C FA ® E x a m P r e p a r a t o r y P r o g r a m

Level 1 Batch 44 | 2023

Quantitative Methods 2
Organizing, Visualizing
and Describing Data
B I N U S F I N A N C I A L A N A LY S T A C A D E M Y P R O G R A M
A d a p t e d f r o m C FA ® In s t i t u t e C u r r i c u l u m L e v e l 1

LOS
A. identify and compare data types;
B. describe how data are organized for quantitative analysis;
C. interpret frequency and related distributions;
D. interpret a contingency table;
E. describe ways that data may be visualized and evaluate uses of specific visualizations;
F. describe how to select among visualization types;
G. calculate and interpret measures of central tendency;
H. evaluate alternative definitions of mean to address an investment problem;
I. calculate quantiles and interpret related visualizations;
J. calculate and interpret measures of dispersion;
K. calculate and interpret target downside deviation;
L. interpret skewness;
M. interpret kurtosis;
N. interpret correlation between two variables (refer to QM-3)

Adapted from CFA® Institute Curriculum Level 1

This presentation material is strictly for class discussion purpose only, and can not be used, copied
and distributed for other purposes.
 Data Types
Data can be defined as a collection of numbers, characters, words, and text—as well as images, audio, and
video—in a raw or organized format to represent facts or information.

From a statistical perspective, data can be classified as:

➢ Numerical data (or quantitative data) are values that represent measured or counted quantities as a number.

✓ Continuous data can be measured and can take on any numerical value in a specified range of values.
Eg. Actual amount of rainfall between 10 – 20 inches per month.

✓ Discrete data are numerical values that result from a counting process, and limited to a finite number of
values. Eg. Number of days it rains in a month.

➢ Categorical data (or qualitative data) are values that describe a quality or characteristic of a group of
observations and usually take only a limited number of values that are mutually exclusive.

✓ Nominal data are categorical values that have no particular or logical order. Eg.: GICS sectors – 10
Energy, 20 Industrial, etc.

✓ Ordinal data are categorical values that can be logically ordered or ranked. Eg.: Morningstar ratings for
investment funds.
Adapted from CFA® Institute Curriculum Level 1

Time Series, Cross-sectional & Panel

➢ Variable: characteristic or quantity that can be measured, counted, or categorized and is subject to change.
Eg. EPS.

➢ Observation: the value of a specific variable collected at a point in time or over a specified period of time. Eg.
EPS of $7.5.

➢ Time series data: a sequence of observations for a single observational unit of a specific variable collected
over time and at discrete and typically equally spaced intervals of time, such as daily, weekly, monthly,
annually, or quarterly. E.g. monthly Microsoft stock return for the past 5 years.

➢ Cross-sectional data: a list of the observations of a specific variable from multiple observational units at a
given point in time. E.g. Inflation rate for EU countries in January.

➢ Panel data consist of observations through time on one or more variables for multiple observational units. Eg.
Inflation rate in EU countries over 5 year periods.

➢ Longitudinal data consist of observations on characteristic(s) of the same observational unit through time.
Eg. Financial ratios of a company over 10 year periods.

Adapted from CFA® Institute Curriculum Level 1

This presentation material is strictly for class discussion purpose only, and can not be used, copied
and distributed for other purposes.
 Structured and Unstructured Data
• Based on whether or not data are in a highly organized form, data can be classified into structured
and unstructured types.

• Structured data are highly organized in a pre-defined manner, usually with repeating patterns.
Typical examples:
• Market data: issued by stock exchanges, e.g. closing stock price, volume.
• Fundamental data: eg. EPS, P/E ratio, dividend yield, ROE.
• Analytical data: derived from analytics, e.g. earnings growth estimate.

