Data-Analysis-PDF

This repository contains coursework for DSC190, showcasing five distinct data analysis projects using R. Each project demonstrates a range of data analysis techniques, statistical methods, and visualization skills.

Projects Overview

1. Analysing the Programming Language Preferences of Data Scientists in 2020

   • Explores survey data from Kaggle to analyze programming language usage and educational backgrounds.
   • Techniques: binary encoding, chi-square tests, clustering, random forest classification.

2. Detecting Replication Patterns in HCMV through Palindrome Analysis

   • Investigates palindrome patterns in genomic data using simulation and statistical tests.
   • Techniques: Monte Carlo simulation, Q-Q plots, KS tests, cluster analysis.

3. Maternal Smoking and Birth Weight

   • Examines the impact of maternal smoking on birth weight using statistical comparisons.
   • Techniques: data cleaning, permutation tests, kurtosis analysis, group comparisons.

4. Statistical Analysis and Calibration of a Gamma Transmission Gauge

   • Analyzes calibration data for a gamma transmission gauge with regression and prediction methods.
   • Techniques: linear/log-linear regression, prediction intervals, reverse prediction, robustness testing.

5. Video Gaming Patterns and Academic Performance

   • Studies the relationship between video gaming habits and academic performance.
   • Techniques: bootstrapping, confidence intervals, demographic analysis, hypothesis testing.

Skills Demonstrated

• Data Cleaning: Handling missing values, recoding, filtering, and outlier removal.
• Exploratory Data Analysis: Visualizations like histograms, barplots, and heatmaps.
• Statistical Testing: Chi-square tests, KS tests, permutation tests, and bootstrap methods.
• Modeling & Prediction: Regression analysis, clustering, and random forest classification.
• Simulation: Monte Carlo methods and resampling techniques.
• Reproducible Reporting: Scripts and tables generated with R and knitr.

Tools & Libraries

• R: Base R and packages like dplyr, caret, randomForest, corrplot, and knitr.
• Data Sources: Includes survey data, genomic data, and other text/delimited files.

Feel free to explore the individual project folders for detailed scripts and reports. Each project folder contains the R script and a corresponding PDF report summarizing the analysis.