deviation (MAD) of 23, 7, 16, 2, 7?
AnswerC — 6.8
Step-by-step- First find the mean.
- So 55 ÷ 5 = 11.
- The distances from 11 are 12, 4, 5, 9, 4.
- Their sum is 34.
- So MAD = 34 ÷ 5 = 6.8.
Quick checkthe distances above and below the mean both add to 17 ✓.
Common mistakes- A (3.4): used only the distances above the mean
- B (6): measured distances from the median
- D (34): added the distances but did not divide
Interquartile range
Method. IQR = median of the upper half − median of the lower half.
Worked exampleWhat is the interquartile range (IQR) of 22, 37, 26, 31, 7, 33, 21, 17?
AnswerD — 13
Step-by-step- Order the values.
- So 7, 17, 21, 22, 26, 31, 33, 37.
- The lower half is 7, 17, 21, 22.
- So Q1 = 19.
- The upper half is 26, 31, 33, 37.
- So Q3 = 32.
- Then IQR = Q3 − Q1 = 32 − 19 = 13.
Quick check19 + 13 = 32, the upper quartile ✓.
Common mistakes- A (5): used the median instead of Q3
- B (6.5): gave half the IQR
- C (8): used the median instead of Q1
Effect of outliers
Method. Find both means, then subtract; an outlier pulls the mean toward it.
Worked exampleThe data set 119, 13, 16, 19, 28, 26, 24 has an outlier. By how much does the mean decrease when the outlier is removed?
AnswerC — 14
Step-by-step- The mean with every value is 245 ÷ 7 = 35.
- The outlier is 119.
- Without it, the mean is 126 ÷ 6 = 21.
- The decrease is 35 − 21 = 14.
Quick check21 + 14 = 35, the original mean ✓.
Common mistakes- A (2.5): found the change in the median
- B (12): used the original mean for the outlier's distance
- D (17): divided the outlier by the count
Comparing data sets
Method. Find the mean of each set separately, then subtract.
Worked exampleData set A is 30, 24, 26, 3, 19. Data set B is 4, 14, 6, 1, 25. How much greater is the mean of A than the mean of B?
AnswerA — 10.4
Step-by-step- Mean of A = 102 ÷ 5 = 20.4.
- Mean of B = 50 ÷ 5 = 10.
- The difference is 20.4 − 10 = 10.4.
Quick check10 + 10.4 = 20.4, the mean of A ✓.
Common mistakes- B (18): compared the medians instead
- C (30.4): added the means
- D (52): compared the sums
Missing value from a mean
Method. Needed score = target mean × new count − current total.
Worked exampleTom scored 89, 76, 86, 96, 83 on 5 tests. What score on the next test makes the mean of all 6 tests exactly 88?
AnswerD — 98
Step-by-step- For a mean of 88 over 6 tests, the total must be 88 × 6 = 528.
- The first 5 scores add to 430.
- So the next score must be 528 − 430 = 98.
Quick check(430 + 98) ÷ 6 = 88 ✓.
Common mistakes- A (10): used the old number of tests
- B (88): gave the target mean
- C (90): averaged the old mean and the new score
Weighted mean
Method. Combined mean = total of all scores ÷ total count, not the average of the two means.
Worked exampleOne class of 8 students has a mean score of 69. Another class of 12 students has a mean score of 80. What is the mean score of all 20 students?
AnswerC — 75.6
Step-by-step- Total for the first class is 8 × 69 = 552.
- Total for the second class is 12 × 80 = 960.
- The combined mean is (552 + 960) ÷ 20 = 75.6.
Quick check75.6 is closer to 80, the mean of the larger class ✓.
Common mistakes- A (73.4): matched each mean with the other group's size
- B (74.5): averaged the two means
- D (1512): gave the total, not the mean
Standard deviation (concept)
Method. Look for values bunched far from the center on both sides, not just one extreme value.
