BOOKLET given in the examLEARN you must remember it · Each block links to its lesson.
Statistics and probability IB MATHS AA · HLpastpaperprep.com/revision-notes I Q R = Q 3 − Q 1 \mathrm{IQR} = Q_{3} - Q_{1} IQR = Q 3 − Q 1 BOOKLET lower fence = Q 1 − 1.5 × I Q R , upper fence = Q 3 + 1.5 × I Q R \text{lower fence} = Q_{1} - 1.5 \times \mathrm{IQR}, \qquad \text{upper fence} = Q_{3} + 1.5 \times \mathrm{IQR} lower fence = Q 1 − 1.5 × IQR , upper fence = Q 3 + 1.5 × IQR LEARN number from a stratum = size of stratum size of population × sample size \text{number from a stratum} = \frac{\text{size of stratum}}{\text{size of population}} \times \text{sample size} number from a stratum = size of population size of stratum × sample size LEARN The population is the whole group; a sample is the part you collect data from. Counted data is discrete; measured data is continuous. LEARN
A sample is biased if the way it is chosen favours some members. Say who is favoured and why. LEARN
Leave missing values out, never record them as 0 0 0 . Correct a recording error only if you know the true value. LEARN outlier: x < Q 1 − 1.5 × I Q R or x > Q 3 + 1.5 × I Q R \text{outlier: } x < Q_{1} - 1.5 \times \mathrm{IQR} \quad \text{or} \quad x > Q_{3} + 1.5 \times \mathrm{IQR} outlier: x < Q 1 − 1.5 × IQR or x > Q 3 + 1.5 × IQR LEARN A value equal to a fence is not an outlier. Keep valid outliers; remove only errors. LEARN
Simple random: every sample equally likely. Systematic: every k k k th, k = N n k = \frac{N}{n} k = n N , random start. Stratified: random within groups, in proportion. Quota: fixed numbers, collector chooses. Convenience: easiest to reach. LEARN median at n 2 , Q 1 at n 4 , Q 3 at 3 n 4 \text{median at } \tfrac{n}{2}, \qquad Q_{1} \text{ at } \tfrac{n}{4}, \qquad Q_{3} \text{ at } \tfrac{3n}{4} median at 2 n , Q 1 at 4 n , Q 3 at 4 3 n LEARN I Q R = Q 3 − Q 1 \mathrm{IQR} = Q_{3} - Q_{1} IQR = Q 3 − Q 1 BOOKLET Class intervals are inequalities with no gaps, such as 20 ≤ t < 25 20 \le t < 25 20 ≤ t < 25 and 25 ≤ t < 30 25 \le t < 30 25 ≤ t < 30 . A boundary value goes in the class whose inequality it satisfies. LEARN In a histogram with equal class widths, bar height is frequency and the bars touch. LEARN
