Statistics for Data Analysis

Why statistics

What is statistics?

Statistics is the discipline that studies

1. the procedure of collection, illustration(explain or prove), processing and analysis of the data
2. how to extract information about empirical (experienced) or theoretical models from the investigation of random phenomena
3. learning from data (or making sense of them)
4. quantification(judge) of uncertainty and risk

Goals of statistics

1. Exploratory data analysis and descriptive statistics
   • for a given objective
   data collection
   data preparation
   interpretation
   • quantitative characterization of phenomena
   • results and statements only for the examined data
2. Inferential statistics
   • procedures and general conditions that enable conclusions to be drawn for the population based on analysis of a subpopulation (sample)
   • understanding of the process that generates the data
   • uses methods of probability theory that ensure a certain level of precision

Steps of statistical analysis

1. Planning
2. Collection of data
   • survey
   • observation
   • experiment
   • automatic collection
3. Preparation
4. Analysis
5. Interpretation

Exploratory of data analysis

Things to consider when choosing summary statistics and data visualization:
A. the type of data (scaling)
B. the goal(s)
C. the audience
D. you can learn more about this in the modules Telling stories with data (Urban Informatics) or the optional module Simulation and Data Visualisation (Data Science)