• Unstructured data do not follow any conventionally organized forms. Common types: text (eg.
Financial news, company fillings), audio/video (e.g. earnings call). They are typically alternative
data as they are usually collected from unconventional sources. Three group of sources:
• Individuals: social media posts, web searches
• Business process: credit card transaction, corporate fillings
• Sensors: satellite images, foot traffic by mobile devices

Adapted from CFA® Institute Curriculum Level 1

Organizing Data for Quantitative Analysis

• Raw data are usually not suitable for use directly for quantitative analysis and modelling.
• Raw data can be organized into two formats:
• one-dimensional array: simplest format, suitable to represent single variable. Eg. daily
closing stock price in past 10 days.
• two-dimensional rectangular array (or data table): one of most popular forms of data for
computer processing or visual data presentation for human. Eg. Quarterly financial data
(revenue, EPS, DPS) in the past 8 quarters.

Adapted from CFA® Institute Curriculum Level 1

This presentation material is strictly for class discussion purpose only, and can not be used, copied
and distributed for other purposes.
 Frequency Distribution
• Frequency distribution is a tabular display of data constructed by: counting the number of
observations of each unique value of a variable or counting values of numerical variable into a set
of intervals or range.

• Interval or bucket: set of return values in which an observation falls (all-inclusive, non overlapping,
and mutually exclusive)

• Interval is an easy method to see the frequency distribution of a data by looking at the number of
members in each group

• From a set of raw data, we can build a frequency distribution, relative frequency and cumulative
absolute/relative frequencies.

Adapted from CFA® Institute Curriculum Level 1

Frequency Distribution
Procedures to construct frequency distribution:

1. Define the interval or class

2. Tally the observations, assigned to appropriate interval

3. Count the observations that are assigned to each interval

Example: Annual return of stock XYZ

10.4% 22.5% 11.1% (12.4%)

9.8% 17.0% 2.8% 8.4%

34.6% (28.6%) 0.6% 5.0%

(17.6%) 5.6% 8.9% 40.4%

(1.0%) (4.2%) (5.2%) 21%

Adapted from CFA® Institute Curriculum Level 1

This presentation material is strictly for class discussion purpose only, and can not be used, copied
and distributed for other purposes.
 Relative Frequencies

Interval Frequency Relative Frequency

-30% ≤ R < -20% 1 5%
-20% ≤ R < -10% 2 10%
-10% ≤ R < 0% 3 15%
0% ≤ R < 10% 7 35%
10% ≤ R < 20% 3 15%
20% ≤ R < 30% 2 10%
30% ≤ R < 40% 1 5%
40% ≤ R < 50% 1 5%
Total 20 100%

Relative frequency is calculated by dividing the absolute frequency in each

return interval by the total no of observations

Adapted from CFA® Institute Curriculum Level 1

Cumulative Frequencies

Cummulative Cummulative
Relative
Interval Frequency Absolute Relative
Frequency
Frequency Frequency
Interval
R < -20%
-30% ≤ R < -20% 1 5% 1 5%
-20% ≤ R < -10% 2 10% 3 15% R < -10%
-10% ≤ R < 0% 3 15% 6 30% R < 0%
0% ≤ R < 10% 7 35% 13 65% R < 10%
10% ≤ R < 20% 3 15% 16 80% R < 20%
20% ≤ R < 30% 2 10% 18 90% R < 30%
30% ≤ R < 40% 1 5% 19 95% R < 40%
40% ≤ R < 50% 1 5% 20 100% R < 50%
Total 20 100%

Cumulative frequency is calculated by summing up the absolute or relative

frequency starting from the lowest interval and progress through the highest.

Adapted from CFA® Institute Curriculum Level 1

This presentation material is strictly for class discussion purpose only, and can not be used, copied
and distributed for other purposes.
 Contingency table
Contingency table: a tabular format that displays the frequency distributions of two or more
variables simultaneously; used for finding patterns between the variables. A contingency table for two
categorical variables is also known as a two-way table.

Joint frequency: joining a variable from the row (e.g. sector) and other variable from the column (e.g.
market cap) to count observations.

Marginal frequency: sum of added joint frequencies across rows and across columns.

One application of contingency tables is for evaluating the performance of a classification model
(using a confusion matrix). Another application of contingency tables is to investigate a potential
association between two categorical variables by performing a chi-square test of independence.

