It’s 2019: Do We Need “Super” Attention Check Items to Conduct Web-Based Survey Research? The Evolution of MTurk Survey Respondents Kateryna Sylaska,

Slides:



Advertisements
Similar presentations
Months of the year December January November October February
Advertisements

Sarah E. Stegall, Darrin L. Rogers, Emanuel Cervantes.
OH 10-1 Managing Voluntary Terminations Human Resources Management and Supervision 10 OH 10-1.
Bringing the crowdsourcing revolution to research in communication disorders Tara McAllister Byun, PhD, CCC-SLP Suzanne M. Adlof, PhD Michelle W. Moore,
Conceptual change. Conceptual reorganization in psychology students beliefs’ about the discipline. Eric Amsel & Adam Johnston Weber State University 10.
Assessment Report Department of Psychology School of Science & Mathematics D. Abwender, Chair J. Witnauer, Assessment Coordinator Spring, 2013.
Thinking Actively in a Social Context T A S C.
13/14 YEAR OLDS: SOCIAL & LANGUAGE Neatness an issue with appearance, not environment Feelings easily hurt Hang out in large groups, but starting to.
Decision-Making: Introduction and Definitions The opening vignette demonstrated some aspects of a typical business decision: The decision is often made.
EMOTIONAL INTELLIGENCE ENGAGING THE AFFECTIVE DOMAIN ENGAGING THE AFFECTIVE DOMAIN FOR EFFECTIVE PEDAGOGY FOR EFFECTIVE PEDAGOGY IN DISTANCE AND DISTRIBUTED.
Year 11 GCSE Information Evening 17 th September 2015.
CHAPTER 2 Research Methods in Industrial/Organizational Psychology
David Ackerman, Associate VP Crystal Butler, Research Associate.
2011 Calendar Important Dates/Events/Homework. SunSatFriThursWedTuesMon January
A COMPARISON OF DIFFERENT METHODS OF DETECTING INATTENTIVE RESPONDENTS Avi Fleischer M.S.
Minnesota Manual of Accommodations for Students with Disabilities Training January 2010.
Measurement Experiment - effect of IV on DV. Independent Variable (2 or more levels) MANIPULATED a) situational - features in the environment b) task.
Getting to Know Webb’s. Webb’s Depth of Knowledge Level One (recall) requires simple recall of such information as fact, definition, term, or simple procedure.
The Reliability of Crowdsourcing: Latent Trait Modeling with Mechanical Turk Matt Baucum, Steven V. Rouse, Cindy Miller-Perrin, Elizabeth Mancuso Pepperdine.
Psychology Unit 1 Vocabulary. Unit 1 - Psychology 1. Applied research 2. Basic research 3. Biological perspective 4. Cognitive perspective 5. Functionalism.
Looking for statistical twins
Discussion and Conclusions
Which One Doesn’t Belong?
Requirements for the Course
SESRI Workshop on Survey-based Experiments
Supporting students’ formal decision-making about biofuels
Chapter 11: The Nuts and Bolts of one-factor experiments.
Fabrizio Fontana and Matteo Martini
Consider This! The Development of a Considerateness Scale
Comparing Bayesian and Frequentist Inference for Decision-Making
The workaholism phenomenon: A cross-national perspective Raphael Snir The Department of Economics and Management The Academic College of Tel Aviv-Yaffo.
Chapter 9: Conducting Experiments
Principles of Quantitative Research
A Comparison of Two Nonprobability Samples with Probability Samples
Logan L. Watts, Ph.D. Baruch College, CUNY
Exploratory Factor Analysis Participants, Procedures, & Measures
Independent School Districts
Chapter 2 Personality Research Methods
Psychometric Benefits of Removing Different Types of Bad Responders
Individual Characteristics
Pilot Study for a Novel Measure Designed to Detect ADHD Simulators
ASSESSMENT OF STUDENT LEARNING
CHAPTER 2 Research Methods in Industrial/Organizational Psychology
General Education Assessment
EXPLORING PSYCHOLOGY Unit 6 – Part 2 Intelligence Ms. Markham.
MANA 4328 Dennis C. Veit Measurement MANA 4328 Dennis C. Veit 1.
Cognitive explanations
ICP 7-th Regional Coordinators Meeting World Bank, Washington D.C.
PHLS 8334 Class 2 (Spring 2017).
Cognitive approach Lesson 6.
SESRI Workshop on Survey-based Experiments
Lesson 5. Lesson 5 Extraneous variables Extraneous variable (EV) is a general term for any variable, other than the IV, that might affect the results.
Myers EXPLORING PSYCHOLOGY (6th Edition in Modules)
MANA 4328 Dennis C. Veit Measurement MANA 4328 Dennis C. Veit 1.
Why Arriving Late to Meetings May Harm Workplace Relationships
Survey Design & Use.
ABAB Design Ethical considerations
อภิปัญญา (Metacognition)
Basics of a Joint Health and Safety Committee
Chapter 3 Organizational Behavior And Management Thinking.
Jeanie Behrend, FAST Coordinator Janine Quisenberry, FAST Assistant
Feasibility of Conducting a Palliative Care Randomized Controlled Trial in Children With Advanced Cancer: Assessment of the PediQUEST Study  Veronica.
Myers’ EXPLORING PSYCHOLOGY (6th Ed)
Module 4 Using Data for Decision Making
Mechanical Turk Lessons: CardLasso
Discussion and Conclusions Brief Report of Studies 3 and 4
The Brief Mood Introspection Scale (BMIS) 30 Years Later: Norms and Validity Evidence from a Meta-Analysis . Rachael M. Cavallaro, Victoria M. Bryan.
Open and Online Experimental Philosophy (X-Phi)
2015 January February March April May June July August September
18. Selection and Training
Presentation transcript:

