Flashcards in Ch18Research Deck (48):
What is the definition of measurement used by the text?
systematic process by which things are differentiated; not a random process, but proceeds according to rules and guidelines
What are some of the examples of variable properties?
distance, duration, frequency, magnitude, topography, latency, pattern
What are the scales of measurement?
Nominal, Ordinal, Interval, Ratio
What are nominal scales?
classification without placing any value on the categories; none of the properties of a real number system; identified by name or numeral
ex: quadriplegic, dipelgic, and hemiplegic
What are ordinal scales?
indicate whether a person or object has more or less of a certain quality; do not ensure that there are equal intervals between categories or ranks; possesses one property of a real number system (order)
Ex-the amount of assistance a patient needs to ambulate is often rated as maximal, moderate, minimal, standby, or independent.
What are interval scales?
have order and distance, but lack origin; equal intervals so addition and subtraction are meaningful, but because there is no meaningful zero, multiplication and division are not useful.
ex: Celsius and Fahrenheit temperature scales
What are ratio scales?
exhibit order, distance, and origin; all arithmetic functions can be applied; absence is zero
ex: Length, time and weight are generally considered ratio scales because their absence is scored as zero, and the intervals between numbers are known to be equal.
How do you determine the scale of a measurement?
determine whether there is a true zero (origin), whether intervals between numbers are equal (distance), and whether there is an order to the numbers or names that constitute the measure (order)
What are the two classifications of variables?
continuous and discrete
What are continuous variables?
one that theoretically can be measured to a finer and finer degree
ex- time (seconds then milliseconds, etc)
What are discrete variables?
numbers can only assume only distinct values, no "between categories"
ex - male/female, quadriplegic/dipelgic/hemiplegic
What seven basic concepts underlie measurement theory?
1 frequency distribution, 2 mean, 3 variance, 4 standard deviation, 5 normal curve, 6 correlation coefficient, and 7 standard error of measurement
What are the two basic frameworks in which measurement is conducted and evaluated?
norm-referenced and criterion referenced
What are norm-referenced frameworks?
Judge individual performance in relation to group norms
What are criterion referenced frameworks?
individual's performance is evaluated with respect to some absolute level of achievement
How is reliability defined?
the degree to which test scores are free from errors of measurement
What are the two theories of reliability?
classical measurement theory and generalizability theory
What is classical measurement theory?
the assumption that every measurement, or obtained score, consists of a true component and an error component
What is generalizability theory?
recognizes that there are different sources of variability for any measure
What are the four components of reliability presented?
instrument, intrarater, interrater, and intrasubject reliability
What are the two ways in which reliability is quantified?
relative and absolute reliability
What is relative reliability?
examines the relationship between two or more sets of repeated measures
What is absolute reliability?
examines the variability of the scores from measurement to measurement
What is measurement validity?
the appropriateness, meaningfulness, and usefulness of the specific inferences made from test scores
What three forms of validity are concerned with measurement validity?
construct, content, and criterion
Difference between a numeral and a number
Numeral-does not necessarily have a quantitative meaning; Number-has quantitative meaning
Characteristics of a Real Number System
Order - higher numbers represent greater amount
Distance - magnitude of differences between successive numbers
Origin - number 0 represents an absence of the measured quality
What is Reliability?
degree to which test scores are free from errors of measurement
What is frequency distribution?
The numbers of times each score is represented in the data set.
What is Mean?
the sum of the observations divided by the number of observations
What is variance?
Measure of the variability around the mean within a data set; does not have a great deal of intuitive meaning because it is calculated from squared deviation scores.
What is Standard Deviation?
the square root of the variance and is expressed in the units of the original measure; does have intuitive meaning.
What is Normal Curve?
symmetric frequency distribution that can be defined in terms of the mean and standard deviation of a set of data (bell curve)
What is Correlation Coefficient?
a statistical summary of the degree of relationship that exists between two or more measures; the relationship can either be different variables or repeated measures of the same variables
What is Standard Error of Measurement?
taking repeated measures of the same participant and then calculating the standard deviation score
What are the 3 categories Instrument Reliability?
Biophysiological, Self-Report, and Observational
What is Intrarater Reliability?
The consistency with which one rater assigns scores to a single set of response on two occasions
What is Interrater Reliability?
Consistency of performance among different raters or judges in assigning scores to the same objects or responses. It is determined when two or more raters judge the performance of one group of subjects at the same point in time.
What is Intrasubject Reliability?
The actual changes in subject performance from time to time
What is Biophysiological Measurement?
Instruments can be calibrated to ensure accuracy and then typically, the reliability of these instruments is assessed by taking repeated measurements across the range of values expected to be found in actual use of the device.
What is Self-report Measurement?
Test-retest reliability: subjects take the same test on 2/more occasions;
Parallel-form reliability: similar forms of a test are each administered once;
Split-half reliability: portions of a test are compared with each other;
Internal consistency: responses to individual items are evaluated.
What is Observational Measurement?
Require only a human instrument with systematic knowledge of what to observe.
What is Construct Validity?
The extent to which a test measures what it claims to be measuring
What is Content Validity?
The extent to which a measure is a complete representation of the concept of interest.
What is Criterion Validity?
The extent to which one measure estimates or predicts the values of another measure or quality; (concurrent and predictive validity)
demonstrated when a test correlates well with a measure that has previously been validated
Relates to whether a test done at one point in time is predictive of future status.