Lab 5: Item Analyses. Quick Notes Load the files for Lab 5 from course website –

Slides:



Advertisements
Similar presentations
Assessing Student Performance
Advertisements

Item Analysis.
Test Development.
FACULTY DEVELOPMENT PROFESSIONAL SERIES OFFICE OF MEDICAL EDUCATION TULANE UNIVERSITY SCHOOL OF MEDICINE Using Statistics to Evaluate Multiple Choice.
Rebecca Sleeper July  Statistical  Analysis of test taker performance on specific exam items  Qualitative  Evaluation of adherence to optimal.
© McGraw-Hill Higher Education. All rights reserved. Chapter 3 Reliability and Objectivity.
Using Test Item Analysis to Improve Students’ Assessment
Item Analysis: A Crash Course Lou Ann Cooper, PhD Master Educator Fellowship Program January 10, 2008.
Dr. Majed Wadi MBChB, MSc Med Edu
Test Construction Processes 1- Determining the function and the form 2- Planning( Content: table of specification) 3- Preparing( Knowledge and experience)
Item Analysis What makes a question good??? Answer options?
Statistics for Decision Making Descriptive Statistics QM Fall 2003 Instructor: John Seydel, Ph.D.
Lesson Seven Item Analysis. Contents Item Analysis Item Analysis Item difficulty (item facility) Item difficulty (item facility) Item difficulty Item.
Item Analysis Prof. Trevor Gibbs. Item Analysis After you have set your assessment: How can you be sure that the test items are appropriate?—Not too easy.
Chapter 1 The mean, the number of observations, the variance and the standard deviation.
Lesson Nine Item Analysis.
Multiple Choice Test Item Analysis Facilitator: Sophia Scott.
ANALYZING AND USING TEST ITEM DATA
Measurement Concepts & Interpretation. Scores on tests can be interpreted: By comparing a client to a peer in the norm group to determine how different.
Measures of Central Tendency
Week 11 Chapter 12 – Association between variables measured at the nominal level.
Assessment Report Department of Psychology School of Science & Mathematics D. Abwender, Chair J. Witnauer, Assessment Coordinator Spring, 2013.
ASSESSMENT FOR BETTER LEARNING USING NAPLAN DATA Presented by Philip Holmes-Smith School Research Evaluation and Measurement Services.
WEEK 2 ( SEPTEMBER 2013) Unit 1 Data and Technology.
Part #3 © 2014 Rollant Concepts, Inc.2 Assembling a Test #
Unanswered Questions in Typical Literature Review 1. Thoroughness – How thorough was the literature search? – Did it include a computer search and a hand.
Field Test Analysis Report: SAS Macro and Item/Distractor/DIF Analyses
The Genetics Concept Assessment: a new concept inventory for genetics Michelle K. Smith, William B. Wood, and Jennifer K. Knight Science Education Initiative.
Introduction to Statistics for the Social Sciences SBS200, COMM200, GEOG200, PA200, POL200, or SOC200 Lecture Section 001, Spring 2015 Room 150 Harvill.
CHAPTER 6, INDEXES, SCALES, AND TYPOLOGIES
Chapter 7 Item Analysis In constructing a new test (or shortening or lengthening an existing one), the final set of items is usually identified through.
 Closing the loop: Providing test developers with performance level descriptors so standard setters can do their job Amanda A. Wolkowitz Alpine Testing.
Techniques to improve test items and instruction
1 PUAF 610 TA Session 2. 2 Today Class Review- summary statistics STATA Introduction Reminder: HW this week.
Algorithms and their Applications CS2004 ( ) Dr Stephen Swift 3.1 Mathematical Foundation.
NRTs and CRTs Group members: Camila, Ariel, Annie, William.
VARIABILITY. Case no.AgeHeightM/F 12368M 22264F 32369F 42571M 52764F 62272M 72465F 82366M 92366F F M F M F F F.
UTOPPS—Fall 2004 Teaching Statistics in Psychology.
1 Lesson Mean and Range. 2 Lesson Mean and Range California Standard: Statistics, Data Analysis, and Probability 1.1 Compute the range, mean,
Descriptive Statistics Prepared by: Asma Qassim Al-jawarneh Ati Sardarinejad Reem Suliman Dr. Dr. Balakrishnan Muniandy PTPM-USM.
Grading and Analysis Report For Clinical Portfolio 1.
1 Item Analysis - Outline 1. Types of test items A. Selected response items B. Constructed response items 2. Parts of test items 3. Guidelines for writing.
Lab 9: Two Group Comparisons. Today’s Activities - Evaluating and interpreting differences across groups – Effect sizes Gender differences examples Class.
Experimental Research Methods in Language Learning Chapter 5 Validity in Experimental Research.
Preparing for the OCR Functional Skills Maths Assessment
The Practice of Social Research Chapter 6 – Indexes, Scales, and Typologies.
Unit 5 Seminar D ESCRIBING Y OUR L EARNING. Agenda Unit Objectives Bloom’s Taxonomy Learning Statements Questions.
Discovering Mathematics Week 5 BOOK A - Unit 4: Statistical Summaries 1.
Introduction to Item Analysis Objectives: To begin to understand how to identify items that should be improved or eliminated.
Brian Lukoff Stanford University October 13, 2006.
LECTURE 02: EVALUATING MODELS January 27, 2016 SDS 293 Machine Learning.
Dan Thompson Oklahoma State University Center for Health Science Evaluating Assessments: Utilizing ExamSoft’s item-analysis to better understand student.
Psychometrics: Exam Analysis David Hope
Dept. of Community Medicine, PDU Government Medical College,
Norm Referenced Your score can be compared with others 75 th Percentile Normed.
Items analysis Introduction Items can adopt different formats and assess cognitive variables (skills, performance, etc.) where there are right and.
Bivariate Association. Introduction This chapter is about measures of association This chapter is about measures of association These are designed to.
Using Data to Drive Decision Making:
CORRELATION.
ARDHIAN SUSENO CHOIRUL RISA PRADANA P.
Teaching Statistics in Psychology
Data Analysis and Standard Setting
Classroom Analytics.
Validity and Reliability
Classroom Assessment Ways to improve tests.
Dept. of Community Medicine, PDU Government Medical College,
Using statistics to evaluate your test Gerard Seinhorst
Lies, Damned Lies & Statistical Analysis for Language Testing
Analyzing test data using Excel Gerard Seinhorst
Tests are given for 4 primary reasons.
Presentation transcript:

