Please enable JavaScript.
Coggle requires JavaScript to display documents.
Nature of Data, Statistical
Modeling, and Visualization (Metrics for
…
Nature of Data, Statistical
Modeling, and Visualization
-
Data
Taxonomy
Structured
- Targeted for computers to process
- Numeric versus nominal
-
-
Semi-structured
- XML, HTML, Log files, etc
Unstructered
- Targeted for humans to process/digest
-
-
Data Preprocessing
Data transformation
- Normalize data
- Discrete data
- Create attribute
Data cleaning
- Impute data
- Reduce noise
- Eliminate duplicate
Data reduction
- Reduce dimension
- Reduce volume
- Balance data
Data consolidation
- Collect data
- Select data
- Integrate data
Regression
Modeling
-
-
Process
Model Fitting
- Transform data
- Estimate parameter
Model Assessment
- Test assumption
- Assess model fit
-
-
-
-