gravatar

kar_ng

KAR NG

Recently Published

Document
Life Expectancy (On Going)
Analysis of Titanic Mortality
Data manipulation, imputation, feature engineering, and machine learning algorithms (K-Nearest neightbour, random forest, and extreme-gradient boosting) were applied to clean the dataset. A final, perfectly cleaned dataset was synthesised for data visualisation to understand the trend in the tragedy.
Marketing Analytics
Length: 35 mins | EDA + Statistical Analysis + Machine Learning Prediction Techniques | Solved 9 business tasks by 18 graphs and 10 statistical methods include dummy data partitioning (train & test for RMSE & R2), stepwise model selection, MLR, multicollinearity (correlation & VIF), GLM’s binomial for logistic regression.
Cucumber: Multi-Env Latin Square Field Experiment
Length: 16 mins | Visualisation + Statistical Analysis | A multi-environment Latin Square designed trial analysed by ANOVA, Two-way ANOVA, Fully Random Model, Mixed Effect Model, and Tukey test.
Oats: Variety-Fertilizer Field Experiment
Length: 14 mins | Visualisation + Statistical Analysis | A factorial Split-plot system analysed by Shapiro-Wilk test, Levene’s test, Q-Q plot, CI plot, mixed-effect model, ANOVA and Tukey Post-hoc test.
Maize: Soil Nutrient Glasshouse Experiment (CRD)
Length: 12 mins | Visualisation + Statistical Analysis | A CRD system (8 treatments + 3 harvests) analysed by Shapiro-Wilk test, Q-Q plot, Levene’s test, Kruskal-Wallis test and Dunn’s Post-hoc test.
Brisbane Real Estate Sales 2018 - 2020
Length: 24 mins | EDA + Mapping | 320k observations and 11 variables cleaned and manipulated for EDA and mapping (choropleth, cluster, points) to find a new home for a Brisbane family.
Avocado Prices EDA & Prediction
Length: 29 mins | EDA + Forecast | 18k observations & 14 variables cleaned and manipulated for EDA, time plots, and forecasting (ETS, ARIMA) of US and Houston Avocado's prices.
Resort Hotel versus City Hotel
Length: 27 mins | EDA | 119k observations & 32 variables cleaned and manipulated to create 14 distinct graphs and statistics tables during an extensive EDA to draw insights.
Bike-Share Big Data Analysis
Length: 28 mins | EDA + Mapping | 3.7 million observations & 13 variables were cleaned and manipulated for 6 graphs, dynamic map and general statistics to convert casual riders into members.
Sugar Beets Golden vs Merlin, who is more susceptible to herbicide?
Standard Student's Two-Sample t-Test, Welch's t-Test, Paired t-Test, Wilcoxon Matched Pairs, Mann-Whitney test, Levene's test, Shapiro-wilk test.
Wheat Yield Comparison with Country-Wide Average
[One-sample Student's T-test] This report is created for showcasing or educational purpose to introduce the application of One-sample Student's T-test on the scale of one-sided and two-sided method. Data are synthesized and has been modified from publicly available source.