Adapted from CFA® Institute Curriculum Level 1

Example: 5x3 Contingency table

Adapted from CFA® Institute Curriculum Level 1

This presentation material is strictly for class discussion purpose only, and can not be used, copied
and distributed for other purposes.
 Contingency table
• One application of contingency tables is for evaluating the performance of a classification model
(using a confusion matrix). Example: Confusion matrix for bond default prediction model

• Another application of contingency tables is to investigate a potential association between two

categorical variables by performing a chi-square test of independence.

Adapted from CFA® Institute Curriculum Level 1

Data Visualization
Visualization: presentation of data in a graphical format to increase understanding and gaining
insights into the data. The key consideration when selecting among chart types is the intended
purpose of visualizing data (i.e. for exploring/presenting distributions or relationships or for making
comparisons).
• Histogram: a bar chart of data that are grouped into a frequency distribution. A frequency
polygon is a graph of frequency distributions obtained by drawing straight lines joining successive
midpoints of bars representing the class frequencies.
• Bar chart is used to plot the frequency distribution of data, with each bar representing a distinct
category and the bar’s height proportional to the frequency of the corresponding category. Grouped
bar charts or stacked bar charts can present the frequency distribution of multiple categorical
variables simultaneously.
• Tree-map: a graphical tool to display categorical data. It consists of a set of colored rectangles to
represent distinct groups, and the area of each rectangle is proportional to the value of the
corresponding group. Additional dimensions of categorical data can be displayed by nested
rectangles.
Adapted from CFA® Institute Curriculum Level 1

This presentation material is strictly for class discussion purpose only, and can not be used, copied
and distributed for other purposes.
 Example Data visualization
Histogram and Frequency Polygon Cummulative Frequency distribution

Bar Chart Tree map

Adapted from CFA® Institute Curriculum Level 1

Data Visualization (2)

• Word cloud: a visual device for representing textual data, with the size of each distinct word being
proportional to the frequency of appearance in the given text.
• Line chart: a type of graph used to visualize ordered observations and often to display the change
of data series over time. A bubble line chart is a special type of line chart that uses varying-sized
bubbles as data points to represent an additional dimension of data.
• Scatter plot: a type of graph for visualizing the joint variation in two numerical variables. It is
constructed by drawing dots to indicate the values of the two variables plotted against the
corresponding axes. A scatter plot matrix organizes scatter plots between pairs of variables into a
matrix format to inspect all pairwise relationships between more than two variables in one
combined visual.
• Heat map: a type of graphic that organizes and summarizes data in a tabular format and
represents it using a color spectrum. It is often used in displaying frequency distributions or
visualizing the degree of correlation among different variables.

Adapted from CFA® Institute Curriculum Level 1

This presentation material is strictly for class discussion purpose only, and can not be used, copied
and distributed for other purposes.
 Example Data visualization (2)
Line chart
Word cloud

Scatter plot Heat map

Adapted from CFA® Institute Curriculum Level 1

Selecting Visualization types

Adapted from CFA® Institute Curriculum Level 1

This presentation material is strictly for class discussion purpose only, and can not be used, copied
and distributed for other purposes.
 What is Statistics?
Statistics refers to data and the methods we use to analyze the data. There are 2 categories:

• Descriptive Statistics

How data can be summarized effectively to describe important aspects of large data set.
Consolidate data into useful information.

• Inferential Statistics

Procedures used to make forecasts, estimates, judgment about a large set of data on the basis
of the statistical characteristics of a smaller set (a sample)

Adapted from CFA® Institute Curriculum Level 1

Populations and Samples

Population
• Defined as all members of a specified group
• At most of the times, it is impossible to measure the exact number of the population
• E.g.: CFA L1 course participants

Sample
• Defined as portion, or subset of the population of interest which is taken to represent the
whole population
• E.g: This class is a sample of CFA L1 course participants

Parameter
• Some common statistical measures to describe the characteristics of the population
• Any descriptive measure of a population characteristics
• Although there are many parameters, only a few utilized. E.g. mean return, standard deviation
of returns
• 4 parameters in statistic: Central tendency, Dispersion, skewness, kurtosis.

Adapted from CFA® Institute Curriculum Level 1

This presentation material is strictly for class discussion purpose only, and can not be used, copied
and distributed for other purposes.
 Measures of Central Tendency
Measures of central tendency identifies the center or average of a data set. This central point
can be used to represent the typical or expected value in data set.

