intro to statistics

number of values that fall within a given interval

numerical width (ex. 50 ≤ x< 60)

class of values and intervals that appears most often

has infinite possibilities in a range (ex. time)

The main difference is that in stratified sampling, you draw a random sample from each subgroup (probability sampling). In quota sampling you select a predetermined number or proportion of units, in a non-random manner (non-probability sampling

only has particular values

also the 50th percentile

value with the highest frequency

when one value of the frequency is added to the sum of all the values that came before it

the score below which a certain percentage of the data lies. ex. if you score in the 95th percentile, that means 95% of other scored less than you

75th percentile

25th percentile

Q3-Q1

how far the data ranges from the mean

the difference between the max and min values

upper quartile +(1.5)(IQR). any data larger than this is an outlier

lower quartile - (1.5)(IQR). any data smaller than this is an outlier

how consistent a set of values are

standard deviation squared

stat→ edit → put the values in L1 (midpoint of each interval in L2 if using frequency) → stat → calc → 1. var stats (freq. list=L2 if using frequency) → calculate → enter

everyone has an equal chance of being selected. ex. drawing names out of a hat

selects members at regular intervals ex. polling every 20th customer. interval =population size / sample size

sample has the same proportion from each stratum (group with commonality) as the population does, selected randomly

sample has the same proportion from each stratum (group with commonality) as the population does, selected specifically

random selection from groups likely to be representative of the entire population instead of the whole population. ex. surveying employees from some Walmart stores instead of employees throughout the chain

several levels of random sampling

members of a sample group are invited to participate

members are chosen out of convenience

sample does not accurately represent population due to sampling technique/members chosen

groups are underrepresented because they chose not to respond

collection process affects the dependent variable. ex coercion, multiple choice survey

members give inaccurate answers

• mean = X-d

• standard deviation = O

• variance= O²

• mean =pX

• standard deviation =pO

• variance =p²O²

the relationship between 2 variable

measures the strength of correlation. ranges from -1 to 1

positive correlation

negative correlation

perfect negative correlation

perfect positive correlation

no correlation

strong positive/negative correlation

stat→ x and y values in L1 and L2→ stat - calc→ 8 → calculate. make sure you switch diagnosticON by going into catalogue

A line that represents the trend or pattern in a scatter plot. It minimizes the distance between the data points and the line, showing the overall relationship between the variables. must pass through mean point

method for finding line of best fit. Linear regression is used for predicting and understanding the impact of independent variables on the dependent variable. find by going to 4 instead of 8 (on graphing calculator)

the horizontal distance of points, found by switching the x and y columns

closer to 1, the stronger the correlation