The ability to automatically classify physical activity movements into categories in respect of their proper performance form (so-called qualitative activity recognition) can have potential benefits in reduction of weightlifting-related injuries. This project is aimed at identifying correctly the type of the form in which a simple weightlifting excercise (unilateral bicep curl with dumbbell) was performed. There are 5 types of form, 1 of which was correct, the others illustrated common mistakes. The results show a great quality of classification.

In this document a fuel efficiency of 1970's automobiles is the main subject of interest. In particular, there are 2 major questions of the research: 1. Is an automatic transmission better than manual in regard to US miles per gallon (MPG) travelled? 2. And what is the actual MPG difference between automatic and manual transmissions? Judging by the results of the study, it appears that there is in fact a significant difference in MPG between the 2 types of transmissions. Unfortunately, the data for this study does not provide satisfactory basis for more or less reliable quantification of the difference in fuel economy between 2 groups.

Sometimes performance evaluation of certain business processes can be obstructed by the time factor. For example, to measure profitability of marketing channels the time of the first visit (or some other action) should be accounted for. If the time span of the data is short and the majority of acquired clients registered during the latest part of the period in question, then those clients simply did not have the opportunity to return the investments. Dividing clients into groups (cohorts) by the time of the required action makes the analysis more reliable. In this document we will explore the data of a movie ticket service and perform simple cohort analysis of marketing channel profitability.

The goal of this project is to explore the effect of vitamin C supplementation on tooth growth in guinea pigs with control for the dose and the delivery method of the vitamin. The analysis is based on the dataset of 60 guinea pigs and providing the underlying assumptions to be the case the conclusions can be extended to the general population of guinea pigs.

The Central Limit Theorem (or CLT for short) is one of the crucial aspects of probability theory and a powerful tool for inferential data analysis. The application of CLT requires only a few assumpttions and the resulted inference is robust to the population's distribution. In this document we will demonstrate the CLT application on the example of exponentialy distributed data.

This is my submission of coursera's reproducible research course (https://www.coursera.org/learn/reproducible-research) project.