STA 2023 Final Exam, Top Question with
accurate answers, 100% Accurate, rated
A+
Population - ✔✔-A collection or set of individuals, objects or events whose properties are to be
analyzed.
Data is rarely collecte
...
STA 2023 Final Exam, Top Question with
accurate answers, 100% Accurate, rated
A+
Population - ✔✔-A collection or set of individuals, objects or events whose properties are to be
analyzed.
Data is rarely collected from the entire population - instead a representative sample is used
Sample - ✔✔-a subset of the population
Parameter - ✔✔-a numerical value summarizing all data of the population
statistic - ✔✔-a numerical value summarizing all data of the sample
Statistic or Parameter? A health club surveys 40 randomly selected members and found the avg weight
is 157 lbs - ✔✔-statistic
Statistic or parameter? A researcher examines records of all registered voters and finds 43% are
registered democrats - ✔✔-parameter
variable - ✔✔-characteristic of the individuals within the population or sample
qualitative - ✔✔-non-numerical characteristic
may or may not be numbers, but the numbers have no real meaning (e.g., SSN, eye color)
You cannot do any math with qualitative data (i.e., adding or subtracting SSNs doesn't give you anything
meaningful)
quantitative - ✔✔-numerical measurements in which the numbers have meaning.
You can compare the numbers and the comparison will make sense
Ex: fat content of different cookies
discrete data - ✔✔-whole numbers
countable
continuous data - ✔✔-non-count
What are the 4 levels of measurement? - ✔✔-1) Nominal
2) Ordinal
3) Interval
4) Ratio
nominal data - ✔✔-qualitative data ONLY
Cannot be ordered, cannot be used for calculations
Ex: eye color, SSN
Ordinal data - ✔✔-can be qualitative or quantitative
Data can be ordered, but there is no meaning placed on the order
Ex: if you are 5th in line, this doesn't mean you are 5 times better than the 1st person in line.
Interval data - ✔✔-Quantitative data
You can calculate differences between the data
Zero is NOT the starting point of the data, but it does contain zero, but it is NOT a true zero (e.g., 0
degrees F does not mean there is no heat at all)
Begin to see meaning in data b/c you are able to subract
Ex: IQ - there is a meaningful difference between an IQ of 109 and 110.
Ex 2: temperature
Ratio - ✔✔-Interval data PLUS you can form ratios, so you can express one point as a multiple of
another, i.e., you can DIVIDE the data
Ratio data starts at zero - there are NO negatives.
Ex: fat contents of cookies. You can divide to show that cookie B has twice the fat of cookie A
Quant or Qual? Nominal, Ordinal, interval or ratio? Temperatures of ocean at various depths - ✔✔-
quantitative, interval
Quant or Qual? Nominal, Ordinal, interval or ratio? The subjects in which college students major - ✔✔-
Qualitative, nominal
Quant or Qual? Nominal, Ordinal, interval or ratio? Salaries of college Profs - ✔✔-Quantitative, ratio
Quant or Qual? Nominal, Ordinal, interval or ratio? Survey responses of "good, better, best" - ✔✔-
Qualitative, ordinal (sequential order)
random sample - ✔✔-n measurements selected so that every member from the population has an equal
probability of being selected
simple random sample - ✔✔-n subjects selected in a way that every possible sample of the sample size
has the same chance of being chosen.
stratified sampling - ✔✔-groups or classes within population share common a common characteristic
called "strata".
Ex: in undergrad population, you may divide into freshmen, sophomores, etc.
