In this instance, a new recommender system has been tested live in the platform, in order to gain data about its efficiency, what could seem as a straight comparison, requires a deeper look into the control group, in order to understand the validity of the results, which this report will provide. The main questions we endeavour to investigate are: - is there a significant difference between the mean hours watched by the control group versus the standard one? - do subgroups’ sizes, related to particular variables, have an effect in the outcome for the test? - if not, what would be their required size and scope of a new test? - what other findings this test provides us? - what correlations can we find in the analysis?

This report encompasses the solutions, and their findings, for six given problems. The purpose of this assessment is to apply your understanding of key concepts covered in this course, and to explore issues around the ability of statistical tests to correctly assess differences in population means. This assessment covers the following topic areas: • Probability distributions • Sampling distributions • Confidence intervals and hypothesis testing • ANOVA.

This report covers a statistical investigation and a series of business-related questions, based on a population dataset from the Australian Bureau of Statistics (ABS). We will use a range of data analysis techniques such as descriptive statistics, data manipulation, and plotting in R, to accurately interpret and communicate the findings.

Correlation between high temperatures and domestic violence cases in Bogota (Colombia)

As part of the assignment 1 for the Data Wrangling subject, at the Master of Data Science Strategy and Leadership at RMIT Online, we had to produce a report of given tasks for a chosen open source data set.

An example of a basketball dashboard for post match insights

As part of the assessment 2