• Population Mean

• Sample Mean

• Weighted Mean

• Median

• Mode

• Arithmetic Mean

• Geometric Mean

• Quantiles

Adapted from CFA® Institute Curriculum Level 1

Mean
• Population mean, all observed values in the population are summed and divided by number of
observations in the population

 X i
= 
=
N

• Sample mean, all the values in a sample of a population is divided by the number of observations
in the sample

 X i
X= 
=
n

Adapted from CFA® Institute Curriculum Level 1

This presentation material is strictly for class discussion purpose only, and can not be used, copied
and distributed for other purposes.
 Example:
Stock of AXZ has annual return as follows:

12%, 25%, 34%, 15%, 19%, 44%, 54%, 33%, 22%, 28%, 17%, 24%

The researcher takes the sample of 5 most recent data.

Calculate population and sample mean

 = pop mean = 12 + 25 + 34 + 15 + 19 + 44 + 54 + 33 + 22 + 28 + 17 + 24

12

= 27.25%

X = sample mean = 25 + 34 + 19 + 54 + 17 = 29.8%

Adapted from CFA® Institute Curriculum Level 1

Arithmetic Mean
• Population mean and sample mean are example of arithmetic mean
• Arithmetic mean is the sum of observation value divided by the number of observations
• All interval and ratio data sets have an arithmetic mean
• A data set has only one arithmetic mean
• The sum of deviation of the data set from the mean is always zero
• Sum of mean deviations= (Xi – X) = 0

Annualized Return
Year (Xi – X)
1 • 30% +8% (30%-22%)
-10% (12%-22%)
2 • 2%
3 • 25% +3% (25%-22%)

4 • 20% -2% (20-22%)

5 +1% (23%-
• 23% 22%)
Mean 22% (Xi – X) = 0

Adapted from CFA® Institute Curriculum Level 1

This presentation material is strictly for class discussion purpose only, and can not be used, copied
and distributed for other purposes.
 Weighted Mean, Median, Mode
• Weighted Mean is the mean of the data based on the frequency/weight of each observation in comparison with the whole
dataset

Xw = wiXi = (w1X1 + w2X2 + … + wnXn) where wi =1

Example: A portfolio consists of 50% common stocks, 40% bonds, and 10% cash. If the return on common stocks is 12%, the
return on bonds is 7%, and the return on cash is 3%, what is the return of the portfolio?

Xw = w iXi = (w stockXstock + w bondsXbonds + w cashXcash)

Xw = (0.5 X 0.12) + (0.4 X 0.07) + (0.1 X 0.03) = 9.1%

• Median: The midpoint of the data when it arranged from the largest to the smallest values

Example: What is the median of this data of 30, 25, 23, 21, 15?

23 is the median

What is the median of this data of 30, 28, 25, 23, 21, 15?

0.5 (25 + 23) = 24

• Mode: The value of the observation that appears most frequently

Example: What is the modus of this data of 30, 28, 25, 23, 28, 21, 15, 5

28 is the modus.

Adapted from CFA® Institute Curriculum Level 1

Geometric Mean
Geometric mean is often used when calculating investment returns over multiple periods or to find
compound Annual growth rate (CAGR)

Geometric mean always be less than or equal to the arithmetic mean

Geometric Return is standard method for return calculation

Formula:

1 + RG = N√((1 + R1) X (1 + R2) X… X (1 + Rn))

Example: for the last 3 years the return for Acme Corp common stock have been -9.34%, 23.45%
and 8.92%. What is the compound annual rate of return for 3 years?