Plot cumulative frequency at each upper class boundary, starting from 0 0 0 at the first lower boundary. It counts values at or below, so for “more than” subtract from n n n . LEARN median at n 2 , Q 1 at n 4 , Q 3 at 3 n 4 , k th percentile at k 100 × n \text{median at } \tfrac{n}{2}, \qquad Q_{1} \text{ at } \tfrac{n}{4}, \qquad Q_{3} \text{ at } \tfrac{3n}{4}, \qquad k\text{th percentile at } \tfrac{k}{100} \times n median at 2 n , Q 1 at 4 n , Q 3 at 4 3 n , k th percentile at 100 k × n LEARN Box plot: box from Q 1 Q_{1} Q 1 to Q 3 Q_{3} Q 3 , line at the median, whiskers to the most extreme values that are not outliers, a cross for each outlier. LEARN Compare medians for centre and IQRs for spread, in context. A symmetric box and whiskers means the data may be normal. LEARN
x ˉ = ∑ i = 1 k f i x i n , where n = ∑ i = 1 k f i \bar{x} = \frac{\sum_{i=1}^{k} f_{i}x_{i}}{n}, \quad \text{where } n = \sum_{i=1}^{k} f_{i} x ˉ = n ∑ i = 1 k f i x i , where n = ∑ i = 1 k f i BOOKLET I Q R = Q 3 − Q 1 \mathrm{IQR} = Q_{3} - Q_{1} IQR = Q 3 − Q 1 BOOKLET Median: the n + 1 2 \frac{n+1}{2} 2 n + 1 th value in order; for even n n n , the mean of the middle two. Mode: the most frequent value. LEARN Grouped data: estimate the mean with mid-interval values a + b 2 \frac{a+b}{2} 2 a + b . The modal class has the highest frequency. LEARN Quartiles: medians of the lower and upper halves, median left out when n n n is odd. Other methods may differ slightly. LEARN Standard deviation: GDC only, using σ x \sigma_{x} σ x , not s x s_{x} s x . Variance = σ 2 = \sigma^{2} = σ 2 : square the unrounded value. LEARN x → a x + b x \to ax + b x → a x + b with a > 0 a > 0 a > 0 : mean → a x ˉ + b \to a\bar{x} + b → a x ˉ + b , σ → a σ \sigma \to a\sigma σ → aσ , variance → a 2 σ 2 \to a^{2}\sigma^{2} → a 2 σ 2 .LEARN − 1 ≤ r ≤ 1 -1 \le r \le 1 − 1 ≤ r ≤ 1 LEARN Describe correlation by direction (positive, negative, zero) and strength (strong, weak, none). LEARN
r r r near ± 1 \pm 1 ± 1 : strong linear correlation; near 0 0 0 : none, though there may be a curve. ∣ r ∣ \lvert r\rvert ∣ r ∣ above the critical value: significant.LEARN A line of best fit by eye, and the regression line, pass through the mean point ( x ˉ , y ˉ ) (\bar{x}, \bar{y}) ( x ˉ , y ˉ ) . LEARN Correlation does not imply causation: look for a third variable. LEARN
In y = a x + b y = ax + b y = a x + b , a a a is the change in y y y per 1 1 1 increase in x x x ; b b b is y y y when x = 0 x = 0 x = 0 . LEARN Use the y y y on x x x line only to predict y y y , and only inside the range of the data. LEARN P ( A ) = n ( A ) n ( U ) \mathrm{P}(A) = \frac{n(A)}{n(U)} P ( A ) = n ( U ) n ( A ) BOOKLET relative frequency = number of times the event happens number of trials \text{relative frequency} = \frac{\text{number of times the event happens}}{\text{number of trials}} relative frequency = number of trials number of times the event happens LEARN P ( A ) + P ( A ′ ) = 1 \mathrm{P}(A) + \mathrm{P}(A') = 1 P ( A ) + P ( A ′ ) = 1 BOOKLET expected number of occurrences of A = n × P ( A ) , where n is the number of trials \text{expected number of occurrences of } A = n \times \mathrm{P}(A), \quad \text{where } n \text{ is the number of trials} expected number of occurrences of A = n × P ( A ) , where n is the number of trials LEARN A trial has outcomes; the sample space U U U lists them all; an event is a set of outcomes. For two stages, list pairs or draw a table. LEARN Counting works only for equally likely outcomes. Every probability is between 0 0 0 and 1 1 1 . LEARN Relative frequency = times the event happens number of trials = \frac{\text{times the event happens}}{\text{number of trials}} = number of trials times the event happens estimates a probability. More trials give a better estimate. LEARN For "at least one", use 1 − P ( none ) 1 - \mathrm{P}(\text{none}) 1 − P ( none ) . LEARN Expected number of occurrences = n × P ( A ) = n \times \mathrm{P}(A) = n × P ( A ) for n n n trials. It need not be a whole number. LEARN P ( A ∪ B ) = P ( A ) + P ( B ) − P ( A ∩ B ) \mathrm{P}(A \cup B) = \mathrm{P}(A) + \mathrm{P}(B) - \mathrm{P}(A \cap B) P ( A ∪ B ) = P ( A ) + P ( B ) − P ( A ∩ B ) BOOKLET P ( A ∪ B ) = P ( A ) + P ( B ) \mathrm{P}(A \cup B) = \mathrm{P}(A) + \mathrm{P}(B) P ( A ∪ B ) = P ( A ) + P ( B ) BOOKLET P ( A ∣ B ) = P ( A ∩ B ) P ( B ) \mathrm{P}(A \mid B) = \dfrac{\mathrm{P}(A \cap B)}{\mathrm{P}(B)} P ( A ∣ B ) = P ( B ) P ( A ∩ B ) BOOKLET P ( A ∩ B ) = P ( B ) P ( A ∣ B ) \mathrm{P}(A \cap B) = \mathrm{P}(B)\,\mathrm{P}(A \mid B) P ( A ∩ B ) = P ( B ) P ( A ∣ B ) LEARN P ( A ∩ B ) = P ( A ) P ( B ) \mathrm{P}(A \cap B) = \mathrm{P}(A)\,\mathrm{P}(B) P ( A ∩ B ) = P ( A ) P ( B ) BOOKLET Fill a Venn diagram from the middle out: the overlap, then the rest of each circle, then the outside. "Or" includes both: A ∪ B A \cup B A ∪ B means A A A , B B B or both. LEARN Mutually exclusive events can't both happen: P ( A ∩ B ) = 0 \mathrm{P}(A \cap B) = 0 P ( A ∩ B ) = 0 . LEARN Tree diagrams: multiply along a path, add across paths. Without replacement, the second-stage fractions change. LEARN
∑ P ( X = x ) = 1 \sum \mathrm{P}(X = x) = 1 ∑ P ( X = x ) = 1 LEARN E ( X ) = ∑ x P ( X = x ) \mathrm{E}(X) = \sum x\,\mathrm{P}(X = x) E ( X ) = ∑ x P ( X = x ) BOOKLET fair game: E ( X ) = 0 , where X is the player’s gain \text{fair game: } \mathrm{E}(X) = 0, \quad \text{where } X \text{ is the player's gain} fair game: E ( X ) = 0 , where X is the player’s gain LEARN A discrete random variable X X X has a list of values x x x . Its