BOOKLET given in the examLEARN you must remember it · Each block links to its lesson.
Statistics and probability
IB MATHS AI · HLpastpaperprep.com/revision-notes
4.1Sampling, data quality and outliers
Population: the whole group a question is about. Sample: the part you collect data from. Counted data is discrete; measured data is continuous, even when rounded.LEARN
Sampling bias comes from how a sample is chosen; a bigger sample chosen the same way doesn't remove it.LEARN
Leave a missing value out and say how many are missing; never record it as . Correct a recording error only if you know the true value; otherwise remove it and say so.LEARN
(in the formula booklet).BOOKLET
LEARN
A value exactly on a fence is not an outlier. Keep an outlier that is possible in context; correct or remove only an error.LEARN
Simple random: every sample of that size equally likely. Systematic: every th of an ordered list, (rounded down if not whole), random start in the first , stop at (if doesn't divide , the end of the list is never chosen). Stratified: random within groups, in proportion. Quota: fixed numbers per group, collector chooses. Convenience: easiest to reach.LEARN
LEARN
4.2Data presentation
Class intervals are inequalities with no gaps and no overlaps, such as and . A boundary value goes in the class whose inequality it satisfies.LEARN
In a histogram with equal class widths, each bar's height is its frequency and neighbouring bars touch.LEARN
Plot cumulative frequency at each upper class boundary, starting from at the first lower boundary. It counts values at or below a point, so for “more than” subtract the reading from .LEARN
On a cumulative frequency graph of values, read across from for , for the median, for and for the th percentile.LEARN
BOOKLET
Box plot: box from to , a line at the median, whiskers to the most extreme values that are not outliers, and a cross for each outlier.LEARN
Compare two box plots by their medians and their IQRs or ranges, with numbers and in context. A symmetric box with equal whiskers means the data may be normal; a skewed one is unlikely to be.LEARN
4.3Central tendency and dispersion
BOOKLET
Median: the th value in order; for even , the mean of the middle two. Mode: the most frequent value.LEARN
Grouped data: estimate the mean with mid-interval values . With equal class widths, the modal class is the class with the highest frequency.LEARN
BOOKLET
Quartiles of discrete data: use the GDC. Methods differ, so a by-hand value can differ from the GDC's.LEARN
Standard deviation of a data set: GDC only, using , not . Variance : square the unrounded value.LEARN
Every value : mean , standard deviation , variance . Adding a constant leaves unchanged.LEARN
4.4Correlation and regression (y on x)
Describe correlation by direction (positive, negative or zero) and strength (strong, weak or none), in context.LEARN
LEARN
Pearson's measures linear correlation only: near means no straight-line link, but there may be a curve.LEARN
If is greater than the critical value for that number of pairs and significance level, the linear correlation is significant at that level.LEARN
A line of best fit by eye and the regression line of on both pass through the mean point .LEARN
Correlation does not imply causation: a third variable may drive both.LEARN
In the regression line , is the predicted change in for each increase of in , and is the predicted when , which only means something if makes sense and is near the data.LEARN
Use the on line only to predict , for inside the data range and when the correlation is strong; it cannot reliably predict from .LEARN
4.5Probability foundations and expected value
A trial has outcomes; the sample space lists them all; an event is a set of outcomes. For two stages, list pairs or draw a table.LEARN
BOOKLET
Every probability is between and . From a two-way table with one person chosen at random from everyone in it, divide by the grand total.LEARN
Relative frequency is an experimental estimate of a probability. More trials usually give a better estimate.LEARN
BOOKLET
For "at least one", use .LEARN
Expected number of occurrences for trials. It is a long-run average, so it need not be a whole number.LEARN
4.6Probability diagrams, rules and independence
Fill a Venn diagram from the middle out: the overlap, then the rest of each circle, then the outside. "Or" includes both: means , or both.LEARN
BOOKLET
Mutually exclusive events can't both happen, so . That is not the same as independent.LEARN
BOOKLET
BOOKLET
LEARN
Tree diagrams: multiply along a path, add across paths. Without replacement, the totals and second-stage probabilities change.LEARN
