psychometrics 101: foundational knowledge for testing professionals steve saladin, ph.d. university...

28
Psychometrics 101: Foundational Knowledge for Testing Professionals Steve Saladin, Ph.D. University of Idaho

Upload: dangelo-ake

Post on 29-Mar-2015

214 views

Category:

Documents


1 download

TRANSCRIPT

Page 1: Psychometrics 101: Foundational Knowledge for Testing Professionals Steve Saladin, Ph.D. University of Idaho

Psychometrics 101: Foundational Knowledge for Testing Professionals

Steve Saladin, Ph.D.

University of Idaho

Page 2: Psychometrics 101: Foundational Knowledge for Testing Professionals Steve Saladin, Ph.D. University of Idaho

Criterion-referenced vs norm-referenced• Is performance rated on some pre-established cut

points or is it based on comparisons with othersClass room grading is generally criterion based

• 90% right=A, 80%=B, 70%=C, etc.• Typically reported as a percentage correct or P/F

Grading on the curve means grade based on comparison with rest of class (norm-referenced) • 80% might be a B, an A, a C or something else.

Page 3: Psychometrics 101: Foundational Knowledge for Testing Professionals Steve Saladin, Ph.D. University of Idaho

• Standardized tests are typically norm-referencedSAT, ACT, GRE, IQ testTypically reported as percentile or standard score

• Certification exams are often criterion-referencedProctor certification, licensing examsTypically reported as percentage correct or P/F

• Sometimes you get a mixGED uses norms to establish cut-scores

• Important to note difference between percentile and percentage correct

Criterion-referenced vs norm-referenced

Page 4: Psychometrics 101: Foundational Knowledge for Testing Professionals Steve Saladin, Ph.D. University of Idaho

Damn the Statistics & full speed ahead!

• Testing is all about quantifying something about people (skills, knowledge, behavior, etc.)

• Stats are just a way to describe the numbers Make it more understandable Reveal relationships

• To understand norm-referenced test scores, you need to know two general things What is the typical score? To what degree did others score differently?

Page 5: Psychometrics 101: Foundational Knowledge for Testing Professionals Steve Saladin, Ph.D. University of Idaho

What’s typical?

• Mean

• Median

• Mode

How different are the scores?• Range = highest – lowest = 40

• Variance = average of squared differences from mean = 163.6

• Standard Deviation = square root of Variance = 12.8

10 10 20 20 30 30 40 40 40 40 50

= arithmetic average = 30

= # in the middle = 30

= most frequently occurring # = 40

Page 6: Psychometrics 101: Foundational Knowledge for Testing Professionals Steve Saladin, Ph.D. University of Idaho

Standard Normal Distribution

• Normal Curve

• Assumes trait is normally distributed in population

Mean

Standard deviation

Page 7: Psychometrics 101: Foundational Knowledge for Testing Professionals Steve Saladin, Ph.D. University of Idaho

The Normal Curve

%tile <1% 2.5% 16% 50% 84% 97.5% 99.5%GRE 200 300 400 500 600 700 800SAT 200 300 400 500 600 700 800IQ 55 70 85 100 115 130 145ACT 1 6 12 18 24 30 36

Page 8: Psychometrics 101: Foundational Knowledge for Testing Professionals Steve Saladin, Ph.D. University of Idaho

How are these things related?

GRE scores and Grad School grades CLEP scores and final exam scores Compass/Accuplacer scores and success in

entry classes Motivation and cheating

• Correlation tells us if things vary or change in a related way Higher GRE scores means higher grades Lower motivation suggests higher levels of

cheating

Page 9: Psychometrics 101: Foundational Knowledge for Testing Professionals Steve Saladin, Ph.D. University of Idaho

Some Facts About Correlation• Ranges from +1.0 to -1.0

• Sign tells you direction of correlation + as A gets bigger so does B - as A gets bigger, B gets smaller

Page 10: Psychometrics 101: Foundational Knowledge for Testing Professionals Steve Saladin, Ph.D. University of Idaho

How To Lie With Statistics!

• Test Taking linked to Longevity! A recent study found that people who had taken more tests during early adulthood tended to live longer. The number of tests taken between the ages of 16 and 30 correlated strongly with the age of death. The more tests you take, the longer you will live!

Page 11: Psychometrics 101: Foundational Knowledge for Testing Professionals Steve Saladin, Ph.D. University of Idaho

Some Facts About Correlation• It is not causation, but can be used to predict

• Small samples may miss relationship

• Heterogeneous samples may miss relationship

0.87

0.78

0.42

Page 12: Psychometrics 101: Foundational Knowledge for Testing Professionals Steve Saladin, Ph.D. University of Idaho

Error, Error Everywhere

• No test is perfect, no measurement is perfect

________

• Get more precise, but never get exact

• Score = Truth + Error

Page 13: Psychometrics 101: Foundational Knowledge for Testing Professionals Steve Saladin, Ph.D. University of Idaho

Error, Error Everywhere

• Error can be lots of things including The environment The test-taker Procedural variations The test itself

• Since error makes scores inconsistent or unreliable, a measure of reliability of scores is important

Page 14: Psychometrics 101: Foundational Knowledge for Testing Professionals Steve Saladin, Ph.D. University of Idaho

Reliability• Test-Retest

Test group on two different occasions and correlate the results

Are results stable over time

• Internal Consistency Correlate score on each item to total Are they all measuring the same thing

• Alternate Forms Develop two versions of same test and correlate

scores on each Are your versions comparable

• All correlations so subject to same problems

Page 15: Psychometrics 101: Foundational Knowledge for Testing Professionals Steve Saladin, Ph.D. University of Idaho

So what’s good?

