Stats Ap Fall Exam

Front 1

variables

Back 1

characteristics recorded about each individual
quantitative: variables in numbers
categorical: names the category

Front 2

case

Back 2

individual about whom or which we have data

Front 3

frequency table

Back 3

organizing counts

Front 4

relative frequency table

Back 4

similar to a normal frequency table, but this give percentages

Front 5

distribution

Back 5

names the different possible categories and how frequently they may occur

Front 6

area principle

Back 6

the area occupied by a part of the graph should correspond to the magnitude of the value it represents

Front 7

bar chart

Back 7

displays the distribution of a categorical variable, showing the counts for each category next to each other for easy comparison

Front 8

pie chart

Back 8

shows the relative portion/ the whole group of cases as a circle.

Front 9

contingency table

Back 9

used when looking at two categorical variables together. shows how the individuals are distributed along each variable

Front 10

marginal distribution

Back 10

th distribution of one of the variables in a contingency table

Front 11

conditional distribution

Back 11

a distribution of one variable for only those individuals satisfying some condition on another variable

Front 12

independent

Back 12

in a contingency table when the distribution of one variable is the same for all categories of another

Front 13

segmented bar chart

Back 13

used rather than a bar chart. each bar represents a "whole" and is divided into the separate parts

Front 14

Simpson's paradox

Back 14

when averages are taken across different groups, they can appear contradictory

Front 15

distribution

Back 15

the bins and the counts in each bin give the distribution for a quantitative variable

Front 16

histogram

Back 16

shows the distribution as the heights of bars

Front 17

relative frequency histogram

Back 17

displays the percentage of cases in each bin instead of the count

Front 18

stem-and-leaf displays

Back 18

contains all the information found in a histogram and satisfies the area principle ad show the distribution. Preserves the individual data values

Front 19

dotplot

Back 19

a simple display the places a dot for each case in the data

Front 20

Describing distribution of a Histogram

Back 20

unimodal: one main peak
bimodal: two peaks
multimodal: three of more peaks
uniform: all bars are approximately the same height
symmetric: fold along the middle and the sides will match
tails: thinner ends of a distribution
skewed: if a tail stretches out really far than the histogram is skewed to the side of the longer tail
outliers: stragglers that stand off away from the body of the distribution

Front 21

timeplot

Back 21

shows data that change over time

Front 22

center of distribution

Back 22

median: the middle value that divides the histogram into two equal areas

(n+1)/2

n is the number of numbers

Front 23

spread

Back 23

describes the distribution numerically which measures the spread along with its center

Front 24

range

Back 24

max-min

Front 25

quartiles

Back 25

split the data at the median and find the medians of those two halves

Front 26

interquartile range/IQR

Back 26

upper quartile-lower quartile

Front 27

percentiles

Back 27

the lower and upper quartiles are aka the 25th and the 75th percentiles of the data

Front 28

the five-number-summary

Back 28

Median
Quartiles : Q1 and Q3
Maximum
Minimum

Front 29

mean

Back 29

add up the numbers and divided by n

the point in which the histogram would balance

for skewed data, use the median instead

Front 30

deviation

Back 30

how far the data value is from the mean

Front 31

standard deviation

Back 31

1) you find the mean (ybar)
2) subtract the mean from each value
3) square each value
4) add these numbers and divide by n-1
5) take the square root of this number

Front 32

z-scores

Back 32

how many standard deviations something is from the mean

z= (y-ybar)/s

s is the standard deviation

Front 33

normal model

Back 33

appropriate for distributions whose shapes are unimodal and roughly symmetric

mean=0
SD=1

Front 34

standardized value

Back 34

found by subtracting the mean and dividing by the standard deviation

Front 35

68-95-99.7 Rule

Back 35

In a Normal model, 68% of the values fall within one standard deviation of the mean, 95% fall within two standard deviations of the mean, and 99.7% fall within three standard deviations of the mean