Worked exampleSet P = {11, 11, 12, 12, 13, 13}, Set Q = {16, 17, 18, 20, 21, 22}, Set R = {2, 2, 2, 3, 3, 16} and Set S = {7, 7, 7, 19, 19, 19}. Which set has the greatest standard deviation?
AnswerD — Set S
Step-by-step- Standard deviation measures how far values typically are from the mean.
- In Set S, the values sit farthest from their mean overall (SD ≈ 6.00).
- The other sets have smaller SDs: Set P ≈ 0.82, Set Q ≈ 2.16, Set R ≈ 5.09.
- So the answer is Set S.
Quick checka large range alone does not make a large SD; Set R has the greatest range but a smaller SD ✓.
Common mistakes- A (Set R): chose the set with the greatest range
- B (Set Q): chose the set with the greatest mean
- C (Set P): chose the set with the least spread
Distributions
Describe shape, center and spread. Box plots show the five-number summary, histograms show shape, and a long tail pulls the mean toward it, away from the median.
Key formulas| Five-number summary | min, Q1, median, Q3, max |
| Skew | right skew: mean usually>median; left skew: mean usually<median |
Five-number summary
Method. Sort, split into lower and upper halves, then take the median of each half.
Worked exampleWhat is the first quartile (Q1) of 34, 90, 33, 48, 61, 74, 88, 84, 2, 71?
AnswerB — 34
Step-by-step- Order the values.
- So 2, 33, 34, 48, 61, 71, 74, 84, 88, 90.
- The lower half is 2, 33, 34, 48, 61.
- Its median is Q1 = 34.
Quick checkQ1 = 34 is below the median 66 ✓.
Common mistakes- A (33): took the second value
- C (66): gave the median
- D (84): gave Q3 instead
Histograms
Method. Find the middle position, then add bar heights from the left until you pass it.
Worked exampleThe histogram shows test scores for 19 students. Each bar includes its left edge but not its right edge. Which interval contains the median?

A35 to 40
B45 to 50
C40 to 45
D50 to 55
AnswerB — 45 to 50
Step-by-step- With 19 values, the median is value number 10.
- The running totals of the bars are 1, 7, 9, 14, 19.
- The total first reaches 10 in the bar from 45 to 50.
Quick checkfewer than 10 values lie below 45 and at least 10 lie below 50 ✓.
Common mistakes- A (35 to 40): chose the tallest bar
- C (40 to 45): chose the middle interval on the scale
- D (50 to 55): miscounted the position of the middle value by a bar
Comparing distributions
Method. Read the same feature from both plots, then subtract.
Worked exampleThe box plots compare two groups. How much greater is the median of Class A than the median of Class B?

AnswerC — 10
Step-by-step- The median of Class A is 35 and the median of Class B is 25.
- The difference is 35 − 25 = 10.
Quick checkthe answer uses the median line of each plot only ✓.
Common mistakes- A (−20): compared the maximums
- B (5): compared the Q3 values
- D (60): added the medians
Cumulative frequency
Method. Cumulative = running total; one interval's frequency = difference of consecutive totals.
Worked exampleThe frequency table shows scores. What is the cumulative frequency for the interval 40–49?

AnswerC — 31
Step-by-step- Cumulative frequency adds every interval up to and including this one.
- So 12 + 19 = 31.
Quick check12 (through 30–39) + 19 = 31 ✓.
Common mistakes- A (12): stopped one interval early
- B (19): gave the frequency of that interval only
- D (44): went one interval too far
Percentiles
Method. Percent below = (number below ÷ total) × 100.
Worked exampleThe data set is 99, 91, 50, 93, 58, 42, 41, 76, 51, 47, 44, 61, 68, 73, 48, 84, 81, 79, 82, 46, 63, 72, 75, 77, 62. What percent of the values are less than 68?
AnswerB — 48%
Step-by-step- Order the values.
- Exactly 12 values are less than 68.
- Out of 25 values, that is 12 ÷ 25 × 100 = 48%.
Quick check12 values below, 1 equal and 12 above make 25 ✓.
