Psychological Assessment (Diagnosis) pt.7

Mesokurtic

It is approximately a normal distribution—yes, there are outliers, but not too many.

It is not as thin as a platykurtic distribution and not as thick as a leptokurtic distribution.

Leptokurtic

Tails are heavy and shoulders are light; more extreme values at the tails

Platykurtic

Tails are light while shoulders are heavy; free outliers at the tails

Platykurtic

The tails are light or thin.

There are only a few outliers, and most of the scores are concentrated in the middle and shoulders.

Leptokurtic

The tails are heavier, and the shoulders are relatively thinner.

The tails are heavier because there are more outliers on both ends.

Validity

is the extent of how a test measures what it purports to measure

Validity

The ___ of a test may diminish as the culture or the time changes.

Validity

A judgment or estimate of how well a test measures what it purports to measure in a particular context

valid

A "___" tests is a test that has been shown to be valid for a particular use with a particular population of test takers at a particular time. No test is "universally valid" for all time, for all uses and with all types of populations.

universally valid

No test is "_____" for all time, for all uses and with all types of populations.

Validity

The ____of a test may diminish as the culture or the time change, thus a test's ___ has to be reestablished w/ the same or other test taker populations

Validation

is the process of gathering and evaluating evidence about validity. Both the test developer and test user may play a role in this.

Does this test measure what it claims to measure?

Example: Conscientiousness: Does the test for conscientiousness actually measure conscientiousness?

According to studies at UP, validity is "evidence."

When a test is valid, it means that it is reliable or solid.

Katibayan

According to studies at UP, validity is "______". If your test is valid, then it is "matibayan"

Validity

A test is valid only for a particular purpose (e.g., if it's an intelligence test, it should be validated as an intelligence test and shouldn't be used as an aptitude or personality test).

A test that is valid is only valid for a particular population; for instance, if a test is valid for 18 years old and above, it should only be used by people in that age range, not younger individuals.

Validity

There is no universally valid test. Tests have limitations, and if we go beyond those limitations, the validity of the test may be questioned.

Example: An intelligence test that was found valid in 1975 may no longer be valid and should not be used.

It's been too long, many changes have happened, and the theory that the test was based on may be outdated compared to the present or the construct it was meant to measure.

Validation

The validity may have diminished. It is considered obsolete.

If the test's validity diminished, you can re-establish its validity by repeating the _____ process.

You can also re-establish its validity for a different population (e.g., an intelligence test validated in 1975 for adults may be revalidated for teenagers).

A test cannot be valid if it is not reliable

What is the relationship of reliability & validity?

Reliability

The first thing we establish is

limit

Reliability does ____ validity.

necessary, but not sufficient

From the psychometric perspective, evidence of score reliability is considered to be _______, condition for validity (Urbina, 2014)

reliable; valid

A test should first be _____ before it can be ____.

validity

The test should be established as stable/reliable first before we establish its _____.

Content

This is the validation used to check for the appropriateness of a survey.

Types of Validity

Content Validity

Criterion Validity

Construct Validity

Face Validity

Content Validity

Evaluates how adequately an instrument covers all relevant parts of the construct it aims to measure

Content Validity

Extent on how appropriate/representative the items relative to the construct it is measuring

Ex. Depression has behavioral, affective and cognitive aspects which must be covered adequately in a scale.

Content Validity

Does our instrument or measure cover all the relevant parts of the construct we are aiming to measure, or not?

Content Validity

Are the items appropriate and representative of what we are trying to measure?

For example, if you create a depression scale, we know that depression has behavioral, affective, and cognitive aspects. If we want to make our test content valid, then in our items, we should include the behavioral, affective, and cognitive aspects of depression.

Criterion Validity

To assess the validity of the newly created college admission test of Backburner University, they have decided to use the first semester GWA of the incoming freshman students as a standard to assess if the test was actually effective. What measure of validity will they use?

Criterion Validity

A judgment of how adequately a test score can be used to infer an individual's most probable standing on some measure of interest - criterion

Criterion

the standard giants which a test/test score is compared or evaluated; it is a direct and independent measure of what the test is designed to predict (can be another test or an outcome measure)

Concurrent Validity

Predictive Validity

Two Types of Criterion Validity

Criterion Validity

How adequate is the score on the test we are validating? Can we use this to infer the probable standing of the test taker on the test/criterion we have?

Criterion

The _____ is the standard we use to compare or evaluate the test score on the test being validated. It could be another test or an outcome measure.

Concurrent Validity

Extent to which test scores may be used to estimate an individual's present standing on a criterion

Test scores are obtained at about the same time that the criterion measures are obtained.

Concurrent Validity

Extent to which test scores may be used to estimate an individual's present standing on a criterion

Concurrent Validity

Test scores are obtained at about the same time that the criterion measures are obtained.

Concurrent Validity

You get the scores/data from the test and criterion at the same time

Predictive Validity

Measures the relationship between the test scores and a criterion measure obtained at a future time

How accurately scores on the test predict some criterion measure

Ex. the relationship between college admission tests and freshman GPA provides evidence of the predictive validity of the admission test

Predictive Validity

Measures the relationship between the test scores and a criterion measure obtained at a future time

Predictive Validity

How accurately scores on the test predict some criterion measure

Ex. the relationship between college admission tests and freshman GPA provides evidence of the predictive validity of the admission test

Alpha Error

Type I Error is also known as

Alpha Error / Type I Error

False positive

Rejecting the null hypothesis when it is true

Alpha Error / Type I Error

False positive

Alpha Error / Type I Error

Rejecting the null hypothesis when it is true

Alpha Error / Type I Error

You thought there was something, but there wasn't.

You rejected the null hypothesis when you should have retained it.

Alpha Error / Type I Error

In research, when we say null hypothesis—there's no significant effect or significant difference.

You rejected the null because your result showed no significant effect/relationship, but you were wrong because there wasn't any in the first place.

Ex. "He said he liked you, but it wasn't true."

Beta Error

Type II Error is also known as

Beta Error / Type II Error

False negative

Failing to reject the null hypothesis when it is false