THEN SRS is drawn from each stratum
systematic sampling - ✔✔-All elements of population arranged in some natural sequential order
Then random starting point selected and every kth element selected for the sample
cluster sampling - ✔✔-divide demographic area into sections
then randomly select some sections or clusters
every member of the cluster is included in the sample
frequency distribution - ✔✔-a table that displays data broken into natural groups, called classes
frequency - ✔✔-f - the number of times a value appears in data
relative frequency - ✔✔-f/n
cumulative frequency - ✔✔-the sum of frequencies for that class and all previous classes
Can be given as a decimal, fraction, or percent
Cumulative freqs of all classes should add up to 1
class width - ✔✔-(max-min)/# of classes
**Always round UP**
lower class limits - ✔✔-use min for first lower class limit
Then add class width to first lower class limit to get next lower class limit
class boundaries - ✔✔-(first upper class limit + next lower class limit) / 2
then subract answer from every lower class limit
Add answer to every upper class limit
class midpoint - ✔✔-(lower class limit + upper class limit) / 2
histograpm - ✔✔-y axis = frequency
x axis = class boundaries
NO gaps between bars - bars connected
frequency polygon - ✔✔-displays frequency and class midpoints
midpoints are connected by line segments
Ex: see ch. 2 notes p. 3
ogive - ✔✔-line graph that shows cumulative frequency
stem and leaf plot - ✔✔-shows raw data
normal distribution - ✔✔-bell-shaped curve
mean=median=mode
frequency distribution is symmetric
uniform - ✔✔-all entries (classes) have the same frequency, so there's a straight line across the graph
skewed - ✔✔-there is an elongated tail on one side
left (negatively) skewed - ✔✔-long tail is to left
right (positively) skewed - ✔✔-long tail is to right
What are the measures of Central Tendency? Aka measures of center - ✔✔-1) mean
2) median
3) mode
mean - ✔✔-average (sample mean (x-bar) or population mean (mu)
NOT resistant to outliers
median - ✔✔-physical middle of the data
resistant to outliers
to find, put data in order
then, calculate (n+1) / 2 to find the POSITION of the median
Then locate that position
**if you have an even number of values, take the average of the 2 middle values**
mode - ✔✔-the number that shows up most frequently
weighted mean - ✔✔-x-bar=∑(x×w) / ∑w
w is the "weight"
sample variance or sample standard deviation for grouped data - ✔✔-grouped data = frequency table
format
use class midpoint for x
empirical rule - ✔✔-used with frequency distributions that have a symmetric bell shape
1) 68% of data will lie within 1 stand dev of mean (x-bar - s)
2) 95% of data will lie within 2 stand devs of mean (x-bar - 2s)
3) 99.7% of data will be within 3 stand devs of mean (x-bar - 3s)
fractiles - ✔✔-numbers that partition/divide an ordered data set itno equal parts
Ex: median is fractile b/c it divides ordered data set into two equal parts
percentile - ✔✔-the pth percetile is a value representing that AT LEAST p% of data is at or BELOW it
divides data set into 100 equal parts
How to find percentile? - ✔✔-list your data in INCREASING order
then use a location formula: L = n × p/100
**if L is a whole number, average it with next higher one**
***If L is NOT whole, round UP for location of percentile***
Then find location
3 quartiles divide ordered data set into 3 equal parts - ✔✔-Q₁= P25
Q₂= P50
Q₃= P75
Inner Quartile Range - ✔✔-= IQR
The difference between Q3 and Q1 (IQR = Q3-Q1)
**Any data value that is more than 1.5 IQRs to left or Q1 or 1.5 IQRs right of Q3 is an outlier**
How to create a boxplot? - ✔✔-1. put data in order
2. Get 5-number summary: min, Q1, Q2, Q3, max
3. make a box with Q1, Q2, Q3
4. mark min and max with dots and connect to box
Modified boxplot - ✔✔-for a modified boxplot, include outliers as points, but do not connect to line or
box
range rule of thumb - ✔✔-the majority of sample values (≈95% for instance) lie within 2 standard devs
of the mean
**so, if something doesn't fall within two standard devs of the mean, it is UNUSUAL**
what does standard deviation measure? - ✔✔-the average variation of all values from the mean
it is usually positive
only 0 when all numbers are the same
never negative
outliers can dramatically affect it
how would you *estimate* standard deviation (ch. 3) - ✔✔-s ≈ range / 4 (ch. 3 p. 104)
z-score - ✔✔-aka standardized value = number of standard deviations a given value x is above or below
the mean
**when a data value is less than the mean, its z-score is negative**
Sample z-score:
z= (x - x-bar) / s
Population z-score
z= (x - Mu) / sigma
round to 2 decimal places
unusual values (z-scores) - ✔✔-unusual values have z scores less than -2 or greater than 2
Ordinary: -2 ≤ z-score ≤ 2
Unusual: z-score < -2 or z-score >
[Show More]