BOOKLET
4.7Discrete random variables and expected value
A discrete random variable has a list of possible values . Its probability distribution gives for each one, as a table or a formula.LEARN
LEARN
BOOKLET
is the long-run mean of . It need not be a value can take. Over independent repeats of the trial, expect a total of .LEARN
GDC: one-variable statistics with the values as data and the probabilities as frequencies gives ; with the probabilities entered as they are, the total frequency should be .LEARN
LEARN
4.8Binomial distribution
counts the successes in a fixed number of independent trials, each with two outcomes and the same probability of success.LEARN
On a GDC, binomial pdf gives and binomial cdf gives .LEARN
For binomial (whole numbers only): and .LEARN
BOOKLET
BOOKLET
For , is the expected number of successes: a long-run average that need not be a whole number. The standard deviation is .LEARN
4.9Normal distribution
LEARN
LEARN
LEARN
: a symmetric bell-shaped curve about , with total area . Mean, median and mode all equal . The second number is the variance.LEARN
For a continuous random variable, , so and give the same probability.LEARN
Normal cdf takes lower bound, upper bound, and . Use as the lower bound for less than, and as the upper bound for more than.LEARN
Inverse normal, with the tail set to left, returns from . For a middle region of probability centred on , each tail holds .LEARN
Expected number of independent items in a region , using the unrounded probability. Give it to 3 s.f.: it need not be a whole number.LEARN
4.10Spearman's rank correlation
Rank each variable separately, both in the same direction. Tied values each get the mean of the ranks they share.LEARN
is Pearson's calculated on the ranks. On the GDC: enter the two lists of ranks, run linear regression, read .LEARN
. : the rankings are identical. : one is the exact reverse of the other.LEARN
Pearson's measures only linear correlation. measures any monotonic relationship, straight or curved.LEARN
is less sensitive to outliers than : an extreme value can only take the top or bottom rank.LEARN
A link that rises then falls can give and near , and neither coefficient shows causation.LEARN
4.11Chi-squared tests and the t-test
LEARN
is the no-effect claim: independent, fits the claimed distribution, or for population means.LEARN
Reject when the p-value is less than the significance level, or is greater than the critical value.LEARN
Expected frequencies are what predicts. The test needs every expected frequency greater than : SL exam questions always meet this; at HL you may need to merge classes first.LEARN
χ² tests use the upper tail only. df for an contingency table; df for goodness of fit at SL ( categories).LEARN
SL t-test: pooled two-sample, unpaired samples, normal populations, equal population variances. is two-tailed; or is one-tailed.LEARN
Every conclusion gives the comparison, the decision and its meaning in context.LEARN
4.12 ◆Data collection, reliability and validity
Good survey questions are unbiased (neutral wording) and precise (one meaning, a stated time period). Structured answer choices don't overlap and cover every possible answer. Ask personal questions only if needed, and anonymously.LEARN
Choose variables linked to the question. For a linear model, compare candidates by the size of , not its sign. Use only data from the population and conditions the question is about, and say what you left out.LEARN
In IB χ² questions every expected frequency must be greater than . Merge a small class with an adjacent class, observed and expected together, until every expected frequency is greater than , then count the categories again.LEARN
Goodness of fit: , with categories after merging and parameters estimated from the data. Binomial estimated: ; normal and estimated: ; parameters given in the question: .LEARN
Reliability: the same results when the method is repeated under the same conditions. Validity: the method measures what it claims to. Reliable does not mean valid.LEARN
Reliability checks: test–retest (same test, same people, two times) and parallel forms (two equivalent versions, same people). A strong positive correlation between the two sets of scores suggests reliability.LEARN
Validity checks: content (the test covers every part of what it should) and criterion-related (a strong correlation, in the expected direction, with an established measure of the same thing).LEARN
4.13 ◆Non-linear regression and R²
Choose the model type from the context and the scatter diagram (or the form the question names); the GDC fits the parameters. Give them to 3 s.f.LEARN
