Statistics Flashcards
Descriptive (statistics)
Mean, median, mode, standard deviation.
Used to organize and summarize data in a meaningful way (ex: frequency distributions, measures of central tendency, measures of variability, …)
Definition & why we use it
Used to help support research findings and hypothesis.
Data must be collected and evaluated correctly.
Reliability (is data consistent?) and validity (does it measure what it is supposed to?)!
Inferential (statistics)
Assumptions; guesses; use measurements from a sample to draw conclusions about a larger, measured population.
Determines whether outcomes are likely to be more than nuts chance and whether they can be legitimately generalized to a larger population.
Statistically significant.
Always dealing with probabilities (not factual) NOT certainties.
Must replicate.
Chance
.001 best
.01 better
Less than 5% for it to happen by chance
Nominal (data)
Numbers that are used to name or categorize (categorical info)
Ordinal (data)
Numbers represent serial position; greater or lesser than.
Mode and median generally reported.
Differences between RANKINGS are not always the same.
Number relationships; superiority and inferiority.
Interval scale (data)
Consistent units of measurement, equal spacing between, allows for mathematical operations.
No true zero point.
Intervals between numbers are equal.
Ratio scale (data)
Same consistent units of measurement as in the interval scale but with the added property of a true zero point (complete absence of the thing being measured).
Compare scores in terms of ratios.
Ex: time, length, speed….
Frequency distribution
Lists scores in ascending order, allows us to see HOW OFTEN A CERTAIN SCORE SHOWS UP.
Set up in arable format.
Good for summarizing data; typically a visual component (graph)
Histogram
Bar graph that uses vertical bars that touch.
Way to graphically represent a frequency distribution.
Frequency ploygon
Method of graphically representing a frequency distribution.
Line graph.
Positive skew
Most people/scores are LOW.
The few high scores “skew” the graph.
Skew = slang
Negative skew
Most people/score are HIGH.
Skew indicates whether tail is.
Mean is larger than median (central tendency)
Pulls distribution to the right - positive skew
Mean is smaller than median (central tendency)
Pulls distribution to the left - negative skew
Measures of central tendency
Mode, median, mean
Measures of variability
Presents info about the spread of scores in a distribution.
Variance
How clustered or spread out individuals scores are around the mean.
The lower the level, the better.
Standard deviation
The average distance of scores around the mean.
Equation for variance
Σ(x-x̅)² divided by (n-1)
Equation for standard deviation
After finding variance (Σ(x-x̅)² divided by (n-1)), square root the variance.
Calculating variance
Find mean. Subtract mean from each score. Square each. Find sum of squared scores. Divide the sum by total number of scores.
Σ(x-x̅)² divided by (n-1)
What does each symbol represent?
n = # of scores x = score x̅ = mean Σ = sum of
Standard normal curve
Symmetrical distribution forming a bell-shaped curve (mean, median, and mode are all equal and fall in the exact middle).
Used to tell exactly what % falls between any 2 points.
Tells exactly where a person stands relative to everyone else in the distribution.
Z-scores
A number that shows an individual score’s deviation from the mean (written in standard deviation form).
Calculating & equation of z-score
Subtract mean from score and divide it by SD.
Z = (x-x) divide by standard deviation
Positive z-score
Indicates that score is above mean.
Negative z-score
Indicates that score is below mean.
