Introduction to Measurements
A scale that is ordinal and has equal intervals between categories or scores.
Is a frequency of individual scores are typically ranked-ordered from highest to lowest, and the frequency of each score is indicated.
Simple Frequency
An overall evaluation of the extent to which theory and empirical evidence support interpretation that are implied in given uses of the scores.
Measurement Validity
The extent to which participant, rater, and observer scores are free from error.
Measurement reliability
A scale in which the categories are rank ordered.
Ordinal
When scores are concentrated at the low end of the distribution, with fewer high scores.
Positively Skewed
Provided when the relationships between items and parts of the instrument are empirically consistent with the theory or intended use of the scores.
Internal Structure
Also called alternate-forms reliability and is obtained by administering two forms of the same measure to one group of individuals and then correlating the scores from the two forms.
A scale in which there are mutually exclusive categories, without any order implied.
Nominal Scale
The middle score of the distribution - the midpoint that divides a rank-ordered distribution into halves containing an equal number of scores.
Median
Demonstrates the extent to which the sample of items or questions in the instrument is representative of some appropriate definition, universe or domain of content, tasks, or hypothetical construct such as motivation or attitude.
Content
Indicates the degree to which individuals’ answers to items measuring the same trait are consistent.
Internal consistency
A scale that can be used in comparing and interpreting the scores.
Ratio Scale
Statistic that indicates whether the scores are clustered close to the mean or deviate broadly from the mean.
Relationships to other variables when the criterion is measured in the future, after the instrument has been administered.
Predictive relationships
Estimate is obtained by administering one form of an instrument and then the second form after a time interval to the same group of individuals. This method combines equivalence (alternate forms) with stability (time interval).
Equivalence and stability
Means “evaluation,” and sometimes it refers to the more specific process of diagnosing of individual difficulties, such as assessing for learning disabilities and or to refer to procedures used to obtain information about student performance.
Assessment
Indicates the percentage of scores at or below a particular score.
Percentile Rank
Relationships to other variables established by correlating two measures of the same trait that are given to the same individuals at about the same time
Concurrent relationships
Obtained by administering one measure to one group of individuals, waiting a specified period of time, and then readministering the same instrument to the same group.
Stability estimate of reliability