Univariate anaylsis: what is needed in order to tell a good story

summary of statistics including mean, median, stdev, quartiles, etc...

Univariate analysis: What is Stratified sampling

categorized sampling based off shared characteristics

500 cities: why do we add weightings to dimensions and indicators?

to prioritize more important variables

Probability: mutually exclusive events...

are events that don't occur at the same time

Me and the bees: Why did we have to CLEAN the Me and the Bees data?

to create 1 spreadsheet with all months for easy comparison of variables.

Me and the bees: what does a discussion of findings entail?

Brings analysis and synthesis of the data

Probability: independent variables...

do not change the probability that another event will occur

Univariate anaylsis: In an analysis why should you talk about the measure of center and the measure of spread?

emphasize the distribution and the variability of the data.

500 cities: what does min max normalization do?

puts each indicator on the same scale of 0-1

Univariate anaylsis: What does it mean about the data if there’s a skew?

there is an apparent point on the y axis

Bivariate: What do residuals tell you

The distance between the actual point and the LSRL

Bivariate: r2=.95, what does this tell you?

95% of the variation in y can be explained by the variation of x

studbud

Data science quiz game

21 termsStudBud Administration

Imported from external platform

Flashcards21 cardsFPractice quizPHost liveL

Questions 21

Answers

1
Bivariate: What does this graph on avg temp vs water usage tell you?
The there isn't a strong correlation between water usage and avg temp
There is a positive association
the line of best fit is y=4033.08x+-34488.74
All of the above
2
Univariate anaylsis: what is needed in order to tell a good story
summary of statistics including mean, median, stdev, quartiles, etc...
emotionally charged graphs
a connection to the real world
analysis of a section of the data
3
Univariate analysis: What is Stratified sampling
Every nth term is selected after a selected start
categorized sampling based off shared characteristics
Dividing the population into subgroups and randomly selecting from each
Every member of the population has an equal chance of being selected
4
500 cities: why do we add weightings to dimensions and indicators?
to make the results look more complex
To hide over simplified dimensions
to prioritize more important variables
to eliminate outliers
5
Bivariate: what is the correlation between an increase of ice cream sales and an increase of drowning cases?
spurious confounding
causal mediating
causal direct
spurious confounding
6
Probability: mutually exclusive events...
cannot occur at the same time, but they can still be related in some ways.
always add up to 1
are events that don't occur at the same time
have all events in common
7
500 cities: what does reverse coding do?
finds the median
creates a weighted variable
prioritizes higher numbers
prioritizes lower numbers
8
Me and the bees: Why did we have to CLEAN the Me and the Bees data?
all of the above
to create 1 spreadsheet with all months for easy comparison of variables.
To make the months in chronological order
To delete what ever we didn't want
9
500 cities: what is the normalization equation?
(value-min/value-max)
(value-max/value-min)
(value-max)/(value-mix)
(value-min)/(max-min)
10
Me and the bees: what does a discussion of findings entail?
A list of conclusions
Provides context for the report
Gives the overall objective of the report
Brings analysis and synthesis of the data
11
UV: A researcher posts a survey on Spotify to identify who most popular artist is, what biases may this introduce?
non response bias
recall bias
selection bias
volunteer bias
12
Probability: independent variables...
do not change the probability that another event will occur
change the probability that another event will occur
are events that don't occur at the same time
are events that occur at the same time
13
Univariate anaylsis: In an analysis why should you talk about the measure of center and the measure of spread?
emphasize the distribution and the variability of the data.
it’s mandatory for every analysis
to just add numbers
they paint a full story
14
500 cities: what does min max normalization do?
puts each dimension on the same scale of 0-1
puts each dimension on the same scale of 0-100
puts each indecator on the same scale of 0-100
puts each indicator on the same scale of 0-1
15
Univariate anaylsis: What does it mean about the data if there’s a skew?
there is an apparent point on the y axis
all of the above
there is an apparent point on the x axis
16
Bivariate: who is the master cube grabber (answer is obvious)
Sienna Souza
Ella smith
Spencer young
Aleece Cluer
17
Bivariate: What does LSRL mean
All of the above
Least squares regression line
Line of best fit
Linear regression line
18
Bivariate: What do residuals tell you
water usage
The distance between the actual point and the LSRL
the percentage of the variants that y is explained by x
the line of best fit
19
Bivariate: r²=.95, what does this tell you?
94% of y can be explained by x
95% of x can be explained by the y
94% of the variation in x can be explained by the variation of y
95% of the variation in y can be explained by the variation of x
20
Probability: which conditional probability explains the probability of yes heart disease given no coffee
HD|Cc
P(HD|C)
P(HD|Cc)
HD|C
21
Me and the bees: What does a good business report include?
All of the above
a simplified conclusion
recommendations based off the conclusions
an explaination of thinking

Data science quiz game Flashcards | StudBud