July 21, 2021 Conference paper Open Access

Chiodini Luca

Citation Style Language JSON Export

{
  "publisher": "Zenodo", 
  "DOI": "10.5281/zenodo.5118719", 
  "author": [
    {
      "family": "Chiodini Luca"
    }
  ], 
  "issued": {
    "date-parts": [
      [
        2021, 
        7, 
        21
      ]
    ]
  }, 
  "abstract": "<p>This folder contains anonymized data from the experiment described in the paper &quot;Wrong Answers for Wrong Reasons: The Risks of Ad Hoc Instruments&quot;.</p>\n\n<ul>\n\t<li><code>questions.md</code>&nbsp;contains the 14 questions used as pre/post-test</li>\n\t<li>Participants are identified using numeric identifiers (from 1 to 40).</li>\n\t<li><code>conditions.csv</code> contains the mapping between participants identifiers and their condition</li>\n\t<li>\n\t<p><code>{test}_{assessment_type}_anon.csv</code> contains data for a given test (<code>pretest</code> or <code>posttest</code>) using a certain assessment type. Two assessment types are used:</p>\n\n\t<ul>\n\t\t<li><code>mc</code> (multiple choice as assessed by Moodle: <code>0</code> means wrong, <code>1</code> means correct, <code>-</code> means missing)</li>\n\t\t<li><code>revised</code> (human revision after reading the explanation: the judgment is either a <code>0</code> or a <code>1</code> following what presented in the paper)</li>\n\t</ul>\n\t</li>\n\t<li>\n\t<p>Statistics are computed with Python and SciPy. You can execute the script by running:</p>\n\n\t<pre><code>python3 main.py\n</code></pre>\n\n\t<p>and you should get this output:</p>\n\n\t<pre><code>=== Analyzing answers using mc as assessment type ===\nResults on pretest - Condition Text: N: 21, mean \u00b1 std: 9.81 \u00b1 3.03\nResults on pretest - Condition Graphic: N: 19, mean \u00b1 std: 9.68 \u00b1 2.11\nMann Whitney U on pretest scores: U=184.0, p=0.3406\n\nResults on posttest - Condition Text: N: 21, mean \u00b1 std: 11.19 \u00b1 2.75\nResults on posttest - Condition Graphic: N: 19, mean \u00b1 std: 10.74 \u00b1 2.23\nMann Whitney U on posttest scores: U=164.0, p=0.1681\n\n=== Analyzing answers using revised as assessment type ===\nResults on pretest - Condition Text: N: 20, mean \u00b1 std: 9.15 \u00b1 3.10\nResults on pretest - Condition Graphic: N: 19, mean \u00b1 std: 7.89 \u00b1 3.16\nMann Whitney U on pretest scores: U=150.5, p=0.1344\n\nResults on posttest - Condition Text: N: 20, mean \u00b1 std: 11.15 \u00b1 2.39\nResults on posttest - Condition Graphic: N: 19, mean \u00b1 std: 9.42 \u00b1 3.11\nMann Whitney U on posttest scores: U=123.0, p=0.0299\n</code></pre>\n\n\t<p>You might need to install <code>scipy</code> (e.g., depending on your setup, <code>pip install scipy</code>).</p>\n\t</li>\n</ul>", 
  "title": "Wrong Answers for Wrong Reasons: The Risks of Ad Hoc Instruments", 
  "type": "paper-conference", 
  "id": "5118719"
}