BCS - Level 4 Certificate in Data Analysis Tools

Lehrplan

1. Processes and Tools Used for Data Integration

In diesem Thema wird der Teilnehmer beschreiben, wie Datenintegration durch die Manipulation von Daten aus verschiedenen Quellen erreicht wird. Sie lernen auch, wie diese Daten mit Hilfe von Programmiersprachen manipuliert und für die Analyse vorbereitet werden. Sie werden in der Lage sein:

1.1. Describe the purpose and outputs of data integration activities.

• Business need for analysis
• Non-functional requirements (such as speed and time available)
• Information structure and rules relevant to the business
• Rationale for using and integrating data from multiple sources
• Importance of data in a business context

1.2. Explain how data from multiple sources can be integrated to provide a unified view of

the data.

• Reasons for using data from multiple sources
• Importance of data source quality to improve the quality of results
• Filtering data to ensure only relevant data is combined to underpin business
• objectives
• Ensure data is selected in line with current legislation
• Data integration techniques
• Common user interface
• Virtual integration
• Physical data integration (for example ETL (Extract - Transform - Load))

1.3. Discover how programming languages for statistical computing can be applied to data

integration activities to filter and prepare data for analysis.

• Programming constructs
• Sequence, selection and iteration
• Modularisation, coupling and cohesion
• Commands for manipulating data (for example, but not limited to)
• Select and Select* statements
• From
• Where (such as but not limited to; AND, OR, use of Wildcards and ordering)
• Joins (inner and outer, right, left, Full, Union and Select into)
• Joins with duplicate values
• Joining on multiple fields
• Single queries
• Multiple queries
• Expressions
• Functions (such as but not limited to; Avg(), Count(), Max(), Min(), Group by,
• Round(), Cast(), Convert(), ISNULL ())
• Querying multiple tables in different information
• Selecting the first/last of occurrences
• Implicit data conversion

1.4. Explain the nature and challenges of data volumes and types being processed through

data integration activities.

• Big data sets
• Qualitative data versus quantitative data
• Technical requirements for managing large data set (such as, but not limited to; the
• location of data and challenge of restrictions due to the computer architecture)
• Data warehousing
• Data migration
• Master data management
• Integration design
• Business requirements for integration
• Objectives and deliverable
• Business rules
• Support models and SLAs
• Non-functional requirements
• Data integration tools (such as future scalability, implementation and support costs)
• Data synchronisation (such as data ownership, frequency of updates, format,
• security, data quality, performance and maintenance)

1.5. Develop appropriate testing strategies to ensure that unified data sets are correct,

complete and up to date.

• Check against business requirements
• Test for a variety of states (such as, but not limited to; presence, completeness,
• configuration and format, that data is valued and that data is not fragmented)
• Business testing & technical testing
• Technical acceptance testing (TAT)
• User acceptance testing (UAT)
• Performance stress tests (PST)
  

2. Industry Standard Tools and Methods for Data Analysis

In diesem Bereich wird der Teilnehmer eine Reihe von Werkzeugen, Techniken und Methoden zur Vorbereitung und Analyse von Daten beschreiben und anwenden. Der erfolgreiche Auszubildende sollte in der Lage sein:

2.1. Demonstrate the data manipulating, processing, cleaning and analysis capabilities of statistical programming languages and proprietary software tools capabilities and functions of statistical programming languages (such as, but not limited to; R, Python, SPSS, SAS, SQL, Microsoft Excel and VBA, Julia, Hadoop and Hive, Scala)

2.2. Demonstrate how to apply statistical programming languages in preparing data for analysis and conducting analysis projects.

• Preparation techniques (such as, but not limited to; searching and sorting, grouping,
• filtering, macros and modelling)
• Data cleaning to remove a range of data issues (such as, but not limited to; errors,
• invalid values, data that is out of range, outliers)
• Processing and analysing:
• Mean, Median, Mode and Range
• Probability
• Bias
• Statistical significance
• Linear Regression (simple & multiple)
• Logistics Regression (simple & multiple)
• Scatter plots and correlation
• And/Or probability
• Stem and leaf plots
• Factorials
• Box and whisker plots
• Methods for presenting results (such as, but not limited to; tables, charts and
• graphs, correctly arranged and presented using suitable language)
• Presenting for data analysts
• Working with people