Residual , observed minus predicted: positive above the curve, negative below.LEARN
LEARN
For models fitted to the same data, a smaller means a closer fit; the least squares curve of a type has the smallest of that type (the GDC's exponential and power regressions minimise it for instead).LEARN
is the proportion of the variation in that the model accounts for. For a linear least squares model, .LEARN
alone does not choose a model: check the context, the shape and any extrapolation. On the same data, a cubic regression's is never lower than a quadratic regression's.LEARN
4.14 ◆Linear combinations and unbiased estimates
BOOKLET
BOOKLET
The standard deviation of is . Adding a constant moves the mean but not the spread.LEARN
Expected values add for any random variables, independent or not: .BOOKLET
Only for independent : . Every term is added, even for a difference. Add variances, never standard deviations.BOOKLET
The total of independent items, each with mean and variance , has mean and variance . One item scaled by , , has variance .LEARN
From a random sample, is an unbiased estimate of and is an unbiased estimate of . On the GDC, is Sx (sx on the Casio and Nspire).BOOKLET
4.15 ◆Sample mean and the central limit theorem
If are independent and each is normal, then is normal. Find its mean and variance with the booklet rules, then enter in normal cdf.LEARN
LEARN
For a random sample of size from a population with variance , and the standard deviation of is : four times the sample size halves the spread.LEARN
Central limit theorem: for a random sample of size from any population with mean and variance , is approximately when is large. How large depends on the population; in IB exams is enough.LEARN
A normal population gives an exactly normal for every . A population that is not normal needs a large sample before can be treated as normal.LEARN
4.16 ◆Confidence intervals for the mean
LEARN
LEARN
For the mean of a normal population: known, use the normal distribution; unknown, use the t-distribution with degrees of freedom and , whatever the sample size.LEARN
Normal multipliers ( known): for , for , for .LEARN
A confidence interval comes from a method that captures for about of random samples. One interval either contains or not.LEARN
A claimed mean inside the interval is plausible (no evidence against it); one outside the interval is evidence against the claim.LEARN
From the same sample, a higher confidence level gives a wider interval. At the same confidence level and standard deviation, a larger sample gives a narrower one.LEARN
4.17 ◆Poisson distribution
models the number of events in a fixed interval of time or space when the events happen independently at a uniform average rate of per interval. can be with no upper limit.LEARN
BOOKLET
BOOKLET
Because the rate is uniform, a Poisson mean of per unit interval becomes for an interval times as long.LEARN
If and are independent, then . Multiples such as and differences such as are not Poisson.LEARN
Choosing a model: a continuous measurement with a symmetric bell-shaped spread is normal; successes in a fixed number of independent trials with constant are binomial; independent events in an interval at a uniform average rate, with no upper limit, are Poisson.LEARN
4.18 ◆Further hypothesis tests and errors
LEARN
Mean of a normal population: z-test when is known, t-test when is unknown, whatever the sample size. IB questions don't ask for a critical region in a t-test: decide with the p-value.LEARN
Matched pairs: take differences in a fixed order, then a one-sample t-test with : , assuming the differences are normally distributed.LEARN
In IB AI, binomial and Poisson tests are one-tailed. The critical region has the largest probability under that is still less than the significance level.LEARN
Correlation: test : with the GDC, assuming a bivariate normal distribution.LEARN
Type I error: rejecting a true . Its probability is the significance level for a normal test with known , and the critical region's probability under for a binomial or Poisson test.LEARN
Type II error: not rejecting a false . Its probability is , using a stated true parameter value.LEARN
4.19 ◆Transition matrices and Markov chains
BOOKLET
Transition matrix: is the chance of going to state at the next step, given the chain is in state now, so each column adds up to . Columns are “from”, rows are “to”.LEARN
In a transition diagram the probabilities on the arrows leaving any one state, including its loop, add up to .LEARN
