EERA Workshop on Q methodology Q factor analysis

EERA Workshop on Q methodology & Q factor analysis Sue Ramlo Joe Jurczyk Al Herbert Isadore Newman

Workshop Outline n Introduction to Q methodology q q q n Q factor analysis q q q n Sorting items onto a normal Gaussian distribution Concourse of items & the Q sample Analyzing the sorts using PQ Method – factors & interpretation How is Q FA different from Q method? Using QUANAL to find topologies in Q FA Using PQ Method for Q FA Why groups of people?

Introduction to Q methodology Overview n Allows a researcher to investigate the views, or perspectives, of a person or a group of people. n The process involves sorting items (typically statements) into a normal Gaussian distribution. n Analysis involves factor analysis that groups people, not items. FA – grouping based on correlation among the participants’ sorts.

Sorting items onto a normal Gaussian distribution n Pre-sort into 3 piles LEAST like my view (~14 statements here) n Neutral view about this statement MOST like my view (~14 statements here) Distribute (& redistribute) to fit specific normal Gaussian distribution. (usually most disagree to most agree)

Now you try it! n Condition of instruction - “Because you’ve been working so hard, you have been ordered by your boss/department chairperson to take a 5 -day vacation by yourself or with your family, all expenses paid. Rate the following items on a scale of “most enjoyable” (+5) to “most unenjoyable” (-5)…. ” Most unenjoyable (~7 items) Neutral view about this statement (~7 items) n Pre-sort into 3 piles n Distribute (& re-distribute) to fit specific normal Gaussian distribution. (usually most disagree to most agree) MOST enjoyable (~7 items)

Introduction to Q methodology – historical background n Developed in 1935 by William Stephenson q Physicist-psychologist q Student of Spearman q A Study of Behavior, 1955 n Q because of its philosophical similarity to the physics field of Quantum Mechanics n Most often used in fields of psychology, marketing, advertising, political science… n Mixes quantitative & qualitative aspects of research

Why not another method to determine views? n Alternatives for determining perspectives are not as powerful as Q. n Likert scale evaluations and rank ordering lead to the loss of meaning (Mc. Keown, 2001). n Because Q measures personal opinion regarding a concourse of items related to a topic, validity is not a consideration (Brown, 1999).

What is meant by subjectivity? n n What do you see? Bunny? Duck? Is one right & the other wrong or are they both just different views?

Any Q study starts with a concourse: n Can consist of words / statements, pictures, sounds, smells… n Subjective q q Not “It’s raining” But can be “the rain makes me feel sad” –or- “I love to walk in the rain. ” n Items are interpreted by participant – removes the view of the researcher & the issue of validity / reliability. n Select the Q sample from the concourse n Try to “balance” the Q sample

Concourse of items – 3 possibilities “Naturalistic” statements - taken from participants’ oral or written n communications. n q Interviews q Focus Groups “Ready made” statements - from sources other than those of the participants’ communications. q Likert survey items q Based on knowledge of researcher w/o interviews n Hybrid - combine both “naturalistic” and “ready made” items. n One is not inherently superior to the other (Mc. Keown & Thomas, 1988). n Researcher selects the type best suited to the project at hand

Q sample – select items from the concourse to use in the study. n Example: Selection from a Q sample of 44 (chosen from a concourse of 53) 1 What I learn from textbook depends on how I use it to study in this class. 23 I can tell when I understand the material in this class. 2 I need to learn how to study more effectively to succeed in this class. 24 I feel comfortable applying what I learned in this class to the real-world. 3 Working hard on difficult problems does not help me learn in this class. 25 Doing homework helps me learn in this class. 4 I don't have to work hard to learn in this class. 26 Reading the textbook helps me learn in this class. 5 I need to learn how to learn in this class. 27 I like the exactness of math-type subjects. 6 I have very little control over how much I learn in this course. 28 I often think about how well I understand the topics in this class. 7 In this class, if I can't understand something right away, I will keep on trying 29 What I learn in this class will help me in other classes. 8 Working with classmates inside &/or outside this class helps me learn. 30 What I learn in this class will help me when I get a job in my field.

Condition of instruction n Participants sort based upon a condition of instruction (or multiple conditions). q n E. g. Sort the following statements as they relate to your views about learning in this class. The statements are matters of subjective opinion and may mean different things to different people. q e. g. I worked hard in this class.

Analyzing Q sorts n SPSS & SAS not really designed for Q sorts – you mess with weightings, etc. n Need software designed for Q methodology q q q QUANAL PCQ PQMethod

Factor Analysis n Higher order correlation n Used to determine patterns in a data set n R-factor analysis groups items (people are rows, items are in columns). Factors represent similar items. n Q-factor analysis groups people (people are in columns, items are in rows). The factors represent people with similar topologies. n Q methodology is not Q FA but does group people based upon their VIEWS on a subject. Factors represent similar views about a topic.

PQ Method to determine factors & assist in their interpretation n PQMethod q q q n Choices q q n Free download (start at www. qmethod. org) DOS based Designed for handling Q sort entry and analyses Centroid versus Principle Components factor extraction Graphical hand rotation versus Varimax Start PQMethod

PQMethod Analyses n Creates print out with: q q q Factor loadings Factor correlations Distinguishing statements Consensus statements, etc Example - knowledge Tech Physics sorts Ramlo 2006. lis.

Q factor analysis n How is Q FA different from Q method? n Using QUANAL to find topologies in Q FA

QFA run in PQMethod n Create z-scores for each item (if the items all have the same scale, skip this step). n Rank order items for each person (lowest to highest) and then give a grid score (e. g 1 to 6, -2 to 2, etc). Note that PQ Method allows for a scale up to 13 places. n Unlike Q sorts, QFA does not lend itself to a grid that has any columns deeper than one layer. This is important because we are analyzing the topologies of the items. n The *. lis file contains similar outputs to that of QUANAL including distinguishing items for pairs of factors, consensus items, etc.

Why groups of people? q q If groups are known a priori, use discriminative analyses If groups are unknown, need Q FA to determine groups without sorts; Q method with sorts