AP Statistics True False Quiz Prep 1-193

Categorical data

_ cannot be measured. Instead, data is counted and placed into a specific group or category

quantitative data

is measurement data

frequency

looks at actual counts

relative frequency

looks at data as percentages or proportions

Cumulative frequency

the sum of the current count and all previous counts (a running total)

Cumulative relative frequency

is the sum of the current percent and all previous percentages (a running total of the

percentages or proportions)

a contingency table

is also called a two-way table

dependent

If variables are ___ then there is an association/relationship between the variables

independent

If variables are __ then there is not an association/relations between the variables

pie charts and segmented bar charts

should a full distribution (100%)

a mosaic plot

is a type of segmented bar chart

mosaic plot

allows you to compare relative frequencies (percentages or proportions) of two or more groups

a mosaic plot

allows you to compare the actual quantity of two more groups. Large areas have a large quantity than a smaller area

pie charts and bar charts

charts are two ways to visually display categorical data

Histograms, stem-plots, and dot plots

are three ways to visually display quantitative data

lot at or compare one variable statistics

Pie charts, bar charts, histograms, stem-plots, and dot plots

modes

The humps on a histogram are called

gaps

The spaces on a histogram are called

must

Stem-plots ___ have a key

least to greatest

The leaves of stem-plots are listed from ___ from the stems

back-to-back

When comparing two different items (ex. males vs females), you can create a ____ stem-plot

0-4 and 5-9

When creating a stem-plot and you have a lot of data, it is good to split the leaves from

shape, center, and spread

When discussing quantitative data, you must discuss

roughly symmetric

Never say symmetric. Instead say

when discussing shape

you should discuss three things: 1) unimodal, bimodal, multimodal, or uniform 2) roughly symmetric or skewed (left/negative or right/positive), 3) gaps and outliers (if any exist)

mean

is the average

median

is the middle number when numbers are arranged from least to greatest

mode

is the most occurring value

n+1/2

to find the location of the median, use the equation

odd

When the sample size is ___, the median will always be the middle term

even

when the sample size is___, the median will not be a middle term, but rather the average of the two terms closest to

the center

roughly symmetric

The mean and the median are about the same when data is

skewed to the right

The mean is larger than the median when data is

skewed to the left

The mean is smaller than the median when data is

range is the

maximum value minus the minimum value

the lower quartile

is the median of the bottom half of the data

the upper quartile

is the median of the top half of the data

Q3-Q1

The interquartile range (IQR) is

weakest

the range is the ___ form of variability

use mean and standard deviation

when data is roughly symmetric with no potential outliers

use the median and IQR

when data is skewed or outliers exist

median and IQR

are resistant to outliers and skewed data

mean and standard deviation

are not resistant to outliers and skewed data

smallest

Standard deviation is __ when data is tightly clustered around the mean

larger

standard deviation is ___ when data is more spread out

min, Q1, median, Q3, max

five number summary is

lower and upper fences

outliers form the __ on box plots

modified box plots

include outliers

modified

always create ___ box plots

whi

it is skewed left

if the box plot has more amount to the left side

it is skewed right

if the box plot has more amount to the right side

time plots

are a visual displays that look at data over a period of time

are shifted

when adding or subtracting a value to every number in a data set, all measures of position

stay the same

when adding or subtracting a value to every number in a data set, all measures of spread

are rescaled

when multiplying or dividing a value to every number in a data set all measures of spread and variability (with the exception of variance)

when rescaling the variance

you must first square the value you are rescaling and then multiply/divide it by the variance

mew

population mean is

x bar

sample mean is

sigma

population standard deviation is

s

sample standard deviation is

sigma squared

population variance is

s squared

sample variance is

below

Percentile rank is the percentage of data that lies ___ an observation

raw data

is listing out all of the actual data

summary statistics

are statistics that summarize the data (mean, standard deviation, etc.)

n

sample size is denoted by

sample size

is the number of observations in the sample

approximately normal

never say data is normal, instead say it is

normal models

are used when histograms are unimodal and roughly symmetric

normal models are used when

normal probability plots are fairly linear from the lower left to the upper right

mean of the data

The center of every normal model is the

normal models

are standardized when the data is converted into z-scores

zero

When normal models are standardized into z-scores, the mean becomes

units

z-scores have no

above or below

z scores tell us how many standard deviations ___ the mean

data is below the mean

when z scores are negative

data is above the mean

when z scores are positive

y-mew/sigma

the formula for z score is

on or above

density curves look at data ___ the x- axis

one

the area of every density curve is always

the normal distribution

an example of a density curve

normalcdf

When we have normal models and we have z-scores, we can find the probability using

(lower bound, upper bound, mew, sigma)

normalcdf formula is

inversenorm

When you have percentages, percentile ranks, or probabilities and you want to find a z-score or critical z-statistic, then use

(area below, mew, sigma)

formula for inversenorm

subtract the percentage from 100 and then use inversenorm

Your calculator cannot find a z-score when given the top percentage of something (ie. top 5%, top 10%, etc.). You must first

a trial

is a sequence of events that we want to investigate that leads to an outcome

the law of large numbers

looks at long term behavior and says that as the number of trials increase, the repeated trials get closer and closer to the actual probability of the event

a simulation

can be used to imitate behavior and is often used to model long term behavior

simulation steps

1. Start at the beginning of a random number table and move left to right

2. Look at digits 1 at a time, 2 at a time, 3 at a time, etc. depending on the context of the question

3. Discuss how the numbers are assigned

4. Discuss if any numbers should be ignored

5. Discuss whether repeated numbers in a given trial should be ignored

6. Explain when to stop

7. Explain what to do now that the values have been selected

sample space

is the collection of all possible outcomes and is denoted with the letter S

outcome/event

The result or value of the trial is called an

same probability of happening

For equally likely outcomes, every outcome in the sample space has the

zero to one

Probability is always a number from

one

If you add all of the probabilities in a sample space, your sum will always be

complement of a

The probability that the set of outcomes are not in A is called the

1-P(A)

complement of A formula

disjoint events

are also called Mutually Exclusive events

disjoint/mutually exclusive events

can only be one thing or the other, there can be no overlap, they cannot occur at the same time