Common mistakes- A (12%): gave the count, not the percent
- C (50%): divided by one less than the count
- D (52%): counted the value itself as below it
Outliers (1.5 × IQR rule)
Method. Find both fences, then count the values outside them.
Worked exampleHow many outliers does the data set 25, 67, 93, 1, 23, 45, 30, 20, 48, 32, 43, 28 have by the 1.5 × IQR rule?
AnswerB — 1
Step-by-step- Order the data and find Q1 = 24 and Q3 = 46.5.
- So IQR = 22.5.
- The fences are 24 − 33.75 = −9.75 and 46.5 + 33.75 = 80.25.
- The values outside the fences are 93.
- So there is 1 outlier.
Quick checkevery other value lies between −9.75 and 80.25 ✓.
Common mistakes- A (0): used 3 × IQR
- C (2): used 1 × IQR instead of 1.5 × IQR
- D (3): counted every value above Q3
Graphs and Tables
Read the title, axes and scale before reading values. Bar graphs compare categories, line graphs show change over time, circle graphs show parts of a whole.
Key formulas| Percent of whole | totalpart×100% |
| Central angle | totalpart×360∘ |
Circle graphs
Method. Number = percent × total ÷ 100.
Worked exampleThe circle graph shows the results for favorite pizza topping for 60 students. How many more of the students chose Pepperoni than Veggie?

AnswerA — 3
Step-by-step- The percents differ by 25% − 20% = 5%.
- Then 5% of 60 is 1005 × 60 = 3.
Quick checkPepperoni = 15 and Veggie = 12, and 15 − 12 = 3 ✓.
Common mistakes- B (5): subtracted the percents but did not find them of the total
- C (15): gave the number for Pepperoni only
- D (27): added instead of subtracting
Two-way tables
Method. Given a row → divide by that row's total.
Worked exampleThe two-way table shows the results of a survey of students. What percent of the students in the Boys row are in the Plays a sport column?

AnswerA — 8%
Step-by-step- The question is about the Boys row only.
- So divide by its total, 100.
- Then 8 ÷ 100 = 252 = 8%.
Quick check8% of 100 is 8, the Boys and Plays a sport cell ✓.
Common mistakes- B (36%): used the Girls row
- C (80%): found the percent of all students in the Boys row
- D (92%): used the Does not play a sport cell
Line graphs
Method. Percent change = (new − old) ÷ old × 100; always divide by the earlier year.
Worked exampleThe line graph shows concert tickets sold each year. What was the percent increase from 2020 to 2021?

AnswerB — 100%
Step-by-step- Read the graph.
- So 2020 = 150 and 2021 = 300.
- The change is 150.
- Percent increase = change ÷ original × 100 = 150 ÷ 150 × 100 = 100%.
Quick check150 + 100% of 150 = 150 + 150 = 300 ✓.
Common mistakes- A (50%): divided by the new value instead of the original
- C (150%): gave the change, not the percent change
- D (200%): gave the new value as a percent of the original
Bar graphs
Method. Percent change = (new − old) ÷ old × 100; always divide by the earlier year.
Worked exampleThe bar graph shows bikes repaired each year. What was the percent decrease from 2021 to 2023?

AnswerB — 80%
Step-by-step- Read the graph.
- So 2021 = 500 and 2023 = 100.
- The change is 400.
- Percent decrease = change ÷ original × 100 = 400 ÷ 500 × 100 = 80%.
Quick check500 − 80% of 500 = 500 − 400 = 100 ✓.
Common mistakes- A (20%): gave the new value as a percent of the original
- C (400%): divided by the new value instead of the original
- D (500%): gave the original value as a percent of the new value
Misleading graphs
Method. Read values on the scale; a cut axis makes the bars' heights misleading.
Worked exampleThe bar graph shows visitors to two parks. Its vertical axis starts at 280, not 0. How many times as tall as the bar for Park B does the bar for Park A look?

AnswerC — 5
Step-by-step- Each bar's drawn height starts at 280.
- Park A's bar is 480 − 280 = 200 tall and Park B's is 320 − 280 = 40 tall.
