Class Notes (838,568)
Canada (510,954)
Psychology (7,812)
PSYC37H3 (113)
Lecture 5

Lecture 5.docx

6 Pages
Unlock Document

Anthony Ruocco

Lecture 5- Feb 7, 2012 Psychological Assessment- Validity and Test Development *It’s possible that a very simple equations might be on midterm Validity: A Definition  A test is…  There are diff ways we can think of validity (i..e reliability ); just becase something is reliabile doesn’t mean it’s valid  What were to happen if he got off a scale and stepped on a new scale, and it says 300 pounds  The types of decisions we make based on tests should be meaningful, useful, appropriate  You can consider it a unitary value  It’s not as easy as it seems  When you put the tests out there, other people will start using that to measure some things (profs, other students, teachers, etc)  Test validity hinges upon the accumulation of research findings  For ex, transition from the third to the fourth edition of the Wechsler Adult Intelligence Scale (WAIS)  You’re supposed to use the most clearly validated test out there  It’s appropriate to say that I’m going to keep using the WAIS 3 until I see that it’s ok to use WAIS 4 Content Validity  What is the nature of the content in the actual test—is it valid?  Determined by the degree to which the questions, tasks, or items on a test are representative of the universe of behaviour the test was designed to sample  If you’re measuring depression, you should have a test with questions relating to depression, anxiety, and different aspects that revolve around depression or are related to it Achievement Test: Norm-reference test: thousands have been tested Hypothetical Example of Agreement Model of Content Validity for a 100-Item Test  87 items are universally accepted Content Validty Coeffeicint Content validity: Determined by the degree to which the questions, tasks, or items on a test are representative of the universe of behaviorthe test was designed to sample Face Validity  A test has face validity if it looks valid to test users, examiners, and especially examinees  Does a test measure what it’s supposed to look like it’s measuring Criterion-Related Validity  Criterion-related validity is demonstrated when a test is shown to be effective in estimating an examinee’s performance on some outcome measure  Ex. World Health Organization Disability Scale (someone who reports high level disabiality on this measure, they actually show high disability in real life ; others rate them as low-satisfaction in life)  GPA in first year graduate school, could be due to the GRE not being relaibile, or that first year GPA isn’t an indicator to a good criteria  Schedule of recent events: contamination of test (look at powerpoint yellow chart)  Major change in sleeping, eating habits, and social activities -> these are all criteria of depression Types of Criterion-Related Validity  Concurrent validity  Test scores and criterion information are obtained simultaneously  Predictive validity  Test scores are used to estimate outcomes to be measured at a later date  Ex. if I measure impusvility on my test, then I may find that people (undergraduates) later on who go on to commit a violent crime, my test will predict who will go on to commit violence -> basically, one thing I predict now, will happen later on What about the GRE?  Doesn’t really predict much Validity Coefficient and the Standard Error of the Estimate  The relationships between test scores criterion measures  Rxy  Margin of error  Those with a GRE scores of 80 percentile, that the GPA graudatie school might predict at 3.7 and margin of error 3.5 – 3.9  This is why people cannot predict perfectly the whether Decision Theory  One purpose of psychological testing is measurement in the service of decision making  You can make a correct or incorrect deicisons  The more condfident you can mmake about predicting something, then the more likely you are to make a correct decision  Incorrect decision: someone is going to success in something when they actually don’t  False positive (e.g. persons predicted to success actually fail)  False negative (e.g. persons predicted to fail actually success) Examples of ‘False’ Decisions’ One purpose of psychological testing is measurement in the service of decision making False positive (e.g., persons predicted to succeed actually fail) False negative (e.g., persons predicted to fail actually succeed) Quality control: cleaning fluid got into neilson milk  Lime disease: a lot of ticks will reside; you end up noticing one of those cicurcular pattern on your back where the tick might’ve bitten you  Lime disease is associated with psychosis :  Screening tests might result in giving people the wrong information : gold standard for the test is a number of posiitves Construct Validity  Everything is coming together to say this is the thing we
More Less

Related notes for PSYC37H3

Log In


Join OneClass

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

Sign up

Join to view


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.