is the probability of being in state after steps, starting in state . A probability along one fixed path is a product of single-step probabilities instead.LEARN
A Markov chain is regular when some power of has all its entries positive. Then the columns of all approach the steady state, whatever the start.LEARN
Steady state : with entries adding up to . For a regular chain it is unique: find it from a column of a high power of , or exactly by solving with one equation replaced by the sum .LEARN
A steady state is an eigenvector of for the eigenvalue , divided by the sum of its entries. For a regular chain there is only one.LEARN
Which method when
'Is this value an outlier?' → GDC one-variable stats for , ; outlier if or (a value on a fence is not one) (4.1)LEARN
'Estimate the median, quartiles or a percentile' from grouped data → cumulative frequency graph, plotted at upper class boundaries; read across from , , , (4.2)LEARN
'Find the mean and standard deviation' of data or a frequency table → GDC one-variable stats with the frequency list; quote , not ; grouped data uses mid-interval values, so the mean is an estimate (4.3)LEARN
'Is there linear correlation? Predict ' → GDC linear regression for and ; significant if is above the given critical value; predict only, for inside the data, when the correlation is strong (4.4)LEARN
'Given that', or 'or' / 'and' with an overlap → Venn diagram, two-way table or tree; ; multiply only for independent events (4.6)LEARN
A table of values with probabilities, 'find ', 'is the game fair?' → and ; fair when for the player's gain (4.7)LEARN
'Number of successes in trials', fixed , same , independent trials → ; binomial pdf for , binomial cdf for ; (4.8)LEARN
A measurement modelled as , 'find the probability' → normal cdf with , not ; 'find the value the top exceed' → inverse normal with left area (or area with the tail set to right) (4.9)LEARN
Ranked data, a curved but always rising or falling link, or an outlier → Spearman's : rank both variables the same way, tied values take the mean rank, then GDC linear regression on the ranks (4.10)LEARN
Counts in categories → χ² test on the GDC: two categorical variables in a table, 'is X independent of Y?' → test for independence, df ; one variable against claimed proportions ('equally likely', stated percentages) → goodness of fit, expected total × claimed proportion, df for categories; every expected frequency must be greater than (4.11)LEARN
Two independent (unpaired) groups of measurements, 'is the mean of A different from / greater than B?' → pooled two-sample t-test on the GDC, : , assuming normal populations with equal variances; is two-tailed, or one-tailed (4.11)LEARN
◆Which method when
Goodness of fit to a binomial or normal model whose parameters are estimated from the data → merge adjacent classes (observed and expected) until every expected frequency is greater than , then df ( classes after merging, parameters estimated) (4.12)LEARN
Curved scatter, or a named model such as , , quadratic, cubic or sine → GDC regression of that type, parameters to 3 s.f.; compare models on the same data by or , together with the context and any extrapolation, never alone (4.13)LEARN
Probability for a total or difference of independent normal quantities → mean by the rules, variance (added even for a difference), then normal cdf with ; for the mean of a random sample → , exactly for a normal population, approximately by the central limit theorem when (4.14, 4.15)LEARN
Events in a fixed interval of time or space, happening independently at a uniform average rate, 'how many in…' → with scaled to the interval, independent Poisson counts add; a fixed number of independent trials with constant → binomial instead (4.17)LEARN
Estimating or testing the mean of one normal population → given: Z interval or z-test; unknown: T interval or t-test with and degrees of freedom, whatever ; the same subjects measured twice → one-sample t-test on the differences, : (4.16, 4.18)LEARN
A count tested against a claimed proportion or rate → one-tailed binomial or Poisson test, p-value from the tail points to; 'is there correlation in the population?' → GDC test of : , assuming bivariate normal data (4.18)LEARN
States that change step by step, where the next depends only on the current state ('after 3 days', 'in the long run') → transition matrix with columns 'from', each adding up to , and ; long run → for a regular chain, the unique steady state with entries adding up to (an eigenvector for eigenvalue , scaled), which approaches from any start (4.19)LEARN
Follows the IB Maths AI guide (first assessment 2021). Not affiliated with the IB.