- So it looks 200 ÷ 40 = 5 times as tall.
Quick check40 × 5 = 200, the drawn height of the Park A bar ✓.
Common mistakes- A (85): subtracted the starting value from one bar only
- B (23): used the actual values instead of the bar heights
- D (160): found the difference instead of a ratio
Building data displays
Method. Angle = (part ÷ total) × 360°.
Worked exampleA table of favorite fruit lists Apples: 24, Bananas: 18, Grapes: 5 and Oranges: 13. In a circle graph of these data, what is the central angle, in degrees, for Apples?
AnswerD — 144
Step-by-step- The total is 24 + 18 + 5 + 13 = 60.
- Apples is 6024 of the data.
- The angle is 6024 × 360° = 144°.
Quick check144° ÷ 360° = 52, which matches 24 out of 60 ✓.
Common mistakes- A (24): gave the count
- B (40): found the percent instead of the angle
- C (90): split the circle equally
Scatterplots and Lines of Fit
Describe direction, form and strength. A line of fit predicts y from x; r near ±1 means a strong linear relationship.
Key formulas| Line of fit | y^=a+bx |
| Residual | y−y^ |
Interpreting a line of fit
Method. Slope = predicted change per 1 unit of x; intercept = prediction at x = 0.
Worked exampleA line of fit for number of drinks sold against temperature in °F is ŷ = 5.5x + 51. Which is the best interpretation of the slope 5.5?
AWhen temperature in °F is 0, the predicted number of drinks sold is 51.
BFor each additional unit of temperature in °F, the predicted number of drinks sold increases by 5.5.
CFor each additional unit of number of drinks sold, the predicted temperature in °F increases by 5.5.
DEvery individual's number of drinks sold increases by exactly 5.5 for each unit of temperature in °F.
AnswerB — For each additional unit of temperature in °F, the predicted number of drinks sold increases by 5.5.
Step-by-step- The slope is the predicted change in y for a 1-unit increase in x.
- It describes a trend in predictions, not an exact or causal rule.
- So the slope means “For each additional unit of temperature in °F, the predicted number of drinks sold increases by 5.5”.
Quick checkthe chosen sentence uses the right number with x and y in the right roles ✓.
Common mistakes- A (When temperature in °F is 0, the predicted number of drinks sold is 51.): described the intercept instead of the slope
- C (For each additional unit of number of drinks sold, the predicted temperature in °F increases by 5.5.): reversed the roles of x and y
- D (Every individual's number of drinks sold increases by exactly 5.5 for each unit of temperature in °F.): treated the prediction as exact for every individual
Linear and exponential models
Method. Raise the base to the power first, then multiply by the starting value.
Worked exampleAn exponential model for the data is ŷ = 50(3)ˣ. What does the model predict when x = 3?
AnswerC — 1350
Step-by-step- Substitute x = 3.
- Then ŷ = 50 × (3)3 = 50 × 27 = 1350.
Quick checkeach step from x to x + 1 multiplies the prediction by 3 ✓.
Common mistakes- A (77): added a instead of multiplying
- B (450): multiplied by x instead of raising to the power x
- D (4050): used one power too many
Probability
Probability is favorable outcomes over equally likely total outcomes. Use the addition rule for "or"; for "and", multiply the probabilities when the events are independent, and use conditional probability when they are not.
Key formulas| Basic | P(A)=totalfavorable |
| Complement | P(A′)=1−P(A) |
| Addition | P(A∪B)=P(A)+P(B)−P(A∩B) |
| Independent | P(A∩B)=P(A)P(B) |
| Conditional | P(A∣B)=P(B)P(A∩B) |
Compound events
Method. Independent “and” → multiply the probabilities.
Worked exampleA bag of 10 tiles, 3 of them vowels, and a spinner with 4 equal parts, 3 of them blue, are used once each. What is the probability of getting a vowel from the bag and blue from the spinner?
AnswerA — 409
Step-by-step- The two results are independent.
- So multiply.