• GRE has reported reliability of 0.89 (Quantitative), 0.92 (Verbal) GRE Guide to Use of Scores, 2007-2008

• ACT Technical Manual reports Composite score reliability of .97

• SAT reports reliabilities of .89-.93 Test Caharacteristics of the SAT on http://

professionals.collegeboard.com/data-reports-research/sat/data-tables

• COMPASS alternate forms reliability reported to be .73-.90 http://www.nationalcommissiononadultliteracy.org/content/

assessmentmellard.pdf

Page 16: Psychometrics 101: Foundational Knowledge for Testing Professionals Steve Saladin, Ph.D. University of Idaho

Reliability & Error

• Can’t totally get rid of Error, but can estimate how much is there

• Using reliability you can estimate how much a persons score would vary due to error.

• Standard Error of the Measurement

SEM =SD * an index of the extent to which an individual’s

scores vary over multiple administrations gives the range within which the true score is

likely to exist

Page 17: Psychometrics 101: Foundational Knowledge for Testing Professionals Steve Saladin, Ph.D. University of Idaho

SEM for some tests

• GRE Verbal .34, Quantitative .51, so 68% confidence interval for score of 500 is 470-530 for Verbal, 450-550 for Quantitative Only reported in increments of 10 GRE Guide to Use of Scores, 2007-2008

• ACT Composite SEM .91, so 68% confidence interval for score of 20 is 19-21 ACT Technical Manual

• WAIS-IV FSIQ SEM is 2.16, so 68 % confidence interval for score of 100 is 98-102

Page 18: Psychometrics 101: Foundational Knowledge for Testing Professionals Steve Saladin, Ph.D. University of Idaho

Does Reliability = Validity?

• Getting a consistent result means reliability

• Having that result be meaningful is validity

• Validity is based on inferences you make from results Test has to be reliable to be valid Test does not have to be valid to be reliable

NO !

Page 19: Psychometrics 101: Foundational Knowledge for Testing Professionals Steve Saladin, Ph.D. University of Idaho

Validity

• Any evidence that a test measures what it says it is measuring

• Any evidence that inferences made from the test are useful and meaningful

• 3 types of evidence Content Criterion-Related Construct

Page 20: Psychometrics 101: Foundational Knowledge for Testing Professionals Steve Saladin, Ph.D. University of Idaho

Content Validity

• Think of a test as a sample of possible problems/items 4th grade spelling test should be a representative

sample of 4th grade spelling words GRE Quantitative should be a representative

sample of the math problems a grad school applicant might be expected to solve

• Should be part of design Identifying # of algebra, trig, calculus, etc. should

be on test (table of specifications)

• Frequently evaluated by item analysis or expert opinions

Page 21: Psychometrics 101: Foundational Knowledge for Testing Professionals Steve Saladin, Ph.D. University of Idaho

Criterion-Related Validity

• How does test score correlate with some external measure (criterion) Placement test score and performance in class Admission test score and GPA for first semester

• Sometimes called Predictive or Concurrent Validity

• Correlation that is effected by error in the test and error in the criterion Only top students take GRE Graduate School grade restriction

Page 22: Psychometrics 101: Foundational Knowledge for Testing Professionals Steve Saladin, Ph.D. University of Idaho

To use or not to use….

• Depends on the question…. What is impact of decision? What is cost of using? Of not using?

• Decision Theory can be a guide to determining incremental validity Net gain in using scores

Page 23: Psychometrics 101: Foundational Knowledge for Testing Professionals Steve Saladin, Ph.D. University of Idaho

Decision Theory

False negative True positive

True negative False Positive

GPA

GRE score200 400 600 800

A

B

C

Maximize success

Page 24: Psychometrics 101: Foundational Knowledge for Testing Professionals Steve Saladin, Ph.D. University of Idaho

Decision Theory

False negative True positive

True negative False Positive

GPA

GRE score200 400 600 800

A

B

C

Maximize opportunity

Page 25: Psychometrics 101: Foundational Knowledge for Testing Professionals Steve Saladin, Ph.D. University of Idaho

Predictive Utility

• Effectiveness = True Positive + True Negative

True Pos+False Pos+True Neg+False Neg

Have to weigh effectiveness against cost

Page 26: Psychometrics 101: Foundational Knowledge for Testing Professionals Steve Saladin, Ph.D. University of Idaho

Construct Validity

• Most important for psychological test where what you are measuring is abstract or theoretical Intelligence Personality characteristics Attitudes and beliefs

• Usually involves multiple pieces of evidence

Page 27: Psychometrics 101: Foundational Knowledge for Testing Professionals Steve Saladin, Ph.D. University of Idaho

Construct Validity

• Convergent—correlates with measures of same thing

• Divergent—does not correlate with measures of something else

• Scores show expected changes after treatment, education, maturation, etc.

• Factor analysis supports expected factor structure

Page 28: Psychometrics 101: Foundational Knowledge for Testing Professionals Steve Saladin, Ph.D. University of Idaho

Things to remember

• The normal curve

• Correlation

• Reliability

• Standard Error of the Measurement

• Validity

• Decision Theory