Quant. Analytics – Chapter 1

Business analytics 

combines quantitative reasoning with quantitative tools to identify key business problems and translate data analysis into action that improve business performance. 

descriptive analytics

“what has happened?” 

predictive analytics

what could happen in the future?

prescriptive analytics

“what should we do?”

Data

 Compilations of facts, figures, or other contents, both numerical and nonnumerical.

Population

Data in a statistical problem that consists of all items of interest. 

Sample

a subset of the population that is used for the analysis. We rely on this because

(1) it is impossible to examine every member of the population and

(2) obtaining information on the entire population is expensive. 

Statistic

a number that describes a characteristic of a sample from that population.  

Parameter

a number describing a characteristic of a whole population

Cross-sectional data

Data is collected by recording a characteristic of many subjects at the same point in time.

• example: Go to www.zillow.com and find the sale price of 20 single-family homes sold in Las Vegas in the last 30 days. Structure the data including the sale price, the number of bedrooms, the square footage, and the age of the house.

Time series data

Data is collected over several time periods, focusing on certain groups of people, events or objects.

• ex: Find Under Armour’s annual revenue from the past 10 years.

Structured data

 data with pre-defined, row-column format. uses spreadsheet or database applications.

Unstructured data

data that does not conform to a pre-defined, row-column format, textual, multimedia content, and does not conform to database structures—human or machine-generated data like email (human) or camera images (machine). 

Big data

Extremely large datasets that can be analyzed for insights

1. volume: immense amount of data

2. velocity: generated at rapid speed

3. variety: all types of data, including structured and unstructured

Variable

a characteristic of interest that differs in kind or degree among various observations (records). 

Categorical

qualitative; uses labels or names to identify characteristics.

example: marital status. 

Numerical

quantitative; represent meaningful numbers, arithmetic operations are meaningful. example: number of children in a family 

Discrete

numerical variable; assumes a countable number of values.

• for example, we may observe values such as 3 children in a family but we will not observe fractions such as 1.31 children. 

Continuous

numerical variable; characterized by uncountable values within an interval.

• for example, an unlimited number of values occur between the weights of 100 and 101 pounds (like 100.03, 100.4, 100.05, etc). 

• more examples: Weight, height, time, and investment return

Nominal

categorical measurement; the observations differ merely by name or label.

example: marital status, gender

ordianal

categorical measurement; but able to both categorize and rank them with respect to some characteristic or trait.

example: ratings on a scale (excellent to poor, ranking 1 to 5)

Interval

able to categorize, rank, and find meaningful differences between them. ex: temperature

• zero value does not reflect the absence of characteristic 

• ratios are not meaningful

• for example: temperature where 0 degrees does not mean no temperature or time on a clock where 0 seconds does not mean no time

Ratio

the strongest level of measurement. has the characteristics of the interval scale but with a true zero point. ex: profits 

• a true zero point that reflects the absence of characteristic 

• ratios are meaningful

• for example: income where $0 means no income or age where 0 years old means no age

Fixed width format

each column starts and ends at the same place in every row.Every observation or record has the exact same column widths

Delimited format

each piece of data is separated by a comma. the comma is called a delimiter. a comma-separated value file does not limit text to only eight characters. 

1. eXtensible markup language (XML)

2. HyperText Markup Language (HTML)

3. JavaScript Object Notation (JSON)

Three widely used markup languages to provide structure to data.