{"id":"study-survey-bias-three-lines","audience":"high-school","category":"explaining","technique":"format","track":"study","title":"Explain the bias in a school survey in three lines","free":false,"task":"Your AP Statistics free-response practice asks what's wrong with a student council survey. You want to understand it in exactly 3 numbered lines: the name of the bias using your class's term, how it skews this survey's result, and one fix from your notes, each under 20 words, plain text. Use only your notes and the survey details, not other types of bias.","materialLabel":"The survey and your stats notes (attached to your prompt automatically)","material":"AP STATS - Unit 3 - Sampling & bias (Mr. Ibarra)\n\nPRACTICE FRQ: The student council wanted to know if students support a later school start time. They posted a link to an online poll on the council's Instagram and left it open for a week. 412 students responded, and 88% said they support a later start. The council president says, \"This proves most students at our school want a later start.\"\n\nMY NOTES:\n- Voluntary response bias: people choose whether to respond. Usually people with STRONG opinions respond, so results lean toward the strongest feelings.\n- Undercoverage: some groups are left out of the sample or have less chance to be picked.\n- Nonresponse bias: people who are CHOSEN for the sample don't respond.\n  (Mr. Ibarra: \"Don't mix these up. Nonresponse = you picked them and they ignored you. Voluntary = they picked themselves.\")\n- Fixes: use a simple random sample (SRS) from the school roster, then follow up with the people chosen.\n- On FRQs: name the bias, explain the DIRECTION it pushes the result, in context.\n\nSchool has 1,900 students.\n\nMy first guess was nonresponse bias but I'm not sure.","rules":[{"type":"numberedItems","count":3},{"type":"maxWords","max":65},{"type":"plainText"}],"mistakes":[{"title":"Asking what's wrong","why":"The AI lists every possible problem with the survey, which is not how an FRQ wants it.","fix":"Give the shape: \"3 lines: bias name, how it skews this result, one fix.\"","checks":["r0"]},{"title":"Not saying how many lines","why":"The AI picks its own number, and it usually picks more lines than you need.","fix":"Be exact: \"Exactly 3 numbered lines.\"","checks":["numberedItems"]},{"title":"Missing the direction","why":"The AI often names the bias but never says which way it pushes the 88%, which is what the FRQ grades.","fix":"Add: \"Say which direction it pushes the result, in context.\"","checks":["r1"]},{"title":"Letting in other biases","why":"The AI piles on undercoverage and wording bias, which muddies your answer.","fix":"Add: \"Only the main bias and the fix from my notes.\"","checks":["r2"]},{"title":"Trusting the AI to count words","why":"AI is bad at counting. Ask for a total and it often lands 20% over.","fix":"Cap each line: \"each line under 18 words.\"","checks":["maxWords"]},{"title":"Forgetting where it will be read","why":"AI formats for a screen, with bold and headings that show up as stray symbols in your notes.","fix":"Say: \"Plain text, no bold, no headings.\"","checks":["plainText"]}],"promptHints":[{"label":"Says how many lines","patterns":["\\b(3|three)\\b.{0,25}line"]},{"label":"Asks for the direction","patterns":["direction","overstate","push","which way","in context"]},{"label":"Uses class terms","patterns":["my notes","class term","voluntary","from (my|the) notes"]},{"label":"Sets a length limit","patterns":["\\d+\\s*words","word (limit|count)","under \\d+"]},{"label":"Asks for plain text","patterns":["plain","no bold","no markdown","no formatting","no headings"]}],"hint":"AP Stats FRQs grade a specific shape: name it, explain the direction in context, give a fix. Ask the AI for exactly that, one line each, using your notes.","rubricLabels":["Line 1 names voluntary response bias (not nonresponse bias), and no other bias types (such as undercoverage) appear anywhere in the output","Line 2 explains the direction in context: students who feel strongly about a later start were more likely to respond, so the 88% likely overstates support","Line 3 gives the fix from the notes (a simple random sample from the school roster, with follow-up), and nothing comes before line 1 or after line 3"]}