Descriptive Statistics

ratio, interval, ordinal, nominal

levels of measurement include continuous (_____, _____) and categorical (_____, _____)

organized, summarized, analyzed, trends 

raw data needs to be _____, _____, and _____, give structure for _____ in numerical data 

shape, central tendency, variability

descriptive statistics are used to characterize _____, _____, and _____ within a set of data

parameters, statistics 

_____ measure population characteristics while _____ is from sample data 

estimate population parameters, representative sample

descriptive statistics are used to _____ based on a _____

frequency distribution, rank, frequency, continuous, categorical

_____ is table of _____ ordered scores that shows _____ of each value (_____ or _____ data)

highest/lowest, cluster, most, outliers, range, errors

frequency distribution can quickly visualize _____ scores, where scores _____, and which occurred _____, useful for screening to identify _____ or inappropriate _____ that could indicate _____

percentages, sample size, comparisons 

_____ represented by each score in distribution independent of _____ and allow for _____

cumulative percentages, above/below, cut off

_____ are total that sum up to a cumulative point, helpful to quickly see % of scores that fall _____ a score (_____ point)

grouped frequency distribution, continuous, repeat scores

_____ is feasible way to present large amounts of _____ data when unlikely to have _____

mutually exclusive, exhaustive

grouped frequency distributions range is _____ and _____

arbitrary, influence, interpretation

grouped frequency distribution choice of range is _____ which can _____ the _____ of how a variable is distributed

graphed 

frequency distributions can also be _____ for visual representation 

normal, centered, mean, symmetrical, skewed, positively, negatively, tail, asymmetrical

shape may be _____ (scores are _____ around _____, _____) or _____ (_____ or _____, named by direction of _____, _____)

mean, median, mode

measures of central tendency (3)

mean, affected, extreme

_____ is average, represented by μ or x̄, _____ by _____ scores

median, average position, extreme, skewed, ordinal

_____ is value that equally divides scores, _____ in distribution, NOT affected by _____ scores, useful for _____ distributions or _____ data

mode, bimodal, multimodal, nominal, ordinal 

_____ is score that occurs most frequently, more than one = _____/_____, useful for _____ and _____ data 

interval, ratio, nominal, ordinal

mean is most valuable for _____ and _____ data, mode is meaningful for _____ data, median is meaningful for _____ data

stable, fluctuation, repeated, mathematic manipulation, estimation, population

mean is most _____, least amount of _____ if sample is _____, only measure that can be subjected to _____, most reasonable for _____ of _____

mean, median, mode, all equal, mode, median, mean

central tendency increasing order: negatively skewed _____, normal _____, positively skewed _____

dispersion, range, percentiles 

measures of variability refer to score _____ and include _____ and _____

range, two extreme, increased sample size, ineffective

_____ is difference between highest and lowest scores, only using _____ scores, increases with _____ making it _____ for comparison

percentiles, comparative, reference

_____ describes score’s position within a distribution relative to other scores, helping for converting to _____ scores or providing _____

quartiles, interquartile range

_____ divided into four equal quarters and _____ is middle 50% that eliminates extreme scores

continuous, interquartile range, median, range, 1.5 x IQR 

box plot is appropriate for _____ data, box = _____, horizontal line = _____, whiskers = _____ OR _____

outliers, errors, atypical, insights, analysis, data set

_____ are suspected anomalies due to data collection _____ or _____ data, values can distort _____, can be removed from _____ NOT _____

1.5xIQR greater, third quartile, 1.5xIQR less, first quartile, filled dot, 3x, asterisk

outliers are considered when _____ than _____ or _____ than _____, indicated by _____, data point more than _____ is considered extreme and indicated by _____

variance, full set, small, large

_____ is reflective of _____ of scores, close together = _____, spread apart = _____

deviation score, normal distribution, equal, 0 

_____ is distance of each score from mean, cannot calculate mean deviation in _____ because _____ distribution of scores = _____ value 

sum of squares

sample variability is described by _____

sample variance, sample sizes

_____ = sum of squares / sample size OR mean square, allows us to make objective comparisons in data with different _____

underestimate, n-1

sample data tends to _____ true population variance, utilize _____ in formula to correct and get unbiased estimate

standard deviation, mean, smaller 

_____ is square root of variance, so units aren’t squared, reported with _____, less spread out = _____

coefficient of variation, ratio, standard deviation, mean, percentage, interval, ratio, units, comparison, proportion, magnitude, relative

_____ is measure of dispersion around mean and is _____ of _____ to _____ expressed as _____, used with _____ or _____ data, independent of _____ to allow _____ with differences, expresses variation as _____ to account for difference in _____ of mean (_____ variation is most meaningful)

theoretical, estimates, population, sample, constant, predictable

normal distribution is _____ concept with well defined properties to make statistical _____ about _____ using _____ data, characteristics are _____ and _____

z score, relation, distribution, normalized group, area under

expressing scores in terms of standard deviation units is called _____, where score would fall in _____ to score _____, useful for interpreting score to _____, determine _____ normal curve

68, 95, 99 

1 SD = _____%, 2 SD = _____, 3 SD = _____