Statistics for Data Analysis Getting Started

 

Goals: 

Provide the notions for building and organizing a database of cases that can be manipulated, explored, described, synthesized and represented.

Tackle the descriptive and inferential statistical problems preparatory to the construction of multivariate interpretative models.

​

Techniques presented: 

Data access, transformations preparatory to statistical analysis, error detection and correction, management (aggregations, groupings, selection with filters) and data transformation (recoding, computation of new variables, etc.).

Univariate and bivariate statistical techniques, summary indicators, interdependence between two variables.

​

Tutorials:

There are exercises for each of the topics covered.

​

Prerequisites:

Minimum familiarity with the PC, with Windows and with the most common office automation tools is required.

 

Subjects:

Introduction

• Platforms

• Windows environment

• Structure of Statistics for Data Analysis

• How to get help

 

Databases

• The data editor

• Creation of a new database

  • Creating a new file

  • Data entry and modification

  • Information about a Statistics file

  • Guided definition of variable properties

  • Copy data properties

• Imports from external databases

  • Import from spreadsheets and non-relational databases

  • Import from relational databases and other applications

  • Import of text data

• Exporting a file

 

Understanding and preparing data

• Restructuring of files

  • Transpositions of cases and variables

  • Restructure data

• Definition of the database and operations on cases

  • Merging files

  • Data aggregation

  • Weighting of cases

  • Case selections

  • File decomposition

  • Identifying duplicates

• Transformations and operations on variables

  • Sorting of cases

  • Ranking construction

  • Recoding of variables

  • Calculation of new variables

  • Replacement of missing data
     

The descriptive statistics

• The study of a qualitative phenomenon

  • Frequency tables and graphs

  • Mode and median

• The study of a quantitative phenomenon

  • Position indicators, dispersion around the mean, distribution

  • Graphs for quantitative phenomena

  • The Gaussian distribution

• The commands related to descriptive statistics

  • Frequencies

  • descriptive

  • Index numbers

  • Weighting of cases

  • The EXPLORE command

  • Box plot (boxplot)

  • Error graph

 

Preliminary diagnostic and exploratory data analysis

• Check on the distribution of variable

  • Verification of the robustness of the central tendency

  • Focus on intensities

 

Graphical tabular reporting

• Visualization and reporting

• Interactive analysis (OLAP)

• Creation of tabular reports

  • Prospectus creation

  • Custom tables

  • OLAP Cubes

• Creation of graphical reports