Describing Data Patterns

Overview

This is lesson 3 of 6 in “Interpret Statistical Information”. Students build on previous work with statistical displays and summary measures by describing distributions, trends, unusual features and associations accurately, using evidence and context rather than unsupported claims.

Learning intentions

We are learning to:

• describe centre, spread, shape, clusters, gaps, outliers and variation;
• identify increasing, decreasing and seasonal trends, and positive, negative or no apparent association;
• support descriptions with values, ranges or visible features;
• distinguish observation from interpretation and avoid claiming causation from association alone.

Success criteria

• I can use appropriate statistical language to describe a display.
• I can structure a statement as feature + evidence + context.
• I can support my description with a value, range or visible feature.
• I can identify when a statement claims more than the data shows.

Curriculum links

• Use statistical methods to make an inference: discuss distributions, sampling variability, visual features and conclusions in context.
• Evaluate a statistically based report: identify whether findings are supported by appropriate evidence and recognise possible limitations.
• Apply probability methods in solving problems: communicate statistical thinking using appropriate representations and statements.
• NZC competencies: thinking; using language, symbols and texts; managing self; participating and contributing.

Lesson structure (60 minutes)

1. 0–5 min · Hook and retrieval. Teacher displays two contrasting graphs from a local dataset using the opening comparison slides and asks, “What can we safely say, and what would be an overclaim?” Students silently write one observation and share it with a partner.

2. 5–17 min · Model precise descriptions. Teacher introduces the structure “feature + evidence + context” and models examples such as, “Most recorded travel times were between 20 and 35 minutes, suggesting this was the usual range for this group.” Using the modelling slides, teacher explicitly teaches language for typical values, modal categories, centre, spread, symmetric and skewed distributions, clusters, gaps, outliers, and increasing, decreasing or seasonal trends. Students annotate a labelled exemplar and improve an imprecise sentence.

3. 17–27 min · Observation or overclaim? Teacher gives pairs statements from the statement classification and interpretation worksheet and asks students to classify each as observation, interpretation or unsupported claim. Students justify their classification, then rewrite two weak statements so they include evidence and context. Teacher checks responses and addresses the difference between association and causation.

4. 27–45 min · Paired-display investigation. Teacher distributes the worksheet and directs students to analyse paired displays from a local dataset, choosing a less complex display if needed. Students describe at least three relevant features, including a value, range or graph feature for each, and write a short comparison or association statement. They use the prompts on the paired-display task slides and may work from a graph or spreadsheet. Teacher conferences with selected students, prompting: “What do you see?”, “What evidence supports that?”, and “What does this mean in context?”

5. 45–53 min · Spoken interpretation. Teacher models a 30-second spoken interpretation and reminds students to use cautious language such as “is associated with”, “appears to” and “in this sample”. In pairs, students present their interpretation of one display while their partner listens for feature, evidence and context, using the speaking checklist slide.

6. 53–60 min · Written response and exit check. Students submit one accurate paragraph from their analysis for feedback focused on accuracy, evidence and context. They complete the final check on the paragraph and reflection section: identify one statement that avoids causation and explain why. Teacher collects responses to plan the next lesson.

Resources

• the full teaching and discussion slide deck
• the statistical interpretation worksheet
• Local dataset with paired displays
• Graph paper or spreadsheet software
• Calculators
• Display cards or projected statement cards
• Statistical language word wall
• Interpretation scaffold and labelled exemplars

Assessment

• During modelling and classification, listen for correct use of centre, spread, shape, trend, association and outlier language.
• Check rewritten statements for a clear feature, relevant evidence and contextual meaning; identify students who confuse observation, interpretation and unsupported claim.
• Collect one paragraph and the final reflection. Give feedback on accuracy, evidence and context, including whether the student has incorrectly implied causation.

Differentiation

• Provide a word wall, labelled exemplars and sentence frames: “The distribution is ___ because ___; in this context, this suggests ___.” Allow students to choose a less complex display.
• Support learners through a teacher conference, pre-highlighted graph features, paired reading of prompts and oral rehearsal before writing. Offer enlarged displays and reduced writing load where required.
• For EAL learners, explicitly teach meanings through examples, visuals and repeated oral practice; accept labelled annotations before expecting a full paragraph.
• Extend students by asking them to explain how an outlier or the choice of mean, median or range affects the interpretation, and to consider whether another variable could explain an apparent association.
• Include a culturally responsive discussion: ask whose experiences are represented in the local dataset, how categories and time periods were defined, and who may be missing or grouped together. Students consider how these choices affect the conclusions that can reasonably be drawn.