probability distribution gives P ( X = x ) \mathrm{P}(X = x) P ( X = x ) for each, as a table or a formula. LEARN ∑ P ( X = x ) = 1 , 0 ≤ P ( X = x ) ≤ 1 \sum \mathrm{P}(X = x) = 1, \quad 0 \le \mathrm{P}(X = x) \le 1 ∑ P ( X = x ) = 1 , 0 ≤ P ( X = x ) ≤ 1 LEARN To find k k k , set the sum of the probabilities equal to 1 1 1 . Reject any root that gives a probability below 0 0 0 or above 1 1 1 . LEARN E ( X ) \mathrm{E}(X) E ( X ) is the long-run average. It need not be a value X X X can take. Over n n n trials, expect a total of n × E ( X ) n \times \mathrm{E}(X) n × E ( X ) .LEARN If X X X is a player's gain (prize minus cost), the game is fair when E ( X ) = 0 \mathrm{E}(X) = 0 E ( X ) = 0 . LEARN P ( X = r ) = n C r p r ( 1 − p ) n − r , r = 0 , 1 , … , n \mathrm{P}(X = r) = {}^{n}C_{r}\, p^{r}(1-p)^{n-r}, \quad r = 0, 1, \ldots, n P ( X = r ) = n C r p r ( 1 − p ) n − r , r = 0 , 1 , … , n LEARN at most k P ( X ≤ k ) fewer than k P ( X ≤ k − 1 ) at least k P ( X ≥ k ) = 1 − P ( X ≤ k − 1 ) more than k P ( X > k ) = 1 − P ( X ≤ k ) a to b inclusive P ( a ≤ X ≤ b ) = P ( X ≤ b ) − P ( X ≤ a − 1 ) \begin{array}{ll} \text{at most } k & \mathrm{P}(X \le k) \\ \text{fewer than } k & \mathrm{P}(X \le k - 1) \\ \text{at least } k & \mathrm{P}(X \ge k) = 1 - \mathrm{P}(X \le k - 1) \\ \text{more than } k & \mathrm{P}(X > k) = 1 - \mathrm{P}(X \le k) \\ a \text{ to } b \text{ inclusive} & \mathrm{P}(a \le X \le b) = \mathrm{P}(X \le b) - \mathrm{P}(X \le a - 1) \end{array} at most k fewer than k at least k more than k a to b inclusive P ( X ≤ k ) P ( X ≤ k − 1 ) P ( X ≥ k ) = 1 − P ( X ≤ k − 1 ) P ( X > k ) = 1 − P ( X ≤ k ) P ( a ≤ X ≤ b ) = P ( X ≤ b ) − P ( X ≤ a − 1 ) LEARN E ( X ) = n p \mathrm{E}(X) = np E ( X ) = n p BOOKLET V a r ( X ) = n p ( 1 − p ) \mathrm{Var}(X) = np(1-p) Var ( X ) = n p ( 1 − p ) BOOKLET X ∼ B ( n , p ) X \sim \mathrm{B}(n, p) X ∼ B ( n , p ) counts successes in a fixed number n n n of independent trials, each with two outcomes and the same success probability p p p .LEARN On your GDC, binomial pdf gives P ( X = r ) \mathrm{P}(X = r) P ( X = r ) and binomial cdf gives P ( X ≤ k ) \mathrm{P}(X \le k) P ( X ≤ k ) . LEARN P ( X ≥ k ) = 1 − P ( X ≤ k − 1 ) \mathrm{P}(X \ge k) = 1 - \mathrm{P}(X \le k - 1) P ( X ≥ k ) = 1 − P ( X ≤ k − 1 ) and P ( X > k ) = 1 − P ( X ≤ k ) \mathrm{P}(X > k) = 1 - \mathrm{P}(X \le k) P ( X > k ) = 1 − P ( X ≤ k ) .LEARN n p np n p is the expected number of successes. The standard deviation is n p ( 1 − p ) \sqrt{np(1-p)} n p ( 1 − p ) .LEARN P ( X < μ ) = P ( X > μ ) = 0.5 , P ( X < μ − d ) = P ( X > μ + d ) \mathrm{P}(X < \mu) = \mathrm{P}(X > \mu) = 0.5, \qquad \mathrm{P}(X < \mu - d) = \mathrm{P}(X > \mu + d) P ( X < μ ) = P ( X > μ ) = 0.5 , P ( X < μ − d ) = P ( X > μ + d ) LEARN P ( μ − σ < X < μ + σ ) ≈ 0.68 P ( μ − 2 σ < X < μ + 2 σ ) ≈ 0.95 P ( μ − 3 σ < X < μ + 3 σ ) ≈ 0.997 \begin{aligned} \mathrm{P}(\mu - \sigma < X < \mu + \sigma) &\approx 0.68 \\ \mathrm{P}(\mu - 2\sigma < X < \mu + 2\sigma) &\approx 0.95 \\ \mathrm{P}(\mu - 3\sigma < X < \mu + 3\sigma) &\approx 0.997 \end{aligned} P ( μ − σ < X < μ + σ ) P ( μ − 2 σ < X < μ + 2 σ ) P ( μ − 3 σ < X < μ + 3 σ ) ≈ 0.68 ≈ 0.95 ≈ 0.997 LEARN P ( X > k ) = p ⟺ P ( X < k ) = 1 − p \mathrm{P}(X > k) = p \iff \mathrm{P}(X < k) = 1 - p P ( X > k ) = p ⟺ P ( X < k ) = 1 − p LEARN X ∼ N ( μ , σ 2 ) X \sim \mathrm{N}(\mu, \sigma^{2}) X ∼ N ( μ , σ 2 ) : a bell-shaped curve, symmetric about μ \mu μ , with total area 1 1 1 . Mean, median and mode all equal μ \mu μ . The second number is the variance.LEARN For a continuous variable P ( X = a ) = 0 \mathrm{P}(X = a) = 0 P ( X = a ) = 0 , so < < < and ≤ \le ≤ give the same probability. LEARN Normal cdf takes lower bound, upper bound, μ \mu μ and σ \sigma σ . Use − 1 E 99 -1\text{E}99 − 1 E 99 for less than and 1 E 99 1\text{E}99 1 E 99 for more than. LEARN For a middle region of probability p p p , each tail holds 1 − p 2 \frac{1 - p}{2} 2 1 − p . LEARN Given that: P ( A ∣ B ) = P ( A ∩ B ) P ( B ) \mathrm{P}(A \mid B) = \frac{\mathrm{P}(A \cap B)}{\mathrm{P}(B)} P ( A ∣ B ) = P ( B ) P ( A ∩ B ) , where A ∩ B A \cap B A ∩ B is the overlap of the two intervals. LEARN The line of x x x on y y y , x = c y + d x = cy + d x = cy + d , minimises squared horizontal distances. Use it to predict x x x from y y y . LEARN On your GDC, put the y y y -values in the X list and the x x x -values in the Y list. LEARN A line of x x x on y y y can't reliably predict y y y from x x x : use the line of y y y on x x x . Never rearrange one line to predict the other variable. LEARN Both lines go through ( x ˉ , y ˉ ) (\bar{x}, \bar{y}) ( x ˉ , y ˉ ) : solving the two equations together gives the means. They are one line only if r = ± 1 r = \pm 1 r = ± 1 . LEARN Trust a prediction only with strong correlation and a given value inside the range of the data. For a line of x x x on y y y , check the y y y data. LEARN P ( A ∣ B ) = P ( A ∩ B ) P ( B ) \mathrm{P}(A \mid B) = \dfrac{\mathrm{P}(A \cap B)}{\mathrm{P}(B)} P ( A ∣ B ) = P ( B ) P ( A ∩ B ) BOOKLET P ( A ∩ B ) = P ( B ) P ( A ∣ B ) \mathrm{P}(A \cap B) = \mathrm{P}(B)\,\mathrm{P}(A \mid B) P ( A ∩ B ) = P ( B ) P ( A ∣ B ) LEARN The given