Cleaned data view

Estimated reading: 3 minutes

In this article you will learn everything you need to know about the cleaned data view. This view provides you with an overview of the data quality after performing the data cleaning.

You will get to the data view for cleaned data on the one hand after performing the data cleaning or on the other hand when you click on the »Cleaned data« below.

Metadata

As in the Raw data view the following information about the data import is displayed in this section

Number of data points used for the calculation of the data quality
Number of quality scores (quality criteria)
Date of data import (date of creation)
Credits (costs)

Cleaning Summary:

Number of included data records (interviews) after cleaning
Number of excluded data records (interviews)

Cleaning Summary

By clicking »Cleaning Settings« a pop-up menu will open in which the parameters for the data cleansing can be set.

Cleaning (1)
- (2) Clean by the Number of the records remaining after cleaning: Here you can specify how many data records should remain after cleaning, e.g. the 250 highest quality interviews.
- (3) Clean by the ReDem®-Score- resp. Quality-Score-threshold: Here you can specify different cut-off values (between 0 and 100) for the individual quality checks.
- After entering, click »Apply Cleaning«.

Marking (4)
- All data records below the specified ReDem®-Score will be marked.
- After entering, click »Apply marking«.

Quality Report

The quality report widget takes you to the data quality report for this survey. You can share this with all persons involved in the project. In addition, the quality seal level, if applicable, is displayed.

Quotas overview

In the quota overview widget, you will get a visual representation of the progress in achieving the set target quotas. For more detailed information on this topic, we recommend you to take a look at our collection of articles on quotas .

This widget is not displayed for live data imports. Due to live cleaning, the final quotas are already available in real time and are managed in the survey tool.

ReDem®-Score charts

As in the "Raw data view", the following three charts are in this section to help you interpret the data quality.

ReDem®-Score
- Mean value of all individual scores
- Influence of the Quality-Scores (pie chart)
Distribution of the ReDem®-Scores
- Shows how many records are in a given score range.
ReDem® traffic lights
- Shows how many percent of records are in one of the five traffic light areas.
  - Gray = No score
  - Red = bad quality
  - Yellow = moderate quality
  - Light green = good quality

Quality-Score widgets

By clicking on the »Show more« button in the ReDem®-Score widget, you can access an overview of all the Quality-Scores used for this ReDem®-Score. Each of these widgets displays the score mean and contains the following three graphs.

Distribution
Traffic light
Data points (scores per data point)

For more information on the individual quality score widgets, see the detailed view of the quality criteria.

If you have any further questions about the cleaned data view, please contact us at business@redem.io