LESSON 4 - DATA PREPARATION & DATA CLEANING

Data Preparation

the process of:

• checking data accuracy

• correcting errors

• handling missing values

• identifying outliers

• organizing data for analysis

Data Collection - Data Cleaning - Data Analysis - Interpretation - Reporting

Data Analytics Workflow

Step 2

What step is the outlier detected?

Outlier

-a value much higher or lower than most data points

-a value far from the dataset center

FALSE

TRUE OR FALSE.

All outliers are errors

TRUE

TRUE OR FALSE.

Some outliers represents real disease conditions

Flagging

Outlier detection

Data Cleaning

Investigation and Decisions

Interquartile Range

In data analytics, it is the measure of data spread

Range Check

a data validation technique that verifies whether an input value falls within a predefined upper and lower limit

Z-score

tells how far and in what direction a value is fro the mean, measured in standard deviations

Standard score

other term for Z-score

FALSE

TRUE OR FALSE.

All outliers should be deleted.