- P(a vowel) = 103 and P(blue) = 43.
- So P(both) = 103 × 43 = 409.
Quick checkthere are 10 × 4 = 40 equally likely pairs and 9 are favorable, giving 409 ✓.
Common mistakes- B (103): used only the first event
- C (209): doubled the product
- D (43): used only the second event
Addition rule
Method. Add the two probabilities, then subtract the overlap once.
Worked exampleFor two events, P(A) = 0.65, P(B) = 0.55 and P(A and B) = 0.4. What is P(A or B)?
AnswerD — 0.8
Step-by-step- Add P(A) and P(B).
- Then subtract the overlap P(A and B) once.
- So 0.65 + 0.55 − 0.4 = 0.8.
Quick check0.8 is at least the larger of P(A) and P(B) and at most 1 ✓.
Common mistakes- A (0.2): found the probability of neither
- B (0.3575): multiplied the probabilities
- C (0.4): subtracted the overlap twice
Expected counts
Method. Expected count = probability × number of spins.
Worked exampleA spinner has 6 purple, 8 blue and 4 red equal sections. It is spun 252 times. About how many times should it land on purple?
AnswerA — 84
Step-by-step- P(purple) = 186 = 31.
- Multiply by the number of spins.
- So 31 × 252 = 84.
Quick checkthe expected counts for all three colors add to 252 ✓.
Common mistakes- B (112): used the blue sections
- C (168): found the expected number of non-purple results
- D (1512): multiplied by the count of sections instead of the probability
Conditional probability and two-way tables
Method. “Given” or “from those in” → divide by that group's total; “and” → one cell ÷ grand total.
Worked exampleThe table shows a survey of students. A person is chosen at random from everyone surveyed. What is the probability that the person is in the Grade 10 row and the Does not play column?

AnswerB — 92
Step-by-step- The cell for Grade 10 and Does not play has 6 people out of 27 in all.
- So the probability is 276 = 92.
Quick checkthe numerator and the denominator both come from the group the question names ✓.
Common mistakes- A (729140): multiplied the separate probabilities
- C (73): divided by the Grade 10 row total
- D (53): divided by the Does not play column total
Complement rule
Method. P(at least one) = 1 − P(none).
Worked exampleThe probability that a biased coin lands heads is 61, and tries are independent. In 2 flips, what is the probability that Maria gets at least one head?
AnswerC — 3611
Step-by-step- “At least one” is the complement of “none”.
- P(none) = (1−61)2 = (65)2 = 3625.
- So P(at least one) = 1 − 3625 = 3611.
Quick checkP(none) + P(at least one) = 3625 + 3611 = 1 ✓.
Common mistakes- A (361): found the probability that all succeed
- B (61): used only one try
- D (31): multiplied the probability by the number of tries
Independence
Method. Independent: P(A and B) = P(A)P(B); then use the addition rule.
Worked exampleA and B are independent events with P(A) = 0.6 and P(B) = 0.6. What is P(A or B)?
AnswerD — 0.84
Step-by-step- Because A and B are independent, P(A and B) = 0.6 × 0.6 = 0.36.
- Then P(A or B) = 0.6 + 0.6 − 0.36 = 0.84.
Quick check1 − P(neither) = 1 − 0.4 × 0.4 = 0.84 ✓.
Common mistakes- A (0.16): found the probability of neither
- B (0.36): gave P(A and B)
- C (0.48): found exactly one of the events
Conditional probability formula
Method. P(A | B) = P(A and B) ÷ P(B): divide by the probability of the given event.
Worked exampleP(A) = 0.1, P(B) = 0.65 and P(A and B) = 0.05. What is P(A | B), the probability of A given B?
AnswerC — 131
Step-by-step- P(A | B) means divide P(A and B) by P(B).
- So 0.05 ÷ 0.65 = 131.
Quick check131 × 0.65 = 0.05 = P(A and B) ✓.