Front 36

normal percentile

Back 36

gives the percentage of values in a standard normal distribution found at that z-score or below

Front 37

normal probability plot

Back 37

if the plot is normal, then a diagonal straight line should form

Front 38

scatterplot

Back 38

shows the relationship between two quantitative variables measured on the same cases

Front 39

direction of scatterplots

Back 39

runs from upper left to the lower right- negative
lower left to upper right-positive

Front 40

response and explanatory variable

Back 40

explanatory is on the x-axis
response is on the y-axis

Front 41

correlation

Back 41

strength of the linear association between two quantitative variables

between -1 and 1

Front 42

how to find the correlation coefficient

Back 42

1) (x-xbar)(y-ybar) do this for each pair
2) divide this sum by the product of (n-1) x slilx x slily

Front 43

predicted value

Back 43

the value of y-hat found for each x-value in the data. Found by substituting the x-value in the regression equation.

Front 44

residual

Back 44

the difference between the observed value and its associated predicted value

y - y-hat= residual

Front 45

linear model

Back 45

y-hat = b0 + b1x

y-hat is the predicted value
b0 is the y-intercept
b1 is the slope

Front 46

R-squared

Back 46

the correlation between y and x
the fraction of variability accounted for by the least squares regression on c
how successful the regression is in linearly relating y to x

Front 47

least squares

Back 47

specifies the unique line that minimizes the variance of the residuals or, the sum of the squared residuals

Front 48

good linear model?

Back 48

1) scatterplot is linear
2) calculate r. if r is close to 1 or -1 then it is a good model
3) look at residual plot and see no pattern

Front 49

leverage

Back 49

outliers that exert high leverage on a linear model. Pulls the line close, so that they can have a large effect on the line

Front 50

Influential point

Back 50

a point that has high leverage

Front 51

random

Back 51

an event is random if we know what outcomes could happen, but not which particular values did or will happen

Front 52

simulation

Back 52

models random events by using random numbers to specify event outcomes with relative frequencies that correspond to the true-world relative frequencies we are trying to model

Front 53

Census Sample

Back 53

survey of the whole population

Front 54

SRS

Back 54

sample size n in which n elements in the population has an equal chance of selection

Front 55

Convenience Sample

Back 55

biased. Individuals who are conveniently available

Front 56

Systematic Sampling

Back 56

every nth number

Front 57

Stratified Sample

Back 57

divides the population into strata (groups). Into homogeneous strata within each group do a SRS

Front 58

Cluster Sampling

Back 58

divide into heterogeneous groups and take a SRS

Front 59

Multistage Sampling

Back 59

Sampling done in stages

Front 60

Forms of Bias

Back 60

1) Response Bias: wording of the question
2) Non-Response Bias: you are present, but chose not to respond
3) Voluntary Response: responding because you have a strong feeling
4) Undercoverage: you are not present and hence not represented in the sample

Front 61

Observational Study

Back 61

no manipulation of factors has been employed

Front 62

Retrospective Study

Back 62

subjects are selected and then their previous conditions or behaviors are determined

Front 63

Prospective Study

Back 63

observational study in which subjects are followed to observe future outcomes

Front 64

experiment

Back 64

manipulates factor levels to create treatments and compare the responses of the subject groups across treatment levels

Front 65

Principles of Experimental Design

Back 65

1) Control: areas we know may have an effect, but are not factors being studied
2) Randomize
3) Replication
Block: reduces variation (not required)

Front 66

Statistically Significant

Back 66

an observed difference is too large for us to believe that it is likely to have occurred naturally

Front 67

Control Group

Back 67

group given the placebo or baseline treatment

Front 68

single-blind

Back 68

either those who can influence the results do not know or those who evaluate the results dont know

Front 69

double-blind

Back 69

when everyone is blinded

Front 70

block

Back 70

when groups of experimental units are similar, we gather them into blocks. this isolate variability so that we may see the differences more clearly

Front 71

confounded

Back 71

the effects of two or more factors are associated with eachother