Effective data analysis starts with good data collection and/or selection. Conducting this requires good comprehension of all data types and their multiple sources. Furthermore, structuring that properly allows the ease of its visualization under different charts and describes all the results with adequate and efficient descriptive statistics measures.
This course starts with key points in designing a smart data collection process, sampling best approach, validating the quality of the information stored for analysis, and understanding all the visualization possibilities and their corresponding descriptive statistical KPIs. Moreover, this course explores all techniques and tools for comprehensive data analysis, prior to kicking off any work or even a career in the world of data. The course also serves as a primer to any Machine Learning course/program.
In addition, this course is designed to make participants have a clear and complete understanding of data structuring for efficient data analysis, of profiling different groups scientifically by analyzing data smartly and efficiently, and of appropriately manipulating several technology tools now in the market.
Course Methodology
Each statistical tool or methodology used during the course is supported by its own case study with step by step outputs that go in parallel with multi stage analysis.
In addition to group discussions, all analysis tools are detailed and demonstrated with sequential screen shot applications on comparative technologies (EXCEL – STATISTICA and SAS – R and Python).
Course Objectives
By the end of the course, participants will be able to:
Comprehend and plan the lifecycle of a good data analysis project
Translate any business into a comprehensive database
Evaluate data quality for analysis and reporting
Describe and interpret data basics with complete descriptive statistics
Explore the complete story behind data analysis
Target Audience
Applied Data Analysis is the foundation for all Machine Learning and Artificial Intelligence (AI) practitioners. It is prerequisite knowledge that is applicable in all industries and data related functions.
Target Competencies
Project Design
Findings Visualization
Data Analysis
Problem Solving using analytical tools
Course Outline
Data visualization and descriptive statistics
The different types of Data
Data sources
Data
Variables
Data visualization
Pies, Doughnuts, Bars
Histograms, Lines, Scatter plots
Heat maps and Tuckey boxes
Geographical maps
Central tendency measurements
Average
Median
Mode
Scatter tendency measurements
Quartile
Variance
Standard deviation
Estimations
Punctual
Confidence Interval
Comparing two groups
Two mean test
Equal variances (t-test)
Unequal variances (t-test – Welch correction)
Two variance test (F-Test)
Two proportion test (Chi Square test)
Two distribution test (Chi Square test)
Attraction – Repulsion Matrix
Vertical and horizontal profiling
Comparing multiple groups
Multiple mean test
Equal variances (F-Test and ANOVA Table)
Unequal variances (F-Test – Welch Correction)
Multiple Variance test
Levene test
Chi Square test
Multiple proportion test (Chi Square test)
Multiple distribution test (Chi Square test)
Attraction – Repulsion Matrix
Vertical and horizontal profiling
Mean pair comparisons methods:
General
Bonferroni
Tukey - Kramer
Simple regressions
Simple linear regression
Line equation
Testing the regression line validity (t-nullity test)
R vs. R Square interpretation
ANOVA table analysis
Simple logistic regression
Probabilistic model
Testing the model validity (Chi Square test)
Predicting classification
Odds ratio interpretation
Data analysis project best practices
Data analysis project best practices
Ask
Design
Preview
Analyze
Communicate
Sampling methods
Random and systematic
Multilevel, stratified and cluster
Convenient, quota and judgmental
PMP for research projects overview
Integration, cost, scope, time, cost, quality, communication