| A | B |
|---|
| Validity of an instrument refers to... | ...the degree to which an instrument measures what it is supposed to measure. |
| When used as qualitities of a measurement instrument, the terms validity and reliability... | ...have different meanings, unlike their frequent everyday use, when used interchangeably. |
| Reliability refers to... | ... the accuracy which the instrument is measuring. |
| In our handbook, the terms instrument and test... | ...are used interchangeably. |
| "Test" means not only standardized and teacher-made achievement tests... | ...but also aptitude & personality tests, attitude, observational & questionnaire measures. |
| When speaking of the validity of a test... | ...one must specify under what circumstances that the test is a valid measure. |
| There are ___ types of validity that we cover in this class. | ... 3. |
| A test has face validity if... | ...at test appears to measure what it is supposed to. |
| Since this type of validity can be claimed based on only a superficial examination of the test... | ...face validity is a very weak claim for evidence of validity for a test. |
| A test has content validity if... | ...the test is a good measure of a body of knowledge (course content or subject area). |
| To establish content validity... | ...the test items are matched with the content of the subject area. |
| The content may be determined in a number of ways... | ...course objectives, textbooks, teacher notes, syllaabus, curriculum guides, etc. |
| typically, there is no correlation coefficient associated with content validity... | ...just content validity, just a qualitative judgment. |
| Examples of qualitative judgment are... | ...good, poor, fair, excellent, etc. |
| The type of validity called criterion-related validity... | ...is determined by the degree to which the test correlates with some performance outside the test. |
| Criterion-related validity has two subtypes... | ...predictive and concurrent. |
| If the performance is measured at some time (usually several months) after the test is given... | ...this type of validity is called predictive validity. |
| If 6 mos. after a Reading Readiness Test the actual scores correlated .57 with the scores... | ...the predictive validity of the Reading Test was .57. |
| In the Metropolitan Reading Readiness Test, the criterion was... | ...reading ability. |
| In one subtype of criterion-related validity, the test and criterion... | ...are administuered so that a relatively short amount of time elapses between the two administrations. |
| If the correlations between a test and the criterion are at least moderately positive... | ...we can say the test has concurrent validity. |
| The degree to which a test measures what it is supposed to... | ...is called test validity. |
| The accuracy of measurement for a test... | ...is its reliability. |
| If a test correlated with some future performance... | ...this type of validity is called predictive. |
| If the test correlates with some present performance... | ...the test possesses concurrent validity. |
| Both predictive and concurrent validity are subtypes... | ...of criterion-related validity. |
| If a test is a valid measure of 5th grade social studies knowledge... | ...then the test has content validity. |
| If a reading test claims to measure reading readiness, but has no statistical data to back up the claim... | ...and only appears to measure reading readiness, then the test can be said to have face validity. |
| The consistency or accuracy of the test scores... | ...is the test reliability. |
| Three common types of reliability reported are.. | ....test-retest, equivalent or alternate form, and split-half. |
| test-retest reliability is established by... | ...administering the same test twice and correlating the two test scores. |
| If the correlation between the test and retest is strong and positive... | ...then the test has test-retest reliability. |
| One problem with test-retest is... | ...the length of time between administrations of the test. |
| About ____ weeks is commonly accepted test-retest time interval. | ...two. |
| With alternate form, or equivalent form reliability... | ...another form of the same test is constructed. |
| Split-half reliability is determined... | ...by correlating two halves of the same test with each other. |
| The 2 halves of the test are usually established by... | ...scoring the even-numbered and the odd-numbered items separately. |
| To estimate the total reliability of a split-half test... | ...we may use the Spearman-Brown formula. |
| The longer a test is.... | ...the more reliable is tends to be. |
| The greater the spread of scores... | ...the greater the possibility of having higher correlation. |
| If all people are similar (homogeneous), the reliability tends to be lower... | ...than is a more diverse (heterogeneous) group had taken the test. |