It’s 2019: Do We Need “Super” Attention Check Items to Conduct Web-Based Survey Research? The Evolution of MTurk Survey Respondents Kateryna Sylaska, Ph.D., Carthage College John D. Mayer, Ph.D., University of New Hampshire Association for Research in Personality June 28, 2019

Why Do We Need Attention Checks? Low control over testing conditions in online-surveys (e.g., Johnson, 2005) Participant distraction and “multi-tasking” (e.g., Chandler et al., 2013) Participant satisficing to reduce cognitive demand (e.g., Oppenheimer et al., 2009) To support the integrity of our research (e.g., Curran, 2015; Mead & Craig, 2012)

Standard Screening Missing > 50% of survey Speedy Completion Longstring Responding Attention Check Items

Attention Check Items For a number of years, very simple attention-check items were sufficient

But now things appear to be changing Attention Check Items But now things appear to be changing

How do we know things are changing?

Evidence from Research with the Test of Personal Intelligence Personal Intelligence (Mayer, 2008; 2014) Ability to reason about ourselves and others based on personality information Recognize personality information Form accurate models of personality Use models to guide choices and make future plans Test of Personal Intelligence (TOPI) Objective, research-based questions

TOPI A person is straightforward and modest. Most likely, she also could be described as: Valuing ideas and beliefs Active and full of energy Sympathetic to others and “tender minded” Self-conscious and more anxious than average Research into traits indicate that people who are straightforward and modest are also likely to be more tender-minded and sympathetic to others rather than hard-headed.

the good old days (2013-2016)

Mturk Sample on the TOPI-MINI-12 Data Collected February, 2013 (reported in Mayer et al, 2018, Study 1) M = 0.25  Expectation if Randomly Responding “Employees high in PI…” (attention checks employed)

College and Mturk Samples on TOPI-MINI-12 Data Collected January-April 2016 (Sylaska & Mayer, 2019) College (N = 299 for MINI) no attention checks Mturk (N = 468 for MINI) attention checks

College Sample of TOPI-MINI-12 Data Collected 2017-2018 (Sylaska, 2019a) (attention checks employed)