event, after the bar, goes on the bottom. P ( A ∣ B ) \mathrm{P}(A \mid B) P ( A ∣ B ) and P ( B ∣ A ) \mathrm{P}(B \mid A) P ( B ∣ A ) are usually different. LEARN P ( A ′ ∣ B ) = 1 − P ( A ∣ B ) \mathrm{P}(A' \mid B) = 1 - \mathrm{P}(A \mid B) P ( A ′ ∣ B ) = 1 − P ( A ∣ B ) , but P ( A ∣ B ′ ) \mathrm{P}(A \mid B') P ( A ∣ B ′ ) needs the definition again.LEARN With a random variable, the top is the overlap of the two inequalities: P ( X > 7 ∣ X ≤ 9 ) = P ( 8 ≤ X ≤ 9 ) P ( X ≤ 9 ) \mathrm{P}(X > 7 \mid X \le 9) = \frac{\mathrm{P}(8 \le X \le 9)}{\mathrm{P}(X \le 9)} P ( X > 7 ∣ X ≤ 9 ) = P ( X ≤ 9 ) P ( 8 ≤ X ≤ 9 ) . LEARN P ( A ∣ B ) = P ( A ) = P ( A ∣ B ′ ) \mathrm{P}(A \mid B) = \mathrm{P}(A) = \mathrm{P}(A \mid B') P ( A ∣ B ) = P ( A ) = P ( A ∣ B ′ ) LEARN P ( A ∩ B ) = P ( A ) P ( B ) \mathrm{P}(A \cap B) = \mathrm{P}(A)\,\mathrm{P}(B) P ( A ∩ B ) = P ( A ) P ( B ) BOOKLET To test independence, compare two values that would be equal, write = = = or ≠ \ne = , then conclude. LEARN z = x − μ σ z = \dfrac{x - \mu}{\sigma} z = σ x − μ BOOKLET x = μ + z σ x = \mu + z\sigma x = μ + z σ LEARN P ( X < x ) = p ⟹ x − μ σ = z , where P ( Z < z ) = p \mathrm{P}(X < x) = p \implies \frac{x - \mu}{\sigma} = z, \text{ where } \mathrm{P}(Z < z) = p P ( X < x ) = p ⟹ σ x − μ = z , where P ( Z < z ) = p LEARN z z z counts standard deviations from the mean: positive above, negative below. Rearranged, x = μ + z σ x = \mu + z\sigma x = μ + z σ .LEARN Z ∼ N ( 0 , 1 ) Z \sim \mathrm{N}(0, 1) Z ∼ N ( 0 , 1 ) is the standard normal, and P ( X < x ) = P ( Z < z ) \mathrm{P}(X < x) = \mathrm{P}(Z < z) P ( X < x ) = P ( Z < z ) .LEARN Unknown μ \mu μ or σ \sigma σ : inverse normal with mean 0 0 0 and standard deviation 1 1 1 gives z z z , then solve x − μ σ = z \frac{x - \mu}{\sigma} = z σ x − μ = z . LEARN Both unknown: two probabilities give two equations in μ \mu μ and σ \sigma σ . Solve them together. LEARN Inverse normal wants the area to the left: for P ( X > x ) = p \mathrm{P}(X > x) = p P ( X > x ) = p , use 1 − p 1 - p 1 − p . LEARN P ( B ∣ A ) = P ( B ) P ( A ∣ B ) P ( B ) P ( A ∣ B ) + P ( B ′ ) P ( A ∣ B ′ ) \mathrm{P}(B \mid A) = \dfrac{\mathrm{P}(B)\,\mathrm{P}(A \mid B)}{\mathrm{P}(B)\,\mathrm{P}(A \mid B) + \mathrm{P}(B')\,\mathrm{P}(A \mid B')} P ( B ∣ A ) = P ( B ) P ( A ∣ B ) + P ( B ′ ) P ( A ∣ B ′ ) P ( B ) P ( A ∣ B ) BOOKLET P ( B i ∣ A ) = P ( B i ) P ( A ∣ B i ) P ( B 1 ) P ( A ∣ B 1 ) + P ( B 2 ) P ( A ∣ B 2 ) + P ( B 3 ) P ( A ∣ B 3 ) \mathrm{P}(B_{i} \mid A) = \dfrac{\mathrm{P}(B_{i})\,\mathrm{P}(A \mid B_{i})}{\mathrm{P}(B_{1})\,\mathrm{P}(A \mid