Question
Name the population, variable, and decision the analysis must support.
A 7-stage path beginning with Data displays and ending with Regression, with recall checks between major ideas.
Build the underlying ideas in the Statistics subject guide, use the statistics calculator to check a completed setup, and return to Probability & Statistics practice questions when you are ready to retrieve the method without a model.
Short cycles create evidence that the idea is becoming usable rather than merely familiar.
Name the population, variable, and decision the analysis must support.
Check how the data and assumptions permit the chosen method.
Return every numerical result to its units and context.
Inspect uncertainty, alternatives, and conclusions the evidence cannot support.
Later conclusions depend on how the question, data, assumptions, and model were established earlier.
Each unit names the actual skills, demonstrates one complete case, and identifies the mistake most likely to change the result.
You can build and read dot plots, histograms, box plots and two-way tables. You can also describe the shape of a distribution and say what that shape means.
Interpretation risk: Counting the median into both halves when finding the quartiles here, which gives Q1 = 7.5 and Q3 = 13.5 instead of 7 and 15.
You can find mean, median, range and standard deviation, and say which one describes a data set honestly. You can also flag outliers with a rule instead of a hunch.
Interpretation risk: Reporting the mean 20 as the typical value: it sits above four of the five numbers because the single value 84 hauls it upward.
You can find the chance of combined events using addition, multiplication and complements. You can also tell independent events from ones that change each other.
Interpretation risk: Using 5/8 twice: reporting 25/64, about 0.391, which quietly assumes the first marble went back in the bag.
You can build a probability table for a numeric outcome and find its expected value and spread. You can also use the binomial rule for a fixed number of yes-or-no trials.
Interpretation risk: Averaging the payouts instead of weighting them: reporting (10 + 0)/2 = 5 per play, which would make a losing game look profitable.
You can pick a sample that stands in for a whole group and name the bias when it does not. You can also tell a survey, an observational study and an experiment apart.
Interpretation risk: Taking all 80 students from one grade and calling it stratified, which measures a single grade rather than the school.
You can build a range that probably holds the true value and say what that range does and does not mean. You can also show how sample size changes the width.
Interpretation risk: Saying there is a 95% chance the true value sits in this particular interval: the 95% describes how often the method works across many samples, not this one range.
You can fit a straight line to a scatterplot, predict with it, and judge how well it fits. You can also explain why a strong link is not proof that one thing causes another.
Interpretation risk: Treating the slope as the prediction: answering 2.5 when x = 8, which throws away the starting value of 12 and the multiplication entirely.
Start with the earliest unit whose definitions or notation you cannot explain from memory. Later units often depend on that foundation even when the current assignment looks different.
Move on after you can choose the method on a changed problem, complete it without copying a model, and check the answer independently.
Begin without a hint, record the first uncertain decision, repair only that connection, and then answer a fresh question to test whether the repair transferred.