Data evaluation: Feature engineering
Give this one a try later!
Aggregation - unit of analysis
Recoding - disambiguation
Indicator creation
A one-tailed test of significance
Give this one a try later!
, used to test the hypothesis that X > Y (or X < Y)
= to saying that X is larger (or smaller) than Y
You are testing for the possibility of the relationship in one direction and
completely disregarding the possibility of a relationship in the other
direction.
Data evaluation: Exploration - bivariate
Give this one a try later!
Associations - categorical & continuous
Differences & tests of significance
Type I error (α)
Give this one a try later!
Incorrectly concluding that there is a difference
- you reject null hypothesis when it is actually true
e.g. woman told pregnant when she is not
First party data
Give this one a try later!
, First party data is the information you collect directly from your audience
or customers.
Key elements of Data Exploration (4)
Give this one a try later!
Benchmarking:
Fact-based - i.e., non-speculative;
Leverages available data to establish "typical" outcomes as points of
reference - benchmarking
Easy to understand, validate & substantiate;
Direct impact on behavior;
Third party data
Give this one a try later!
Third party data is data that you buy from outside sources that are not the
original collectors of that data.
Instead, you buy it from large data aggregators that pull it from various
other platforms and websites where it was generated.
Contents of Business Data: Measures (2)
Give this one a try later!
Give this one a try later!
Aggregation - unit of analysis
Recoding - disambiguation
Indicator creation
A one-tailed test of significance
Give this one a try later!
, used to test the hypothesis that X > Y (or X < Y)
= to saying that X is larger (or smaller) than Y
You are testing for the possibility of the relationship in one direction and
completely disregarding the possibility of a relationship in the other
direction.
Data evaluation: Exploration - bivariate
Give this one a try later!
Associations - categorical & continuous
Differences & tests of significance
Type I error (α)
Give this one a try later!
Incorrectly concluding that there is a difference
- you reject null hypothesis when it is actually true
e.g. woman told pregnant when she is not
First party data
Give this one a try later!
, First party data is the information you collect directly from your audience
or customers.
Key elements of Data Exploration (4)
Give this one a try later!
Benchmarking:
Fact-based - i.e., non-speculative;
Leverages available data to establish "typical" outcomes as points of
reference - benchmarking
Easy to understand, validate & substantiate;
Direct impact on behavior;
Third party data
Give this one a try later!
Third party data is data that you buy from outside sources that are not the
original collectors of that data.
Instead, you buy it from large data aggregators that pull it from various
other platforms and websites where it was generated.
Contents of Business Data: Measures (2)
Give this one a try later!
