Scales of measurement and describing data Flashcards
Collective influence of all the factors on a test score or measurement beyond those specifically measured by the test or measurement
Error
Scale of measurement: Classification/categorization based on one or more distinguishing characteristics (e.g. DSM, Yes/no questions)
Nominal scale
Scale of measurement: Imply nothing about how much greater one ranking is than another; no absolute zero point (e.g. Binet intelligence test); cant be averaged
Ordinal scale
Scale of measurement: Equal intervals between numbers; no testaker posseses none of the ability or trait being measured; no absolute zero point; can be averaged
Interval scale
Scale of measurement: Zero has meaning; assessment in neurological functioning
Ratio scale
Scale of measurement that is most frequently used
Ordinal scale
A set of test scores arrayed for recording or study
distribution
All scores are listed alongside the number of times each score occurred
Frequency distribution
3 kinds of graphs for frequency distribution
Histogram, bar graph, frequency polygon
Vertical lines drawn at the true limits of each test score (class intervals)
Histogram
Continuous line connecting points where test scores or class intervals meet frequencies
Frequency polygon
Indicates the average or midmost score between the extreme scores in a distribution
Measures of central tendency
Measure of central tendency: appropriate for interval or ratio data
mean
Measure of central tendency: Appropriate for ordinal, interval, ratio data
median
Measure of central tendency: most frequently occurring score in a distribution of scores
Mode
Measure of central tendency: only for nominal; useful in analyses of qualititative data or verbal nature; can convey a wealth of info in addition to the mean
mode
Indication of how scores in a distribution are scattered or dispersed
Variability
Difference between highest and lowest scores;simplest measure of variability
Range
Distribution of test scores can be divided into 4 parts
Quartile
Difference between q3 and q1
interquartile range
interquartile range divided by 2
semi-interquartile range
Square root of the average squared deviations about the mean
Standard deviation
Arithmetic mean of the squares of the differences between the scores in a distribution and their mean; square and sum all deviation scored and divide by total number of scores
Variance
Indication of how the measurements in a distribution are distributed
Skewness
Few scores fall at the high end of distribution; exam was too difficult; q3-q2 distance greater than q2-q1
Positive Skew
Scores fall on the low end of the distribution; test was too easy; q3-q2 distance less than q2-q1
Negative skew
Steepness of a distribution in its center
kurtosis
Kurtosis: relatively flat
Platykurtic
Kurtosis: relatively peaked
Leptokurtic
Kurtosis: Somewhere in the middle
mesokurtic
Simplifies rhe interpretation of individual scores on the test; both sides approach x-axis asymptotically
The normal curve (laplace-gaussian curve)
The first person to refer the normal curve
Karl pearson
Area on the normal curve between 2 and 3 SD above and below the mean
Tail
__% all scores occur between the mean and 1SD above the mean
34%
Approximately % of all scores occur between the mean and + 1SD
68%
Approximately _% of all scores occur between the mean and +_2SD
95%
A raw score that has been converted from one scale to another scale
Standard score
Conversion of a raw score into a number indicating how many SD units the raw score is below or above the mean of a distribution; zero plus,minus scale
z-score
T in T-score means…
Thorndike
mean=50; sd=10 ; no scores are negative and used for aptitude tests
t-scores
Take on whole values from 1-9, which represent a range of performance that is half of a SD in width;Used for achievement tests
Stanine
mean=100; sd=15
deviation IQ
1-10 scale; mean=5.5, SD=2; used for personality tests
Sten
Represent how an individual test taker’s score compares to the scores that are equal or below a certain score within a given sample
percentile
Retains a direct numerical relationship to the original raw score; magnitude of differences between such standard scores exactly parallels the differences between corresponding raw scores
Linear transformation
Data not normally distributed yet comparisons with normal distributions need to be made
non-linear transformation
Normalized standard score scale
involves stretching the skewed curve into the shape of a normal curve and creating a corresponding scale of standard scores
Also called as maximal performance test
Ability test
Measure usual or habitual thoughts, feelings and behavior.
Typical performance test
Compare the relative strength of different characteristics within a test taker and therefore often used “forced choice” test items
Ipsative score
The more the test taker responds in a particular direction keyed by the test manual as correct or consistent with a particular trait, the higher the test taker is presumed to be on targeted ability of trait
cumulative scoring
Component of a test score attributable to sources other than the trait
Error variance
Positive skew
mean is greater than the median, while median is greater than mode
Negative skew
mean is lesser than the median while median is lesser than mode