1 + RG = 3√((1 – 0.0934) X (1 + 0.2345) X (1 + 0.0892 )) = 3√1.21903 = 1.06825 – 1 = 6.825%

Adapted from CFA® Institute Curriculum Level 1

This presentation material is strictly for class discussion purpose only, and can not be used, copied
and distributed for other purposes.
 Harmonic Mean
Used to describe certain computation, such as average cost of shares purchased over time
Calculated as : _N_
1 / Xi

where, N is the number of observations

Xi is the value of each observation

Example: An investor purchases $100 of stock each month for 3 months. The purchase price
for each month is $8, 9, 10. Calculate average cost

Average cost = _3 = $8.926 per shares

1/8 +1/9 +1/10
Cross check:
Total Shares purchased : (100/8)+(100/9)+(100/10) = 33.61 shares
Average cost of shares purchased : 300/33.61 = $8.926 per shares

Adapted from CFA® Institute Curriculum Level 1

Quantiles
General term for value at or below which a stated fraction of data lies. Examples:

• Quartiles –distribution is divided into quarters

• Quintile –distribution is divided into fifths

• Decile –distribution is divided into tenths

• Percentile –distribution is divided into hundredths (percent)

Formula used to identify a position of the observation at a given percentile: Ly = (n + 1) y/100

Example: Find the 3rd quartile of the observations lie below for the following distribution of returns:

8%, 10%, 12%, 13%, 15%, 17%, 17%, 18%, 19%, 23%, 24% (11 observations)

Ly = (11 + 1) X 75/100 = 9

The third quarter is 19%

Adapted from CFA® Institute Curriculum Level 1

This presentation material is strictly for class discussion purpose only, and can not be used, copied
and distributed for other purposes.
 Measures of Dispersion
Dispersion is variability around the central tendency. Tradeoff between reward of
variability, the central tendency (mean) is the reward whereas dispersion is the risk.

Range = Max. value – Min. value

Mean Absolute deviation (MAD) is the average of the absolute values of the deviations
of individual observations from the arithmetic mean.

Example: Annualized returns are: 30%, 12%, 25%, 20% 23%

Mean = (30 + 12 + 25 + 20 + 23) / 5 = 22%
MAD = [30 - 22 + 12 - 22 + 25 - 22+20 - 22 + 23 - 22]
5
= 24 / 5 = 4.8%

Adapted from CFA® Institute Curriculum Level 1

Measures of Dispersion

• σ = 5.97%

Adapted from CFA® Institute Curriculum Level 1

This presentation material is strictly for class discussion purpose only, and can not be used, copied
and distributed for other purposes.
 Dispersion from The Mean

Annualized
Year
Return
1 • 30%

2 • 12%

3 • 25%
4 • 20%

5 • 23%

Mean 22%

MAD and Standard Deviation measures the average dispersion of each data
from the mean. The more dispersed the data plots from the mean, the predictive
value of mean is weaker vice versa

Adapted from CFA® Institute Curriculum Level 1

Measures of Dispersion

Example:
Suppose that in the average score in CFA test is a 70 with standard deviation of 4 points.
At least what percent of the tests have a grade of at least 62 and at most 78?
Answer: 75%
Adapted from CFA® Institute Curriculum Level 1

This presentation material is strictly for class discussion purpose only, and can not be used, copied
and distributed for other purposes.
 Target Downside Deviation
• Variance and standard deviation of returns take account of returns above and below the mean respectively.
However, investors are typically concerned only with downside risk—for example, returns below the mean or
below some specified minimum target return.

• Target downside deviation or target semideviation: measure of dispersion of the observations below the
target. Steps:

1. Specify the target (B)

2. Identify observations below target

3. Find the sum of the squared negative deviation from target

4. Divide that sum by total number of observations (n) minus 1.

5. Take square root.

• Formula:

Adapted from CFA® Institute Curriculum Level 1

Example Target Downside Deviation

Target Semideviation = (84/11)^(0.5) = 2.7634%

Adapted from CFA® Institute Curriculum Level 1

This presentation material is strictly for class discussion purpose only, and can not be used, copied
and distributed for other purposes.
 Coefficient of Variation (CV)

Adapted from CFA® Institute Curriculum Level 1

Symmetric Distribution
• Distribution is the graphical depiction of the collection of all the possible results of the observations

• Symmetric Distribution means the data distribution at the left part is the same as the right part
and the mean is located at the centre at the distribution.

zero skewness mode = median = mean

Adapted from CFA® Institute Curriculum Level 1

This presentation material is strictly for class discussion purpose only, and can not be used, copied
and distributed for other purposes.
 Skewness
• Skewness: the distribution is not symmetrical. Can be positively or negatively skewed and result
from outliers in the data

