Statistical Data Analysis & Predictive Modeling (SPSS) – 386 Case Study

"Applying an engineering analytical mindset to transform raw data into actionable intelligence."

Project Overview:

In this project, I analyzed a comprehensive dataset of 386 trainees to evaluate program effectiveness and predict future performance. By utilizing IBM SPSS Statistics, I bridged the gap between raw numbers and strategic decision-making.

Statistical Methodologies Applied: One-Way ANOVA: Compared training satisfaction across different educational levels (Bachelor, High School, Master). Simple Linear Regression: Developed a predictive model for exam performance based on training hours (Model Equation: Y = 75.181 + 0.073X). Pearson Correlation: Measured the strength of the relationship between motivation and academic achievement.

Technical Deliverables:

Data Cleaning: Structured 386 entries for precise analysis.

Automated Syntax: Wrote optimized SPSS scripts (Syntax) for reproducibility.

Insights Report: Created a professional Word summary with statistical interpretations.

Key Outcomes:

Determined that while training hours show a positive trend, further variables must be engineered to fully optimize performance—providing a data-backed roadmap for project managers.