B_{1}) + \mathrm{P}(B_{2})\,\mathrm{P}(A \mid B_{2}) + \mathrm{P}(B_{3})\,\mathrm{P}(A \mid B_{3})} P ( B i ∣ A ) = P ( B 1 ) P ( A ∣ B 1 ) + P ( B 2 ) P ( A ∣ B 2 ) + P ( B 3 ) P ( A ∣ B 3 ) P ( B i ) P ( A ∣ B i ) BOOKLET Top: the one path through the event you want. Bottom: every path that ends in the given event, which adds up to P ( A ) \mathrm{P}(A) P ( A ) . LEARN P ( B ∣ A ) \mathrm{P}(B \mid A) P ( B ∣ A ) and P ( A ∣ B ) \mathrm{P}(A \mid B) P ( A ∣ B ) are usually different. A rare cause can stay unlikely even after strong evidence.LEARN If P ( A ∣ B ) = P ( A ∣ B ′ ) \mathrm{P}(A \mid B) = \mathrm{P}(A \mid B') P ( A ∣ B ) = P ( A ∣ B ′ ) , then P ( B ∣ A ) = P ( B ) \mathrm{P}(B \mid A) = \mathrm{P}(B) P ( B ∣ A ) = P ( B ) , and A A A and B B B are independent. LEARN V a r ( X ) = E [ ( X − μ ) 2 ] = E ( X 2 ) − [ E ( X ) ] 2 \mathrm{Var}(X) = \mathrm{E}\left[(X - \mu)^{2}\right] = \mathrm{E}(X^{2}) - \left[\mathrm{E}(X)\right]^{2} Var ( X ) = E [ ( X − μ ) 2 ] = E ( X 2 ) − [ E ( X ) ] 2 BOOKLET ∫ − ∞ ∞ f ( x ) d x = 1 \int_{-\infty}^{\infty} f(x)\,\mathrm{d}x = 1 ∫ − ∞ ∞ f ( x ) d x = 1 LEARN P ( a ≤ X ≤ b ) = ∫ a b f ( x ) d x \mathrm{P}(a \le X \le b) = \int_{a}^{b} f(x)\,\mathrm{d}x P ( a ≤ X ≤ b ) = ∫ a b f ( x ) d x LEARN ∫ − ∞ m f ( x ) d x = 1 2 \int_{-\infty}^{m} f(x)\,\mathrm{d}x = \frac{1}{2} ∫ − ∞ m f ( x ) d x = 2 1 LEARN E ( X ) = μ = ∫ − ∞ ∞ x f ( x ) d x \mathrm{E}(X) = \mu = \int_{-\infty}^{\infty} x f(x)\,\mathrm{d}x E ( X ) = μ = ∫ − ∞ ∞ x f ( x ) d x BOOKLET V a r ( X ) = ∫ − ∞ ∞ ( x − μ ) 2 f ( x ) d x = ∫ − ∞ ∞ x 2 f ( x ) d x − μ 2 \mathrm{Var}(X) = \int_{-\infty}^{\infty} (x - \mu)^{2} f(x)\,\mathrm{d}x = \int_{-\infty}^{\infty} x^{2} f(x)\,\mathrm{d}x - \mu^{2} Var ( X ) = ∫ − ∞ ∞ ( x − μ ) 2 f ( x ) d x = ∫ − ∞ ∞ x 2 f ( x ) d x − μ 2 BOOKLET E ( a X + b ) = a E ( X ) + b , V a r ( a X + b ) = a 2 V a r ( X ) \mathrm{E}(aX + b) = a\mathrm{E}(X) + b, \quad \mathrm{Var}(aX + b) = a^{2}\mathrm{Var}(X) E ( a X + b ) = a E ( X ) + b , Var ( a X + b ) = a 2 Var ( X ) BOOKLET σ a X + b = ∣ a ∣ σ X \sigma_{aX + b} = \lvert a\rvert\,\sigma_{X} σ a X + b = ∣ a ∣ σ X LEARN V a r ( X ) = E ( X 2 ) − [ E ( X ) ] 2 , σ = V a r ( X ) \mathrm{Var}(X) = \mathrm{E}(X^{2}) - \left[\mathrm{E}(X)\right]^{2}, \quad \sigma = \sqrt{\mathrm{Var}(X)} Var ( X ) = E ( X 2 ) − [ E ( X ) ] 2 , σ = Var ( X ) BOOKLET A pdf has f ( x ) ≥ 0 f(x) \ge 0 f ( x ) ≥ 0 and total area ∫ f ( x ) d x = 1 \int f(x)\,\mathrm{d}x = 1 ∫ f ( x ) d x = 1 . Probabilities are areas, so P ( X = a ) = 0 \mathrm{P}(X = a) = 0 P ( X = a ) = 0 . LEARN Split every integral of a piecewise density where the formula changes, and include every piece. LEARN