Common mistakes- A (40013): multiplied instead of dividing
- B (201): gave P(A and B)
- D (21): divided by P(A) instead of P(B)
Counting
Multiply choices for each stage. Use permutations when order matters and combinations when it does not.
Key formulas| Counting principle | m⋅n |
| Factorial | n!=n(n−1)⋯1 |
| Permutations | nPr=(n−r)!n! |
| Combinations | nCr=r!(n−r)!n! |
| Expected value | E=∑x⋅P(x) |
Counting principle
Method. Multiply the number of choices for each independent step.
Worked exampleA lock code has 3 positions, each filled with one of the digits 0–9. Digits may repeat. How many codes are possible?
AnswerD — 1000
Step-by-step- Each of the 3 positions has 10 choices, and the choices are independent.
- By the counting principle, 10 × 10 × 10 = 103 = 1000.
Quick checkthe count grows by a factor of each step's choices, giving 1000 ✓.
Common mistakes- A (30): multiplied the number of digits by the length
- B (100): used one position too few
- C (720): did not allow repeated digits
Sample spaces and tree diagrams
Method. Count ordered pairs out of 36.
Worked exampleTwo fair dice are rolled. What is the probability that the sum is 12?
AnswerA — 361
Step-by-step- There are 6 × 6 = 36 equally likely ordered outcomes, and only 1 of them, (6, 6), has sum 12.
- So the probability is 361.
Quick check1 favorable + 35 others = 36 ✓.
Common mistakes- B (121): divided by 12 instead of 36
- C (111): treated the 11 sums as equally likely
- D (61): divided by 6 instead of 36
Combinations
Method. No roles, just a group → order does not matter → nCr = nPr ÷ r!.
Worked exampleIn how many ways can a committee of 3 people be chosen from 10 people?
AnswerB — 120
Step-by-step- Order does not matter.
- So use combinations.
- C(10, 3) = 10! ÷ (3! × 7!) = 720 ÷ 6 = 120.
Quick checkC(10, 3) = C(10, 7) = 120 ✓.
Common mistakes- A (45): chose one too few
- C (720): counted different orders as different
- D (1000): allowed repeats and order
Expected value
Method. E = Σ (payoff × probability); losses are negative.
Worked exampleIn a game, you win $90 with probability 52 and otherwise lose $4. What is the expected value of one play?
A$36.00
B$34.40
C$86.00
D$33.60
AnswerD — $33.60
Step-by-step- Multiply each payoff by its probability and add.
- Win: 90 × 52 = 36.
- Lose: −4 × 53 = −2.4.
- Total 36 − 2.4 = 33.6.
- So the expected value is $33.60 per play.
Quick checkover 50 plays you expect about 20 wins, a net of 1680 dollars ✓.
Common mistakes- A ($36.00): ignored the loss
- B ($34.40): used the winning probability for the loss too
- C ($86.00): ignored the probabilities
Permutations
Method. Different roles → order matters → nPr.
Worked exampleFrom 7 people, a captain and a co-captain are chosen. No person holds two roles. In how many ways can this be done?
AnswerD — 42
Step-by-step- The roles are different.
- So order matters.
- That is 7P2 = 7 × 6 = 42.
Quick checknPr = nCr × r! = 21 × 2 = 42 ✓.
Common mistakes- A (7): filled one role too few
- B (14): multiplied n by r
- C (21): ignored the order (used combinations)
Binomial probability
Method. P(X = k) = C(n, k)·pᵏ·(1−p)n−ᵏ.
Worked exampleA trial succeeds with probability 41, independently each time. In 6 trials, what is the probability of exactly 4 successes?
A40969
B4096135
C25615
D40961215
AnswerB — 4096135
Step-by-step- This is binomial with n = 6 and p = 41.
- P(X = 4) = C(6, 4) p4(1−p)2 = 15 × (41)4 × (43)2 = 4096135.
Quick checksumming this formula for k = 0 to 6 gives 1 ✓.
Common mistakes- A (40969): left out the number of arrangements C(n, k)
- C (25615): left out the failure factor
- D (40961215): swapped the success and failure probabilities