STA 2023 unit 1 vocab

statistics

the study of how to collect/organize/analyze/interpret numerical information from a data set

individuals

people/object included in the study (2 types)

statistics

the study of how to collect/organize/analyze/interpret numerical information from a data set

individuals

people/object included in the study (2 types)

variables

characteristics of the individuals to be measured or observed (2 types)

population data (parameter)

the data from each individual in the population of interest

sample data (statistic)

comes from some individuals in the population of interest

nominal level

applies to data that consists of names/labels/categories, order doesn't matter

ordinal level

applies to data that can be arranged in order, not numerical

interval level

numerical measurements with no true zero or the ratio isn't meaningful

true zero

if the measurement is converted into other units then the result would be zero

ratio level

data with meaningful ratios, have a true zero

simple random sampling

selected randomly with a number table or computer, each individual/sample of the population has equal chances of being selected

stratified sampling

population divided into several groups and then a simple random sample is drawn from each group

systematic sampling

elements of the population are arranged in order and then every kth element is selected with a random starting point

cluster sampling

population are is divided into sections and then some sections are randomly selected with every individual of each section included in the sample

convenience sampling

has a time/location limit and not every individual of the population has a chance of being selected

multistage sampling

using a combination of sampling methods to create smaller groups at each stage (not convenience, last stage is cluster)

class requirements

every data value must fall into one of the classes
the classes must not overlap
the classes must be of equal width
there must be no gaps between classes

relative frequency

class frequency/total number of data values

relative frequency percentage

relative frequency * 100

cumulative frequency

sum of the frequencies for that class and previous classes

mount shaped symmetric

T shaped, mean/median/mode are equal

skewed to the left

rises to the right, mean<median<mode

skewed to the right

rises to the right, mode<median<mean

unimodal

only has 1 peak/mode

bimodal

has 2 peaks/modes

population mean

u, sum of xi over N (N is the population size)

sample mean

x_, sum of xi, over n (n is the sample size)

deviation

xi-mean (u or x_), negative=value below average, positive=value above average

coefficient of variation

(standard deviation/mean) * 100, small=most of the data is split around the mean, large=data values are split everywhere

outlier

a value that's considerably small or large

lower outlier limit

Q1-1.5(LQR)

upper outlier limit

Q3+1.5(LQR)