Now

Mturk Sample for TOPI-MINI Collected December 2018 (Sylaska & Mayer, 2019b) What’s wrong with this picture? The negative skew has disappeared Nearly half appear to be answering at or near a random level M = 0.25  Expectation if Randomly Responding

Turns out, we weren’t the only ones to notice Major attention to this issue last August

Attempt to Solve the Problem

New Sample Paid for 150 participants Removed 25 for speedy completion

Covert Attention Check Item Original Attention Check Item Covert Attention Check Item

Comparing Original and Embedded Attention Checks

AFTER eliminating participants based on passing 50%+ attention checks Evaluating TOPI Traditional Attentional Checks Covert Attention Checks AFTER eliminating participants based on passing 50%+ attention checks

Cost Consideration Paid for 150 participants Removed 25 for speedy completion Removed 53 for failing traditional and covert attention checks Final N = 72 48% return on investment Likely still keeping some inattentive responders Expected mean for TOPI is closer to .80 (mean for using these criterion is .70)

Other Solutions IP Address Collection GPS Coordinate Tracking Open-Ended Response Comparisons Embedded Activity Tracking (e.g., TaskMaster) Dennis et al., 2019; Kennedy et al., 2019; Permut et al., 2019

References Chandler, J., Mueller, P., & Paolacci, G. (2013). Nonnaïveté among Amazon Mechanical Turk workers: Consequences and solutions for behavioral researchers. Behavior Research Methods, 46, 112–130. doi:10.3758/s13428-013-0365-7 Curran, P. G. (2016). Methods for the detection of carelessly invalid responses in survey data. Journal of Experimental Social Psychology, 66, 4-19. doi:10.1016/j.jesp.2015.07.006 Dennis, S. A., Goodson, B. M., & Pearson, C. (March 14, 2019). Virtual Private Servers and the limitations of IP-based screening procedures: Lessons from the MTurk quality crisis of 2018. doi: 10.2139/ssrn.3233954 Johnson, J. A. (2005). Ascertaining the validity of Web-based personality inventories. Journal of Research in Personality, 39, 103–129. doi: 10.1016/j.jrp.2004.09.009 Kennedy, R., Clifford, S., Burleigh, T., Jewell, R., & Waggoner, P. (October 24, 2018). The shape of and solutions to the MTurk quality crisis. doi: 10.2139/ssrn.3272468 Mayer, J. D. (2008). Personal intelligence. Imagination, Cognition and Personality, 27, 209-232. Mayer, J. D. (2014). Personal intelligence: The power of personality and how it shapes our lives. New York: Farrar, Straus and Giroux. Mayer, J. D., Lortie, B., Panter, A. T., & Caruso, D. R. (2018). Employees high in personal intelligence differ from their colleagues in workplace perceptions and behavior. Journal of Personality Assessment, 100, 539-550. Meade, A. W., & Craig, S. B. (2012). Identifying careless responses in survey data. Psychological Methods, 17, 437-455. doi: 10.1037/a0028085 Oppenheimer, D. M., Meyvis, T., & Davidenko, N. (2009). Instructional manipulation checks: Detecting satisficing to increase statistical power. Journal of Experimental Social Psychology, 45, 867–872. doi: 10.1016/j.jesp.2009.03.009 Permut, S., Fisher, M., & Oppenheimer, D. M. (2019). TaskMaster: A tool for determining when subjects are on task. Advances in Methods and Practices in Psychological Science, 2, 188–196. doi: 10.1177/2515245919838479 Sylaska, K. (2019). [Monmouth College students and choosing a major.] Unpublished raw data. Sylaska, K., & Mayer, J. D. (2019a). Major Decisions: Personal intelligence and reasoning about college major contribute to success. Manuscript submitted for publication. Sylaska, K., & Mayer, J. D. (2019b). [Personal intelligence and choosing a college major.] Unpublished raw data.

Thank you