Chapter 5: Identifying Good Measurement Flashcards
Conceptual Variable
(construct or theoretical level)
- Know what it is but It is not enough to study the variable
- Is the researcher’s definition of the variable in question at a theoretical level
Operational Variable
(how its measured or manipulated)
- Represents a researcher’s specific decision about how to measure or manipulate the conceptual variable
Self Report Measure
- Which you asking participants how they feel, how often they do things; etc
- Get information by asking questions
- A variable by recording people’s answers to questions about themselves in a questionnaire or interview
Example: if stress is the variable being studied, researchers might ask people to self - report on the frequency of specific events they’ve experienced in the past year, such as marriage, divorce or moving
Observational/Behavioral Measure
- Operationalize by observing
- Sometimes called a behavioral measure, operationalize a variable by recording observable behavior or physical traces of behaviors
- Observational measures may record physical traces of behaviors
Example: A researcher could operationalize happiness by observing how many times a person smiles
Psychological Measure
- Rely on the biological measure
- Operationalize a variable by recording biological data, such as brain, activity, hormone levels or heart rate
- Usually requires the use of equipment to amplify, record and analyze biological data
Example: Moment to moment happiness has been measured using EMG - a way of electronically recording tiny movements in the muscles in the face
- Can be used to detect a happy facial expression because people who are are smiling show particular patterns of muscles movement around the eyes and cheeks
Categorical Variables
(nominal variables) (e.g., race)
- Levels of categories, by using different scales
- Can divide scales in categorical
Example: Nationality
Example: Type of music
Example: Kind of phone people use
Example: sex, whose levels are male and female, and species, whose levels in study might be rhesus macaque, chimpanzees and bonobos
Quantitative Variables
- Levels of coded with meaningful numbers
- Also called continuous variables
- Are coded with meaningful n
Example: height and weight
Types of Quantitative Variable
Ordinal Scale
- A quantitative variable in which numerals represent a rank order
- It is a distance between subsequent numerals may not be equal
Example: Order of finishers in a swimming race.
Example: Ranking of 10 movies from most to least favorite
Types of Quantitative Variable
Interval Scale
- A quantitative variable in which subsequent numbers represent equal distances, but there is no true zero
Example: IQ score
Example: Shoe size
Example: Degree of agreement on a 1-7 scale
Types of Quantitative Variable
Ratio Scale
- A quantitative variable in which numerals represent equal distances and zero represents “none” of the variable being measured
- Equal interval and has a true zero (has a meaning)
Example: # of exam questions answered correctly
Example: # of seconds to respond to a computer task
Example: Height in cm
Reliabity of Measurement
Is how consistent the results of a measure are
Types of Reliability
Test - Retest Reliability
- Agree to which a scores is remain unchanged change over time
- The consistency in results every time a measure is used
Example: if the CTAS is also reliable, it will produce the same results each it is used
- Have to assess the same set of participants on that measure at least twice
- A low r would be a sign of poor reliability of we are measuring something should stay the same over time
Types of Reliability
Interrator Reliability
- The degrees to which two or more coder or observers give consistent ratings of a set of targets
- Consistent scores are obtained no matter who measures the variable
- Refers to the degree of agreement between among multiple raters or evaluators when assessing the same thing
Example: medical diagnosis
- When different doctors independently diagnose a patient with the same symptoms, it suggest high IRR
Example: Grading Essays
- If multiple teachers give similar grades to an essay using a rubric, it demonstrated high inter - rater reliability in their grading criteria
Example: if two researchers observed behaviors and categories aggression scores in children they should both record the same score
- If r is positive and strong, we would have a very good interrater reliability
- If r is positive but weak, we could not trust the observers ratings
A negative r would indicate a big problem
Types of Reliability
Internal Reliability
- In measures that contains several items, the consistency in a patterns of answers, no matter how a questions is phrased
- Also called internal consistency
- Applies up measures that combine multiple items
- Different parents of the test should give consistent results
Example: if a an IQ test constians section of supposed equal difficulty, participants should achieve similar scores on all sections
Example: A sample of people take Diener’s five item subjective well being scale. The questions on his scale are worded differently, but each item is intended to measure the same construct
- Therefore people who agree with the first item on the scale should also agree with the second item
- Similarly, people who disagree with the first item should also disagree with items 2, 3, 4, and 5
- If the pattern is consistent across items in this way, the scale has internal reliability
Correlation Coefficient
Indicated how close the dots or points on a scatter plot are to a line drawn through them
