Confidence-Based Assessment of Two-Alternative Format Tests

Slides:



Advertisements
Similar presentations
Random Variables Lecture chapter 16 part A Expected value Standard deviation.
Advertisements

Computer Aided-Assessment: Can it be accepted? Phil Davies School of Computing.
Personalized Examinations In Large On-Campus Classes Guy Albertelli, Gerd Kortemeyer, Alexander Sakharuk, Edwin Kashy Michigan State University.
The Proper Conclusion to a Significance Test. Luke Wilcox is an “acorn” at the 2013 AP Statistics reading. After three days of scoring, his table leader.
Item Analysis What makes a question good??? Answer options?
Testing HSPA (High School Proficiency Assessment) SAT (Scholastic Aptitude Test) ACT (American College Test) AP Exams (Advanced Placement)
ANALYZING AND USING TEST ITEM DATA
Teaching American History United States Constitution 2008 Student Pre and Post Assessment Results.
CONFIDENCE – ACCURACY RELATIONS IN STUDENT PERFORMANCES We attempted to determine students’ ability to assess comprehension of course material. Students.
AP World History Multiple Choice Exam.
Chapter 8 Measuring Cognitive Knowledge. Cognitive Domain Intellectual abilities ranging from rote memory tasks to the synthesis and evaluation of complex.
Effectiveness of Using Interactive Technology in a Programming Course Shyamal Mitra Department of Computer Sciences University of Texas at Austin.
Average National Arabic Scale Scores for Grade 1 By Gender MalesFemales Grade Level Scale Score 550.
1 Focusing on the FCAT Test-Taking Strategies Grades 3-5 Nancy E. Brito, Department of Assessment , PX47521 Information.
HIGH SCHOOL TEST PREP. TEST PREP CURRICULUM Grade 6 – third trimester review of language and math skills Grade 7 – second trimester diagnostic tests,
DataDirector in the Non-Core Areas Mitch Fowler – School Data Consultant Calhoun ISD.
Mean and Standard Deviation of Grouped Data Make a frequency table Compute the midpoint (x) for each class. Count the number of entries in each class (f).
Standardized Testing (1) EDU 330: Educational Psychology Daniel Moos.
Classroom Evaluation & Grading Chapter 15. Intelligence and Achievement Intelligence and achievement are not the same Intelligence and achievement are.
Research Problem In one sentence, describe the problem that is the focus of your classroom research project about student learning: Biology undergraduates.
Work the Following on Your Own Paper… Luis mixed 6 ounces of cherry syrup with 53 ounces of water to make a cherry-flavored drink, Martin mixed 5 ounces.
Mean Absolute Deviation
Heriot Watt University Breakout Session MCQ with Confidence Dr Phil Davies Division of Computing & Mathematical Sciences Department of Computing FAT University.
1 Focusing on the FCAT Test-Taking Strategies Grades 6-8 Nancy E. Brito, Department of Assessment , PX47521
1 Focusing on the FCAT Test-Taking Strategies Grades 9-11 Nancy E. Brito, Department of Assessment , PX47521
Strategies for answering multiple choice questions Don’t be chicken to answer!
 SAT Reasoning test: ◦ Tests your skills as a test-taker ◦ Reason & logic-based  ACT: ◦ More academic and straightforward ◦ Curriculum-based (what you.
Which list of numbers is ordered from least to greatest? 10 –3, , 1, 10, , 1, 10, 10 2, 10 – , 10 –3, 1, 10, , 10 –3,
Online Assessment Using Carmen Quizzes. Online Quizzing in Action Bob Burnkrant –Low-stakes, frequent quizzing help students be prepared for lectures.
E-Assessment: Removing the Boundaries of C.A.A. Phil Davies School of Computing University of Glamorgan South Wales UK.
3 STUDENT ASSESSMENT DEPARTMENT
Eyes on a 5: Conquering the APES Exam. The APES Exam May 2, morning session Selected Response Section questions - 90 minutes - 60% of exam.
ACT Prep: Lesson 3 Get out a piece of paper and put your name on it!
Department of Physics and Goal 2 Committee Chair
Using Data to Drive Decision Making:
INDOOR SCORING Vertical 3 Spot - Individual
The SAT vs. ACT Scholastic Aptitude Test American College Testing
Multiplication Strategies
Multiplication table. x
KEYSTONE EXAM TIPS & TRICKS.
How to show what you know!
AP MC Pre-assessment Reflections and goals.
SATs Information Evening
CCMH 535 Possible Is Everything/tutorialrank.com.
CCMH 535 Possible Is Everything/tutorialrank.com.
Partial Credit Scoring for Technology Enhanced Items
End of Year Calculus Assignments Name:______________________________
AP Psychology Exam Tips
A few more tips for APCSA
Advanced Placement English Language and Composition
Test Development Test conceptualization Test construction Test tryout
Math Milestones Information Constructed Response
IB HL Biology Year 1 Maura Palillo.
EXAM SUMMARY Exam format:
IXL.
Testing Updates February 19, 2013
Strategies for Test Success
SAT Math Overview.
Histograms of grades in two classes, each of 200 students
Notes Over 11.2 Number Compared to Base is Unknown
Mari Quenemoen Research Coordinator, NAAC
Rubrics for academic assessment
This file contains class distributions for all quizzes and exams, starting with quiz 1. Two graphs will be posted for each quiz/exam. The first graph.
Eighth Grade Science Mrs.Nelson.
PSSA: Test Taking Strats
Common Exams: Fall Data Update
CS150 Introduction to Computer Science 1
INDOOR SCORING.
Expected Value (MAT 142) Expected Value.
MULTIPLE SCORING ZONES
Presentation transcript:

