PSYC 3377 CHAPTER 9

Chapter 9: Multiple Choice Items

Introduction to Multiple Choice Items

  • Overview: Emphasizes choosing answer “C” yielding correct answers approximately 25% of the time.
  • Recording Notice: All lectures are audio recorded.
  • Source Reference: All content sourced from Salkind, Tests and Measurement 3e. SAGE Publishing (2018).

Characteristics of Multiple-Choice Items

  • Preferred Testing Method:
    • Widely utilized for testing achievement-oriented outcomes.
    • Common in fields such as:
    • Chemistry
    • Biology
    • Psychology
    • Applied as the written component in tests like the Red Cross CPR test and various nursing board exams.
    • Often referred to as “objective items”.

Benefits of Multiple-Choice Items

  • Scoring and Analyzing:
    • Easy to score: Automated scoring possible through scanning technologies.
    • Easy to analyze: Rich data sets available for tester feedback.
  • Flexibility:
    • Adaptable in terms of learning outcomes it assesses.
  • Bloom’s Taxonomy:
    • Can be designed to fit any level within Bloom's taxonomy, which categorizes educational goals.

Structure of Multiple-Choice Questions

  • Anatomy of MC Questions:
    • Comprised of three essential parts:
    • Stem: The primary question or statement posed.
    • Correct Alternative: The correct answer choice.
    • Distracters: The incorrect answer choices, or “decoys”.
  • Example Question:
    • The example illustrates a question regarding logical fallacies:
    • “Presenting a very weak form of an opposing argument is one component of…”
      • a. appeals to pity.
      • b. testimonials.
      • c. creating false cause.
      • d. a straw person.
    • (This example is modified from Halpern, 2013.)

Guidelines for Writing Multiple-Choice Items

  • Format: Write alternatives separately, one after the other.
  • Learning Outcomes Alignment: Each question must align clearly with intended learning outcomes.
  • Avoid Negatives: Recommended to steer clear of negatives in the stem or answer alternatives.
    • Not Recommended: “Which of the following statements is not true?”
    • Recommended: “Which of the following statements is false?”
  • Positioning: Vary the position of the correct answer to reduce impact of guessing.

Clarity and Consistency in MC Items

  • Stem Writing: Ensure stems are self-contained, clear, and precise.
  • Example of Poorly Written Question:
    • “New York City is the site of the next Olympics and”
    • A. has a new stadium for track and field.
    • B. is building a new stadium for track and field.
    • C. will be using only the Jets stadium in New Jersey.
    • D. hasn’t yet completed plans for where the stadium event will take place.
  • Grammar and Consistency: Use correct grammar and maintain consistency throughout.

Pitfalls in Writing Multiple-Choice Items

  • Negatives, Absolutes, and Qualifiers:
    • Among potential pitfalls, these should be avoided.
    • Example: “Not only do cicadas come every 17 years, but they never arrive”
    • a. during a rainy season.
    • b. only if the temperature is sufficiently warm.
    • c. whenever the ground is soft enough for them to emerge.
    • d. after June 1.
  • Distractors Quality: Ensure distractors are plausible and independent of one another; they should not give clues to the correct answer in other items.

Advantages of Multiple-Choice Items

  • Positives:
    • Useful for assessing learning at nearly any cognitive level.
    • Clear and straightforward nature minimizes writing demands on test takers.
    • Guessing effects are reduced in comparison particularly to true-false items.
    • Easy to score with reliable results, enabling effective test analysis.

Disadvantages of Multiple-Choice Items

  • Negatives:
    • Guessing can lead to skewed scores.
    • Extensive time required to formulate quality questions.
    • Developing good multiple-choice items is challenging.
    • Limited expression of creativity or unique responses from test takers.
    • Top-performing students may demonstrate more knowledge than what is assessed by the items.

Question Review and Modifications

  • Evaluating the need for question modification involves considering question difficulty and clarity.
  • Example Question: - “The number of questions we can expect students to complete in one hour is”
    • A. 3
    • B. 50
    • C. 125
  • (Modified from Salkind, Tests and Measurement 3e.)

Different Types of Multiple-Choice Items

  • Best-Answer Items: May contain multiple correct answers but only one is considered the best choice.
  • Rearrangement Items: Participants are tasked with arranging a set of items in sequential order.
  • Interpretive Items: Involve presenting a passage followed by questions based on that passage.
  • Substitution Items: Alternates are provided, and test takers select responses they believe correctly answer the question.

Analyzing Multiple-Choice Items

  • Item Analysis: The process of assessing multiple-choice items through a thorough examination of their effectiveness.
  • Components of Item Analysis:
    • Difficulty Index: Measures how many test-takers got an item correct.
    • Discrimination Index: Indicates how effectively items discriminate between those who know the material and those who do not.

Calculation of Item Analysis Metrics

  • High and Low Groups:
    • Create high and low scoring groups from test-taker responses (top 27% and bottom 27%).
    • Examination is conducted per item, not on full test.

Difficulty Index Formula

  • Difficulty Index (D):
    • $D$ = $ rac{h}{T}$
    • Where $h$ = number of correct responses in the high group.
    • $T$ = total responses to the item.
  • Lower percentages indicate higher difficulty and vice versa.

Example Calculation of Difficulty Index

  • Sample Data:
    • Total Responses = 50
    • Correct Responses (High Group) = 22
    • Correct Responses (Low Group) = 14
  • Calculating D:
    • $D = rac{22 + 14}{50} = 0.72$ or 72% (indicating how many got it correct)

Discrimination Index

  • Definition: Measures how effectively an item distinguishes between high and low-scoring groups.
  • Formula:
    • $d = rac{h - l}{T/2}$
    • Where $h$ = correct responses in high group, $l$ = correct responses in low group, $T$ = total number of correct responses.
  • Index Range: Values range from 0.00 (no discrimination) to 1.00 (perfect discrimination). Negative numbers reflect a poorly constructed item.

Characteristics of a Perfect Item

  • Ideal Conditions:
    • Difficulty level $D$ = 50%: Half the test-takers responded correctly.
    • Discrimination level $d$ = 1.00: High group scores correctly while the low group scores incorrectly.

Plotting Difficulty and Discrimination Indexes

  • A graphical representation outlines the relationship between difficulty level and discrimination effectiveness where optimal items appear in the area where D equals 0.50 and d equals 1.00.

Interpreting the Difficulty and Discrimination Results

  • Item 1:
    • D = 25% (difficult), d = 0.50 (positive discrimination).
  • Item 2:
    • D = 75% (easy), d = 0.50 (positive discrimination).
  • Item 3:
    • D = 75%, d = -0.50 (negative discrimination): indicates potential issues with distractors.
  • Examination of Items: Critical analysis of items to establish their efficacy and the need for any revisions.

Analysis of Item Alternatives

  • Quality of Alternatives: Assessment of choices made available in each multiple-choice item is crucial. Effective distractors should differentiate knowledgeable students from those who lack familiarity. No formulas or complex statistics are required for this analysis.
  • Response Patterns: Each item displays response patterns for upper and lower scorers, allowing educators to gauge the effectiveness of each alternative.
  • Example Analysis of Item Responses:
    • Analysis revealing how distractor patterns correlate with test performance for items 4 and 5.