
zscore:
represents number of standard deviations a data value falls above or below the mean.
 z= (Xμ)/σ
 X= score
 μ= mean
 σ= standard deviation

Percentile:
divides a distribution into 100 equal parts.
Percentile= [((# of values less than X) + .5)/total # of values] * 100%

Outlier:
extremely high or low value in a set of data

Normal graph:
Bellshaped

Normal Rule:
given to a normal (bellshaped) distribution
     I    
 [ 68%]
 [ 95% ]
 [ 99.7% ]

Stem and leaf plot:
 First digit on one side, second digit(s) on the other side.
 ex.: 18 24 25 28 39 45 46 46 49
 1  8
 2  4 5 8
 3  9
 4  5 6 6 9

Nominal
 No order
 ex: religion, race, hair color, gender

Ordinal:
 low detail order
 ex: sequels, seasons, grades, months, alphabet

Intervals:
 High detail oorder, 0≠ nothing
 ex: temperature, clock time, years, IQ

Ratio:
 high detail order, 0= nothing
 ex: height, speed, salary, age


Ungrouped:
 class
 class boundaries (the x.5 numbers above and below each class)
 frequency
 cumulative frequency (total up to a certain point; add number from the class before)
*list classes not listed or classes in between

Grouped:
 class
 class boundaries (x.5 above and below number)
 frequency
 cumulative frequency (add frequency from class before)
 relative frequency (frequency÷total from cumulative frequency)
 cumulative relative frequency


Frequency polygon:
line graph that originates from 0 before first value and ends at 0 after last value.

cumulative frequency graph:
line graph that originates from 0 before first value and ends with a horizontal line after last value.

Nominal:
ordinal:
interval:
ratio:
 mode
 median
 (symmetrical) mean; (skewed) median
 (symmetrical) mean; (skewed) median

Pareto chart:
bar graph used to show frequencies for nominal or qualitative variables.

Time series graph:
line graph used to show a pattern or trend that occurs over a period of time. Doesn't originate from 0 and ends at last value.

Pie graph:
used to show the relationship between the parts and the whole.

Mean (μ) rounding rule:
round to one more decimal place than occurs in the raw data.

Midrange:
average of highest and lowest value.

Weighted Mean:
sum of (weights*values)÷sum of weights

Variance:
the average of the squares of each value's distance from the mean. σ^2
 ex: (0+2+0+0+1+1+0)^2 ÷ 7
 σ^2= 6/7

Standard deviation:
the square root of the variance. σ

rounding rule for variance and standard deviation:
round to one more decimal place than occurs in raw data

If the word "sample" is used in description:
while doing the mean, subtract 1 from the bottom number in the division.
 ex: 0+4+0+0+1+1+0 ÷ 71
 variance: s^2= 6/6= 1
 std. deviation: s= 1

the coefficient of variation:
 CVar= (σ ÷ μ) * 100%
 μ: mean
 σ: std. deviation
When comparing two variations, the higher number is more variable.