Lab 5: Item Analyses

Quick Notes Load the files for Lab 5 from course website – Lab 5.ppt Item.proj.xls

Item Analyses – Introduction We perform item analyses to evaluate individual items. The basic idea is to compute a series of specific descriptive statistics for each item and then evaluate those statistics.

When Can You Do Item Analyses? When responses to items are scored as correct or incorrect. Achievement tests Exams Written driving tests NOT on most attitude or personality measures. Why?

Key Aspects of an Item Analysis Item Difficulty Item Discrimination – 2 Indices

Item Difficulty 1 Item responses are recoded: – Wrong answers are coded as 0 – Right answers are coded as 1 The mean of each recoded item is the percentage of people who got the item correct. It ranges from 0 (no one got the item right) to 1 (everybody got it right).

Example Imagine that you ask 100 people a question. 56 people give the right answer and 44 people give the wrong answer. What is the item mean?

Item Difficulty 2 Traditional method of calculating item difficulty: p p = proportion of people who got the answer correct on an item. – Ranges from 0.00 to 1.00 – The higher the value, the easier the item (i.e., more people got it correct) p =.77 means that 77% of individuals got the item right

An Easy Item What is the name of the daughter of Tom Cruise and Katie Holmes? a) Samantha b) Suri c) Apple d) Sunshine e) Nicole

An Easy Item What is the name of the daughter of Tom Cruise and Katie Holmes? a) Samantha b) Suri c) Apple d) Sunshine e) Nicole Item difficulty is: p =.91

A Difficult Item What TV show won the 2006 Emmy for the best dramatic series? a) Prison Break b) 24 c) The Sopranos d) Lost e) CSI Las Vegas

A Difficult Item What TV show won the 2006 Emmy for the best dramatic series? a) Prison Break b) 24 c) The Sopranos d) Lost e) CSI Las Vegas Item difficulty is: p =.42

Summary: Item Difficulty When few people get an item correct, the item is difficult and p is low. When a lot of people get an item correct, the item is easy and p is high. In general test construction, you want items to range in difficulty. Average item difficulty on the test equals the mean test score. – If you want the mean of your test to be 75%, average of item difficulties should be 75%.

Item Difficulty Analysis for Exam 1 Look at the item analysis file for the exam. Where can you find the item difficulty for each item? Which item is the easiest? Which is the most difficult? What is the average item difficulty?

Item Discrimination An index of how well an item differentiates between people who did well on the test (and presumably knew the material) and those who did not do well (and presumably did not know the material). 2 Methods: – Method 1: Take p for upper range of people (e.g., top 25%) and subtract p for lower range of people (e.g., bottom 25%) on an item – Method 2: item-total correlation correlate item score and test score

Item Discrimination Item discrimination values should always be positive. The higher the value, the better the item predicts how well people did on the test.

Item Discrimination for Exam 1 Look at the Exam 1 item analysis. Where can you find the item discrimination for each item? Which item discriminates best? Which worst?

Relation between Item Difficulty and Item Discrimination I Consider a very easy item, e.g. item 44 What percentage of the upper 25% of people on the test got it right? What percentage of the lower 25%?  This item does not discriminate well between those who did well on the test and those who did not. This is called a ceiling effect.

Relation between Item Difficulty and Item Discrimination Consider a moderately difficult item, e.g., item 15 What percentage of the upper 25% of people on the test got it right? What percentage of the lower 25%? Items with moderate difficulty tend to have higher discrimination. If a person can get an item right or wrong, I can make a judgment about whether the person has high or low ability relative to others.

Homework I l Report and interpret the item difficulty for items 1 – 5. (2 points) l Which item in the first exam is the most difficult? Which is the easiest? (1 point) l Report and interpret both types of item discrimination for items 1 – 5. (2 points) l Which item has the highest discrimination? Which has the lowest? (1 point) 

Homework II 5. Imagine the scoring office gives you these statistics for four different items. For each item, report whether – you would keep the item on the test or – revise the item in future versions of the test and explain your decisions! (4 points) Item 1: p = 0.95; discrimination index = 0 Item 2: p = 0.1; discrimination index = 0.40 Item 3 p = 0.1; discrimination index = 0 Item 4 p = 0.5; discrimination index = 0.60

Your Paper

Picking a Topic for Your Paper The most important first step is finding a topic in psychology that interests you. You can choose a topic from any area of psychology (e.g. biological, cognitive, clinical, community, developmental, educational, personality, social). The question must be one that can be addressed with empirical research. You must have at least 2 variables of interest (e.g., 1 dependent and 1 independent variable) Write down 3 possible research topics and indicate why you are interested in these questions. You will discuss these in lab next week.