Organizing, Visualizing, and Describing Data

Question 1

Data (Definition)

Answer 1

a collection of numbers, characters, words, text that represent FACTS or INFORMATION but NOT KNOWLEDGE (but analysis and interpretation on the facts and information develops knowledge)

Question 2

What are the two main types of Data?

Answer 2

Numerical (quantitative) and Categorical (qualitative)

Question 3

What is the definition of Categorical data?

Answer 3

Values that describe a quality or characteristic (mutually exclusive labels or groups)

Question 4

What are the two types of Categorical data types?

Answer 4

Nominal and Ordinal

Question 5

What is the definition of nominal data?

Answer 5

No logical order (e.g. sectors of the economy)

Question 6

What is the definition of ordinal data?

Answer 6

Has logical order or rank (note that there is no information in the distance between groups)

Question 7

What is the definition of Numerical data?

Answer 7

data that is measured or counted quantities

Question 8

What are the two types of Numerical data?

Answer 8

Integer/Discrete - limited to a finite number of values (number of people)
Ratio/Continous - can take on any value within a range

Question 9

What does NOIR stand for and how does it related to data types?

Answer 9

Nominal
Ordinal
Integer/Discrete
Ratio/Continuous

Question 10

Define variable

Answer 10

a particular quality or characteristic (Stock price, height)

Question 11

Define observation

Answer 11

a value of a specific variable (GM $53.30 and Trish is 5’9”)

Question 12

Define cross-sectional data

Answer 12

multiple observations of a particular variable (the stock price of 60 companies)

Question 13

Define time series

Answer 13

multiple observations of a particular variable for the same observational unit overtime // one unit and multiple observations (GM’s stock price over the last 60 months)

Question 14

Define panel data set

Answer 14

cross-sectional and time-series combined

Question 15

Define structured data

Answer 15

Highly organized in a pre-defined manner (stock prices, returns, EPS)

Question 16

Define unstrucuture data

Answer 16

no organized form (news, social media post, company filings, audio/video)

Question 17

Define absolute frequency

Answer 17

the actual count of observations per value of the variable

Question 18

Define relative frequency

Answer 18

Percentage of observations per value of the variable which is the absolute frequency divided by total N)

Question 19

How to create non-overlapping bins

Answer 19

Sort data in ascending order
Find the range: max-min
Decided on the number of intervals (which is K)
Calculate the interval width by dividing the range by k (always round up)
Add the internal to the first value and so on

Question 20

What is a Contingency table

Answer 20

it’s a table that summarizes data for 2 or more categorical variables (helps visually find patterns)

Question 21

What does a histogram or frequency polygon show?

Answer 21

represents the distribution of numerical data (y-axis shows frequency and x-axis shows intervals/values)

Question 22

What does a bar chart show?

Answer 22

Represent the frequency distribution of categorical data

Question 23

What does a tree map show

Answer 23

a set of coloured rectangles to represent groups

Question 24

What is a line chart used for?

Answer 24

Used to visualize ordered observations
Typically used for time series data
Facilitates showing changes and underlying trends

Question 25

What is a scatter plot used for?

Answer 25

Used to visualize the joint variation in 2 numerical values

Question 26

What is a heat map?

Answer 26

It is a contingency table with color-coded cells

It can also be used to visualize the degree of correlation among different variables

Question 27

Define “measures of central tendency”

Answer 27

Measures of central tendency specify where data are centered (arithmetic mean, median, mode, weighted mean, geometric mean, harmonic mean)

Question 28

Define “measures of location”

Answer 28

they are deciles, quantiles, quintiles

Question 29

Define median

Answer 29

Median is the middlemost value of a set of observations.
It is not affected by extreme values (i.e. outliers).
It is useful for describing the central tendency for a non-symmetrical distribtuion.
If the distribution is perfectly symetrical, then the mean equals the median.

Question 30

How do you calculate median?

Answer 30

For an even number of observations: (n+1)/2

For an odd number of observations: (n/2 + ((n+2)/2) )/ 2

Question 31

Define mode

Answer 31

The most frequently occurring value in a distribution
When there is no mode, then the observations are uniformly distributed.
This is the only measure of central tendency that can be used with nominal data

Question 32

When is geometric mean used?

Answer 32

Used with rates of change over time or to compute growth rates

Question 33

Is the arithmetic mean always greater than the geometric mean?

Answer 33

Yes

Question 34

What is the formula for geometric mean?

Answer 34

( ( (1 + R1) x (1 + R2) x (1 + R3) ) ^ (1 / N) ) - 1

Question 35

How are geometric mean and arithmetic mean related?

Answer 35

Xg = Xa - Variance/2

Question 36

What is an advantage of the harmonic mean?

Answer 36

It gives much less weight to outliers

Question 37

What is it appropriate to use the harmonic mean?

Answer 37

It is appropriate for averaging ratios when the ratios are repeatedly applied to a fixed quantity to yield a variable number of units (i.e. dollar-cost averaging)

Question 38

What is the formula for harmonic mean?

Answer 38

n / sum of all (1 / Xi)
n = number of observations and
Xi = the specific value for each observation.