Mode: the x x x where f f f is largest (check the ends too). Median: ∫ − ∞ m f ( x ) d x = 1 2 \int_{-\infty}^{m} f(x)\,\mathrm{d}x = \frac{1}{2} ∫ − ∞ m f ( x ) d x = 2 1 . LEARN E ( X ) = ∫ x f ( x ) d x , E ( X 2 ) = ∫ x 2 f ( x ) d x \mathrm{E}(X) = \int x f(x)\,\mathrm{d}x, \quad \mathrm{E}(X^{2}) = \int x^{2} f(x)\,\mathrm{d}x E ( X ) = ∫ x f ( x ) d x , E ( X 2 ) = ∫ x 2 f ( x ) d x LEARN A game is fair when the player's expected gain is 0 0 0 . LEARN Which method when Is a value an outlier? → compare it with Q 1 − 1.5 × I Q R Q_{1} - 1.5 \times \mathrm{IQR} Q 1 − 1.5 × IQR and Q 3 + 1.5 × I Q R Q_{3} + 1.5 \times \mathrm{IQR} Q 3 + 1.5 × IQR (4.1) LEARN Predict y y y from x x x → regression line of y y y on x x x . Predict x x x from y y y → line of x x x on y y y . Only inside the range of the data (4.4, 4.10) LEARN “At least one” → 1 − P ( none ) 1 - \mathrm{P}(\text{none}) 1 − P ( none ) (4.5) LEARN Two stages, with or without replacement → tree diagram: multiply along a path, add across paths (4.6) LEARN
“Given that” → P ( A ∣ B ) = P ( A ∩ B ) P ( B ) \mathrm{P}(A \mid B) = \frac{\mathrm{P}(A \cap B)}{\mathrm{P}(B)} P ( A ∣ B ) = P ( B ) P ( A ∩ B ) , with the given event on the bottom (4.6, 4.11) LEARN Are A A A and B B B independent? → compare P ( A ∩ B ) \mathrm{P}(A \cap B) P ( A ∩ B ) with P ( A ) P ( B ) \mathrm{P}(A)\,\mathrm{P}(B) P ( A ) P ( B ) , then conclude (4.6, 4.11) LEARN Unknown k k k in a probability distribution → the probabilities add up to 1 1 1 . Fair game → E ( X ) = 0 \mathrm{E}(X) = 0 E ( X ) = 0 (4.7) LEARN Fixed number of independent trials, two outcomes, same p p p → binomial, X ∼ B ( n , p ) X \sim \mathrm{B}(n, p) X ∼ B ( n , p ) (4.8) LEARN Normal, value to probability → normal cdf. Probability to value → inverse normal, using the area to the left (4.9) LEARN
Normal with μ \mu μ or σ \sigma σ unknown → get z z z from the inverse normal of N ( 0 , 1 ) \mathrm{N}(0, 1) N ( 0 , 1 ) , then solve x − μ σ = z \frac{x - \mu}{\sigma} = z σ x − μ = z (4.12) LEARN ◆ Which method whenProbability of a first-stage event, given what happened next → Bayes' theorem: that path over every path to the given event (4.13) LEARN
Continuous random variable with pdf f f f → probabilities by ∫ f ( x ) d x \int f(x)\,\mathrm{d}x ∫ f ( x ) d x ; median m m m from ∫ − ∞ m f ( x ) d x = 1 2 \int_{-\infty}^{m} f(x)\,\mathrm{d}x = \frac{1}{2} ∫ − ∞ m f ( x ) d x = 2 1 ; E ( X ) = ∫ x f ( x ) d x \mathrm{E}(X) = \int x f(x)\,\mathrm{d}x E ( X ) = ∫ x f ( x ) d x (4.14) LEARN