edpsy 490 ch 1-2

mean (x̄), (μ)

numerical average of the scores; central tendency

median (Mdn)

middlemost score value; central tendency

mode

most frequent score value; central tendency

'big' sigma (∑)

summaration operator; 'add it up'

range

difference between the highest and lowest scores in a distribution; variability

variance (σ²)

The average of the squared differences/deviations from the mean; variability

descriptive statistics

provide descriptions of a specific sample of scores

inferential statistics

numerical data that allow one to generalize- to infer from sample data the probability of something being true of a population

subject (n), (N)

who/what we gather information about

score (x)

single (numerical) value (measured from subject)

variable

quantity that can have multiple values

population

total group of scores used/measured

infinite population

undefined number of scores

finite population

defined number of scores

sample

a subset of scores from the population

parameter

numerical description of a population

statistic

numerical description of a sample

expected value (E)

'long-run average;' expectation of the scores

frequency distribution

presentation of a population of scores

model

framework for describing the shape of a distribution; a 'simplified framework'

nominal scale

unordered categories with arbitrary/assigned numbers
(e.g., 1. skittles, 2. reese's, 3. m&m's, 4. laffy taffy)

ordinal scale

ordered categories with no defined spacing/variation (without a defined middle)
(e.g., 1. never, 2. sometimes, 3. often, 4. always)

interval scale

ordered with equal spacing & with a defined middle (without a true zero)
(e.g., 1. :D, 2. :), 3. :|, 4. ):, 5. D:)

ratio scale

ordered with equal spacing & with a true zero
(e.g., ___ weeks, ___ months, ___ minutes, etc.)

standard deviation (σ)

Distance of each value from the mean; variability

right/positive skew

tail to the right (bulk of scores in the left)

left/negative skew

tail to the left (bulk of scores in the right)

symmetric/no skew

no tail/tail on left & right (bulk of scores in the middle)

Platykurtic

a normal distribution that is relatively spread out and flat

leptokurtic

A normal distribution with most of the scores in the middle and a sharp peak

mesokurtic

a normal distribution with a moderate or middle peak; 'bell-shaped'

parsimony

the essence of the data in the simplest manner possible (without distorting the truth)

normal curve

distribution model that is symmetric, has no skew (bell-shaped), is assumed to be continuous, & bulk of scores are close to the mean

normal curve formula

determines relative frequency of a score in its distribution

2-parameter model

a model is dependent on having/knowing 2 parameters
(e.g., normal curve & mean, variance)

z-distribution (unit/standard normal)

a normal curve in standard deviation units

z-score

the number of standard deviations a particular score is from the mean

percentile rank

Percentage of scores falling at or below a specific score.