FINANCIAL ECONOMICS AND QUANTITATIVE METHODS
Lecture 1
→ follow slides, readings a bit less important
Usefulness of the course: guide policy, forecasting, causal inference, evaluating policy ⇒ learn how
to answer these questions [learn how to learn from data]
>> observing, analysing, draw conclusions
⇒ attend lectures, no need to take notes unless mentioned, follow what is going on → 30 min after
lecture to verify we understand. Solve issues before tutorial
Cluster sampling: cluster as the actual unit of analysis?
1. Introduction to Statistics: Data collection and Sampling, descriptive statistics
● What is statistics: way to get information from data
○ Descriptive statistics: methods of organising, summarising and presenting data in
convenient and informative way (through graphs or numerical techniques)
○ Inferential statistics: methods to draw conclusions about characteristics of populations
based on sample data
○ Key statistical concepts:
■ Population: group of all items of interests
Parameter: descriptive measure of a population
■ Sample: set of data drawn from the studied population
Statistic: descriptive measure of a sample
■ Statistical inference: process of making an estimate, prediction or decision
about a population based on sample data
⇒ confidence level (proportion of times that estimate will be correct) and
significance level (how frequently the conclusion will be wrong)
○ Statistical applications in business: show statistics in functional areas of business
→ financial analyst’s use of probability to construct portfolios that decrease risk
○ Large real data sets: to do statistics at the same time as learning
→ General social survey (GSS) and American national election survey (ANES)
● Graphical descriptive techniques I:
○ Types of data and information:
■ Variables: some characteristic of a population or sample
■ Values: possible observations of the variable
■ Data / datum: observed values of a variable
- Interval data: real numbers
→ all calculations valid, data as O or N
- Nominal / qualitative / categorical data: categories
, → only calculations based on frequency or percentage, not as O or N
- Ordinal data: nominal but values have a meaning, ordering matters
→ only calculations based on frequency or percentage, not as O or N
○ Describing a set of nominal data:
⇒ frequency distribution → through bar chart or pie chart
○ Describing the relationship between two nominal variables and comparing two or
more nominal data sets: cross-classification table of frequencies (table / pie or bar
chart)
● Graphical descriptive techniques II:
○ Graphical techniques to describe a set of interval data:
■ Histogram: powerful graphical technique to summarise interval data
→ determine number of class intervals (class interval widths)
■ Shapes of histograms:
- symmetry: identical when drawing line in middle
- skewness: positively when tail to the right, negatively when left
- number of modal classes1: unimodal, bimodal
- bell-shape: symmetric unimodal histogram
○ Describing time-series data: measures at successive points in time
⇒ Line chart: plot of the variable over time
○ Describing the relationship between two interval variables: scatter diagram
With dependent Y and independent X variables
- Linear relationship: if able to trace a line between the dots
- Direction / strength: when increasing when other does → positive
○ Art and science of graphical presentations:
■ Graphical excellence: techniques that are informative and concise
- concise and coherent, clearly understood by viewer, encouraging to
compare, substance of data, not distortion of what data actually is
■ Graphical integrity: >< graphical deception (without scale on one axis,
graph’s caption influencing, size distortions, pictograms)
● Numerical descriptive techniques:
○ Measure of central location:
■ Arithmetic mean (average):
■ Geometric mean:
■ Median: all observations in order and taking the middle number
■ Mode: observation occurring with greatest frequency
1
Class with largest number of observations
Lecture 1
→ follow slides, readings a bit less important
Usefulness of the course: guide policy, forecasting, causal inference, evaluating policy ⇒ learn how
to answer these questions [learn how to learn from data]
>> observing, analysing, draw conclusions
⇒ attend lectures, no need to take notes unless mentioned, follow what is going on → 30 min after
lecture to verify we understand. Solve issues before tutorial
Cluster sampling: cluster as the actual unit of analysis?
1. Introduction to Statistics: Data collection and Sampling, descriptive statistics
● What is statistics: way to get information from data
○ Descriptive statistics: methods of organising, summarising and presenting data in
convenient and informative way (through graphs or numerical techniques)
○ Inferential statistics: methods to draw conclusions about characteristics of populations
based on sample data
○ Key statistical concepts:
■ Population: group of all items of interests
Parameter: descriptive measure of a population
■ Sample: set of data drawn from the studied population
Statistic: descriptive measure of a sample
■ Statistical inference: process of making an estimate, prediction or decision
about a population based on sample data
⇒ confidence level (proportion of times that estimate will be correct) and
significance level (how frequently the conclusion will be wrong)
○ Statistical applications in business: show statistics in functional areas of business
→ financial analyst’s use of probability to construct portfolios that decrease risk
○ Large real data sets: to do statistics at the same time as learning
→ General social survey (GSS) and American national election survey (ANES)
● Graphical descriptive techniques I:
○ Types of data and information:
■ Variables: some characteristic of a population or sample
■ Values: possible observations of the variable
■ Data / datum: observed values of a variable
- Interval data: real numbers
→ all calculations valid, data as O or N
- Nominal / qualitative / categorical data: categories
, → only calculations based on frequency or percentage, not as O or N
- Ordinal data: nominal but values have a meaning, ordering matters
→ only calculations based on frequency or percentage, not as O or N
○ Describing a set of nominal data:
⇒ frequency distribution → through bar chart or pie chart
○ Describing the relationship between two nominal variables and comparing two or
more nominal data sets: cross-classification table of frequencies (table / pie or bar
chart)
● Graphical descriptive techniques II:
○ Graphical techniques to describe a set of interval data:
■ Histogram: powerful graphical technique to summarise interval data
→ determine number of class intervals (class interval widths)
■ Shapes of histograms:
- symmetry: identical when drawing line in middle
- skewness: positively when tail to the right, negatively when left
- number of modal classes1: unimodal, bimodal
- bell-shape: symmetric unimodal histogram
○ Describing time-series data: measures at successive points in time
⇒ Line chart: plot of the variable over time
○ Describing the relationship between two interval variables: scatter diagram
With dependent Y and independent X variables
- Linear relationship: if able to trace a line between the dots
- Direction / strength: when increasing when other does → positive
○ Art and science of graphical presentations:
■ Graphical excellence: techniques that are informative and concise
- concise and coherent, clearly understood by viewer, encouraging to
compare, substance of data, not distortion of what data actually is
■ Graphical integrity: >< graphical deception (without scale on one axis,
graph’s caption influencing, size distortions, pictograms)
● Numerical descriptive techniques:
○ Measure of central location:
■ Arithmetic mean (average):
■ Geometric mean:
■ Median: all observations in order and taking the middle number
■ Mode: observation occurring with greatest frequency
1
Class with largest number of observations
