Class Notes (836,126)
Canada (509,644)
Brock University (12,091)
Psychology (853)
PSYC 2P25 (29)
Lecture 2

lecture 2.docx

5 Pages
96 Views
Unlock Document

Department
Psychology
Course
PSYC 2P25
Professor
Michael Ashton
Semester
Fall

Description
PSYC 2P25 Sept. 17, 2012 Assessing Quality of Measurement Reliability  A measurement is reliable if it agrees with other measurements of the same variable  3 kinds of reliability o Internal consistency reliability  When scores on a measurement are calculated as a sum (or mean) of various parts (“items”)  Scores should depend strongly on the common element of the items  Indicates the extent to which scores represent the common element of the items  How to make measurements have higher internal-consistency reliability:  Include lots of items – adding many items together gives better measurement of their common characteristic o Any single item has its own specific element but when we combine items, these specific parts get cancelled out  Include “items” that are correlated with each other – items that correlate strongly with each other are measuring a common characteristic o If items are uncorrelated with each other, they don’t have a common characteristic – might be measuring several different characteristics instead o Interrater reliability  When a characteristic is measured by obtaining ratings made by several persons  Scores on the total (or average rating should depend strongly on the raters’ common judgement  Indicates the extent to which overall scores represent the common element of the scores given by the various raters  How to get high interrater reliability:  Have many raters (so that one rater’s idiosyncrasies get cancelled out)  Have only raters whose ratings tend to agree (so that there is a strong common element to their ratings) o Stability (Test-Retest Reliability)  If variable is supposed to be a lasting characteristic, then measurements taken on two occasions (e.g. a few weeks apart) should be highly correlated  Test-retest reliability is usually calculated simply as the correlation between scores on two occasions Validity  Means evidence that measurement assess the intended characteristic PSYC 2P25 Sept. 17, 2012  3 kinds of validity: o Content validity  Together, items should assess all aspects of characteristic and not any irrelevant characteristics o Criterion validity  Measurement should correlate in appropriate ways with external :criterion” variables  Convergent validity – expect high r with relevant criteria (positive for similar, negative for opposite)  Discriminant validity – expect low r with irrelevant criteria  Exs. Think of “convergent” and “discriminant” criteria for scores on a job interview o Construct validity  Subsumes content validity and both aspects of criterion validity (convergent and discriminant) Evaluating Reliability and Validity  Use a sample that is representative of the intended population, and ideally a large sample too  Reliability shouldn’t be too low, if it is, then validity can’t be high  “good” level of convergent validity depends on the criterion variable – expect stronger positive r’s for the theoretically more similar variables (and stronger negative r’s for theoretically more opposite variables) Personality Traits  People differ in tendencies to behave in conceptually related ways across situations and over fairly long time Situationism  1960s & 70s: some researchers denied existence of personality traits (ex. Mischel, 1968)  Said that people didn’t differ consistently in behaviour tendencies. Instead, situation determines which people will show more or less of the behaviour Empirical Studies: Do Traits Exist?  If a personality trait exists, then people should differ consistently in overall (trait-relevant) behaviour as averaged across many situations Hartshorne & May (1928)  Studied trait of dishonesty in children; observed several behaviours  Found low rs between dishonest behaviours in any two situations, but dishonest behaviour is averaged across several situations PSYC 2P25 Sept. 17, 2012  There is high r with dishonesty averaged across several other situations (Epstein, 1979)  So trait does exist: across many situations, overall level of dishonesty emerges Mischel & Peake (1982)  Studied trait of organization in university students; observed several behaviours  Found low rs between organized behaviours in any two situations, but when organized behaviour is averaged across many situations there is hi
More Less

Related notes for PSYC 2P25

Log In


OR

Join OneClass

Access over 10 million pages of study
documents for 1.3 million courses.

Sign up

Join to view


OR

By registering, I agree to the Terms and Privacy Policies
Already have an account?
Just a few more details

So we can recommend you notes for your school.

Reset Password

Please enter below the email address you registered with and we will send you a link to reset your password.

Add your courses

Get notes from the top students in your class.


Submit