Confidence-Based Assessment of Two-Alternative Format Tests AHMED A. BELAL (1) & DIALA F.AMMAR (2) (1)Computer Engineering and Informatics- Beirut Arab University, Lebanon (2)Psychology department, Lebanese American University, Lebanon abelal@bau.edu.lb

Computer Aided Assessment Multiple Choice Exams : No Partial Credit Penalty for Wrong Answers

Designing good distracters Multiple Select Exams Penalty for Wrong Answers Multiple T/F Exams Question may have no correct answers No partial credit Individual T/F questions Weak resistance to guessing

Correct =+ X No Answer = 0 Wrong Answer= -Y Poor discrimination Confidence-based Assessment

Uncertainty improves Discrimination The Element Of Uncertainty improves Discrimination Three Questions +10 Correct 1 2 3 Grade 10 20 30 Correct 1 2 3 Grade -15 15 30 Scaled 45 +10 -5 Correct 1 2 3 Grade -30 -10 10 30 Scaled 20 40 60 +10 -10

Adding an element of uncertainty Correct +10 Wrong -5 No answer Correct 1 2 3 Wrong No answer 9 Different Grades Grade -15 15 30 -10 5 20 10 -5 Scaled 45 35 25 Correct +10 Wrong -10 No answer Grade -30 -10 10 30 -20 20 Scaled 40 60 50 7 Different Grades

Incorporating uncertainty in the test Confidence Level Correct Answer Wrong Answer 1 +3 -1 2 +4 -2 3 +5 -5 Leclereq [1,2] Hard to correctly estimate one’s confidence level Humans are more oriented to judge their uncertainty in things relative to each other

Relative Uncertainty Student ranks questions relative to each other. Value of correct answer decreases as level of confidence decreases. Wrong answers change the confidence level. Use a step size and a reduction function to assign values for a correct answer.

Relative Uncertainty : An Example Answer Vector 000 001 010 011 100 101 110 111 R=5 5 10 15 20 30 R=10 -10/0 R=15 -20/0 -5/0 S=1

Relative Uncertainty (Cont) Confidence Level C1 C2 C3 C4 C5 Reduction Value 2 10 8 6 4 2 Reduction Value 5 5 -5 -10 10 Questions : answer vector 1101001100 Step size = 1 R =2 Score = 10+10+0+8+0+0+4+4+0+0 = 36 R = 5 Score = 10+10+5 -5-5 = 15 Step size = 2 R =2 Score = 10+10+10+8+8 = 46 R = 5 score = 10+10+10+5+5 = 40

Answering Form

Absolute (10-2p) (10-p) (10-5p) R=1;s=2 R=2;S=2 Answer Vector 16 24 32 10 37 34 1001011000 38 44 47 35 50 1101110000 25 40 15 56 52 1010111010 30 0110101100 62 64 72 76 1111001111 80 90 1111111110 66 73 45 1011111110 42 46 1011110000 18 36 20 39 1011010000 51 0111111110 60 1110011011 86 78 84 1110111111 65 1100101111 1101100000 58 67 55 70 1111011100 49 1110111100 1011111100 22 5 0100111010 41 0111110000 0101101000 27 0011100000 1 26 29 28 0110100000 1011001000 4 1110001000 0101110100 54 68 1111100110 61 1110011101 Table 1

Strategy Average Standard Deviation Absolute 37.46428571 22.57084672 10-2P 45.28571429 18.21854396 10-P 51.75 17.3901313 10-5P 29.46429 20.19989 R=1 S=2 56.14286 17.98912 R=2 S=2 54.42857 18.44597 Table 2

Thank you