mirror of
https://github.com/HananoshikaYomaru/openfreebooks.git
synced 2026-11-13 13:05:51 +00:00
93 lines
3.6 KiB
Markdown
93 lines
3.6 KiB
Markdown
+++
|
|
title = "Statistical literacy"
|
|
description = "Evaluate claims in media and research: sampling bias, correlation versus causation, and misleading charts."
|
|
template = "chapter.html"
|
|
weight = 35
|
|
[extra]
|
|
subject = "math"
|
|
chapter_id = "statistical-literacy"
|
|
strand = "Data Handling"
|
|
+++
|
|
|
|
<div class="book-prose">
|
|
<p>
|
|
Statistical literacy is the ability to read claims critically, question data quality, and avoid
|
|
misleading conclusions.
|
|
</p>
|
|
|
|
<h2 id="good-questions" class="book-prose__heading">Questions to ask about a claim</h2>
|
|
<ul>
|
|
<li>Who collected the data and why?</li>
|
|
<li>How large and representative is the sample?</li>
|
|
<li>How was the data measured?</li>
|
|
<li>Are conclusions consistent with evidence?</li>
|
|
</ul>
|
|
|
|
<h2 id="sampling-bias" class="book-prose__heading">Sampling and bias</h2>
|
|
<p>
|
|
Biased samples produce unreliable conclusions. Prefer random, sufficiently large, and
|
|
representative samples.
|
|
</p>
|
|
|
|
<h2 id="correlation-causation" class="book-prose__heading">Correlation vs causation</h2>
|
|
<p>
|
|
Correlation means variables move together. It does <strong>not</strong> prove one causes the other.
|
|
Confounders may explain both.
|
|
</p>
|
|
|
|
<h2 id="misleading-charts" class="book-prose__heading">Misleading charts</h2>
|
|
<ul>
|
|
<li>Truncated axes exaggerating differences.</li>
|
|
<li>Inconsistent scales.</li>
|
|
<li>Cherry-picked time ranges.</li>
|
|
<li>3D chart distortion.</li>
|
|
</ul>
|
|
|
|
<h2 id="risk-language" class="book-prose__heading">Interpreting risk language</h2>
|
|
<p>
|
|
Distinguish <strong>absolute change</strong> from <strong>relative change</strong>.
|
|
“Risk doubled” may still represent a very small absolute increase.
|
|
</p>
|
|
|
|
<h2 id="exam-strategy" class="book-prose__heading">Exam strategy</h2>
|
|
<ul>
|
|
<li>Quote numerical evidence when critiquing claims.</li>
|
|
<li>Mention possible bias/confounding clearly.</li>
|
|
<li>Use “suggests” unless causation is justified by design.</li>
|
|
<li>Comment on uncertainty and data limitations.</li>
|
|
</ul>
|
|
</div>
|
|
|
|
<div class="book-prose">
|
|
<h2 id="checkpoints" class="book-prose__heading">Checkpoints</h2>
|
|
<details class="book-question">
|
|
<summary class="book-question__prompt">A survey about school meals only asks students in one class. Name one issue.</summary>
|
|
<div class="book-question__solution">
|
|
<p><strong>Answer:</strong> Sampling bias; sample may not represent the whole school.</p>
|
|
</div>
|
|
</details>
|
|
<details class="book-question">
|
|
<summary class="book-question__prompt">Two variables are strongly correlated. Can we conclude causation?</summary>
|
|
<div class="book-question__solution">
|
|
<p><strong>Answer:</strong> No, correlation alone is insufficient.</p>
|
|
</div>
|
|
</details>
|
|
<details class="book-question">
|
|
<summary class="book-question__prompt">A bar chart axis starts at 95 instead of 0. Why can this mislead?</summary>
|
|
<div class="book-question__solution">
|
|
<p><strong>Answer:</strong> Differences look much larger than they really are.</p>
|
|
</div>
|
|
</details>
|
|
<details class="book-question">
|
|
<summary class="book-question__prompt">“Risk increased from 1% to 2%.” State absolute and relative increase.</summary>
|
|
<div class="book-question__solution">
|
|
<p><strong>Answer:</strong> Absolute +1 percentage point; relative increase 100% (doubled).</p>
|
|
</div>
|
|
</details>
|
|
<details class="book-question">
|
|
<summary class="book-question__prompt">Name one way to improve reliability of a poll.</summary>
|
|
<div class="book-question__solution">
|
|
<p><strong>Answer:</strong> Use a larger random sample from the target population.</p>
|
|
</div>
|
|
</details>
|
|
</div>
|