Data analysis is conducted by gathering, processing, inspecting, cleaning, transforming and modeling data. There are a variety of tools that are important for modeling data, including both graphical and quantitative techniques. All data analysis requires a strong understanding of mathematical statistics.
Continue ReadingThe primary graphic techniques utilized in data analysis are box plots, histograms, MultiVari charts, Run charts, Pareto charts, scatter plots and stem-and-leaf plots. These techniques, commonly referred to as statistical graphics, enable data scientists to create visual representations of data, assisting them in using data sets to draw conclusions and make decisions. In particular, statistical graphics help with outlier detection, factor effect determination and model validation.
Quantitative techniques are the processes that produce numeric output, allowing the graphics above to be produced during data analysis. Common means of quantitative analysis include analysis of variance, confidence intervals, hypothesis testing, point estimation and least squares regression. Formerly done manually, many of these processes are now commonly accomplished with software.
Popular software and programming languages for data analysis includes CMU-DAP, TinkerPlots, SPSS, R, JMP and LiveGraph. Many of these programs provide the tools necessary to analyze data with quantitative techniques and create corresponding statistical graphics. As data sets have grown exponentially larger, as more data is available online, the rapidity of analysis associated with these products has become more important.
Learn more about Data Graphs