Data Fundamentals, Unit 1

Powerpoint only, not including Webassign Examples

The statistical problem-solving process

Formulate questions - Collect Data - Analyze Data - Interpret Results

Research Question

Broad, ongoing investigation with multiple aspects, e.g. How can a company increase sales?

Statistical Question

Can be answered directly by analyzing a relevant data set, e.g. What is the average salary of people with an MBA?

A statistical question has what characteristics?

• Can be answered directly using an appropriate dataset

• Multiple analysts using the same dataset would get the same answer (That is, not subjective)

If a statistical question involves two or more variables :

The __ is what we would like to predict

The __ variables are used to calculate these predictions

Response

Explanatory

Example :

Response Variable : amount spent by online customers

Possibly Explanatory Variables : Gender, Age, Geographic location

How are data tables usually organized?

With cases in the rows, and the variables in the columns (structured data)

The rows of a data table correspond to

cases

• If we have several measurements for an item, this item is a case and should have it’s own row.

The measurements recorded about items are called ___ and are shown in the __ of the data table

variables, column

The first column is the __, which is used to identify individual cases uniquely and is not considered a variable

Identifier

Quantitative Variable

tells us how much of something was measured and quantifies exactly how far apart individual items are.

It is possible to compute an average value. WE SHOULD BE ABLE TO COMPUTE THE AVERAGE VALUE FOR A QUANTITATIVE VARIABLE.

Categorical Variable

has separate distinct categories. It is not possible to specify exactly how far apart 2 items are, nor do mathematical operations such as compute the average.

Identifier

A unique code assigned to each individual or item, listed in the first column of the data table. It could be a name, or an alpha-numeric code.

Example : Social Security Numbers

Identifiers have similar characteristics as categorical variables in that they can’t be added or averaged, but they are NOT ANALYZED.

Data that consist of the same item measured repeatedly are called

time series

To qualify as time series, we should be able to plot the data with

a line plot with time on the X-Axis

Data that is measured only once is called

cross-sectional - Only measured at one specific point in time, and not ongoing.