Reading...
Play button
Play button
Use LEFT and RIGHT arrow keys to navigate between flashcards;
Use UP and DOWN arrow keys to flip the card;
H to show hint;
A reads text to speech;
28 Cards in this Set
- Front
- Back
|
What is Ordinal?
|
Ranking- a list of who comes first, second, third, etc.; does not name how far away from each other the ranks are.
|
|
|
What is Nominal?
|
Naming a #, naming something. Numbers used to classify, name, or identify something...team jersey numbers, occupational code groups, telephone extension.
|
|
|
What is interval?
|
The distance between each number is equal (used most on psych testing) Thermometer, scales, ruler, etc...
|
|
|
What is Ratio?
|
Having a true Zero (inches, weight, age, $), with equally spaced intervals. The difference between 10 lbs and 20 lbs is 10 lbs, same for 30 and 40 lbs.
|
|
|
What are scales?
|
One way to organize data. Pg. 15 & 16.
|
|
|
What is Formula X=T + E?
|
X=Obtained Score
T=True Ability E= Error (interpretation, administration, double-meanings, examinee, time, scorer, environ., etc. |
|
|
What is a Norm and its function?
|
Norms are ways of interpreting scores compared to a group of people. They give us a way to compare scores with other scores. A good test must have publications and manuals. Look for norms and how they develop the test.
|
|
|
Tests/Assessments are used to do what?
|
Measure the tendencies- never 100% accurate. Can help define a problem, understand/gather/interpret info. about client, help with coping, can be qualitative & quantitative, measure abilities, interests, attitudes. Be aware of presence of multiple layers that can influence the outcome of assmnts. The score of a test is both truth and error.
|
|
|
What is Attribution Bias?
|
Attributing some results in a test to a client that are really attributed to circumstances/setting/situation.
|
|
|
What is Standardized test administration?
|
Tests should be administered, interpreted and scored the same way. But not changes should not be taken into account unless the variance is significant.
|
|
|
What is Measures of Central Tendency?
|
Ways to describe data...the tendency for scores to accumulate most frequently in the middle.
|
|
|
What is Mean?
|
The average of all scores. Add all scores, divide by # of scores.
|
|
|
What is Mode?
|
The score(s) that occur most frequently. Can be more than one= bi-modal.
|
|
|
What is Median?
|
The score that falls in the middle. Where 50 % of scores are above and 50% of scores are below.
|
|
|
What is Measures of Validity?
|
Describes how scores tend to gather around the central tendency.
|
|
|
What is Range?
|
The distance or difference between the largest and smallest scores.
|
|
|
What is Standard Deviation?
|
How far something falls from (above or below) the mean.
|
|
|
What is Normal Distribution?
|
Symmetrical around its mean and is unimodal. Has a single peak and drops off with approximately equal frequency on either side. 68% of people usually score within the first Standard Deviation. Pg. 28
|
|
|
What is Correlation Coefficient?
|
A linear relationship. When A exists, B exists, or a negative correlation, when A exists, B doesn't exist. NOT CAUSALITY. Strongest relationship is when score is closest to Absolute 1.
|
|
|
What is a Curvilinear Relationship?
|
As A continues to go up, B goes down. (Anxiety and sports performance, time and attention span.)
|
|
|
What are Standard T- Scores?
|
A way to understand what the score means?
Mean = 50, SD=10. |
|
|
What is Percentile?
|
In the 95th percentile=95% of scores fell below Jim's.
|
|
|
What is a Reliability Coefficient?
|
.88=88% of the variance of the test score is attributable to true score and 12% error. 88% truth, 12% error.
|
|
|
What is Reliability?
|
The ability to test, re-test and get the same results, that it reliably measures consistently over time. Tests can be reliable...but not valid. Pg. 47 (Yardstick can reliably measure 1 foot, but if marked wrong, NOT valid)
|
|
|
What is Validity?
|
The extent to which the test we're using actually measures the characteristic or dimension we intend to measure. When something measures what it says it should measure. Measuring height might measure intelligence...not valid. A valid test must also have SOME degree of reliability.
|
|
|
What is the Standard Error of Measurement?
|
John scored 100 with a 95% confidence level of 94-106. 95 out of 100 times, he'll score between 94 and 106.
|
|
|
What is Rational Test Construction Skill?
|
Based on the assumption that the content of test items must directly reflect the characteristic/dimension we are interested in measuring. Eliminate ones that aren't valid/ RATIONAL for measuring the topic.
|
|
|
What is Empirical Scale Construction?
|
Based upon the differences in responses of people. (MMPI) Whatever items discriminated between normal answers and the target audience (schitzophrenics hearing voices) ONLY include those questions that discriminates between the two.
|