• Outliers are observations with extraordinarily large (extreme) values, either positive or negative

• Positively skewed distribution has many outliers in the upper region or right tail

• Negatively skewed distribution has many outliers in the lower region or left tail

Positively skewed Negatively skewed

M M
e e
a a
n n

Adapted from CFA® Institute Curriculum Level 1

Mean, Median and Mode for Distributions

• For symmetrical distribution, mean, median and mode are equal.
• Mean can be easily moved by a few large outliers
• Mode will not move easily because the outliers are relatively few
• Median moves more than mode but lesser than mean

Symmetrical Positive skewness Negative skewness

Mean M M M M M M
Median o e e e e o
Mode d d a a d d
e i n n i e
a a
n n
Mean > Median > Mode Mean < Median < Mode

Adapted from CFA® Institute Curriculum Level 1

This presentation material is strictly for class discussion purpose only, and can not be used, copied
and distributed for other purposes.
 Kurtosis
• Kurtosis is a measure of the degree to which a distribution is more or less peaked than a normal
distribution(mesokurtic)

• Leptokurtic (fat-tailed) is a distribution that is more peaked than a normal distribution.

• Platykurtic (thin-tailed) is a distribution that is less peaked or flatter than a normal distribution

• Kurtosis for normal distribution is 3. Leptokurtic has more than 3 kurtosis.

• Leptokurtic data has more data near the central but bigger tails, implying conditions common in stock market
where most daily returns fall in relatively tight range but sometimes large movement do occur, creating outliers.

Adapted from CFA® Institute Curriculum Level 1

Measures of Sample Skew and Kurtosis

Adapted from CFA® Institute Curriculum Level 1

This presentation material is strictly for class discussion purpose only, and can not be used, copied
and distributed for other purposes.
 Example: IHSG negatively skewed

Parameters

Range/ Interval

Adapted from CFA® Institute Curriculum Level 1

Example

25
IHSG monthly return (Jan 2011 - Jun 2022)

20
Frequency

15

10

Return
Parameter
Mean 0.5%
St dev 4.0%
skewness -1.01
Kurtosis 2.03
Adapted from CFA® Institute Curriculum Level 1

This presentation material is strictly for class discussion purpose only, and can not be used, copied
and distributed for other purposes.
 Risk and Return Tradeoff

Adapted from CFA® Institute Curriculum Level 1

Exercise (Untuk latihan dibahas bersama)

The annual return for XYZ stock were 15%, 19%, -8%, 14%
What is the geometric mean return?
A. 9.45% → ((1+0.15)(1+0.19)(1-0.08)(1+0.14))^(1/4)
B. 10.00%
C. 14.21%

Example:
IHSG in 31 dec 2010: 3703
IHSG in 30 June 2022: 6911
CAGR (Compounding Annual growth rate)?
(6911/3703)^(1/11.5) = 5.6%

Adapted from CFA® Institute Curriculum Level 1

This presentation material is strictly for class discussion purpose only, and can not be used, copied
and distributed for other purposes.
 Exercise (Untuk latihan dibahas bersama)
Which of the following is most accurate regarding a distribution of returns that has a mean greater
than its median?

A. It is positively skewed

B. It is a symmetric distribution

C. It is negatively skewed

The intervals in a frequency distribution should always have which of the following characteristics?

A. Be truncated

B. Be open ended

C. Be non overlapping

Adapted from CFA® Institute Curriculum Level 1

References
• Drake, Pamela Peterson, PhD, CFA, and Jian Wu, PhD, “Organizing, Visualizing, and Describing Data”, CFA Program

Curriculum 2022 Level 1. CFA Institute, 2020.

• SchweserNotes for the CFA Exam Level 1: CFA Program Exam Prep. Kaplan, Inc., 2018.

Adapted from CFA® Institute Curriculum Level 1

This presentation material is strictly for class discussion purpose only, and can not be used, copied
and distributed for other purposes.
 @binus_executive_education BINUS Executive Education bbs.binus.ac.id/exed

This presentation material is strictly for class discussion purpose only, and can not be used, copied
and distributed for other purposes.