*RESEARCH DATA SERVICES (RDS) @ Georgia State University Library

Topics:

• Using RStudio to work with R
• R syntax, commands, functions, and packages
• Opening, viewing, and exploring data
• Generating basic descriptive statistics from data

R 2: Tidyverse and Manipulating Data

Topics:

• Introduction to Tidyverse packages (emphasis on dplyr)
• Transforming and generating variables
• Handling data with missing values
• “Piping” data and data processes

R 3: Data Visualization and Mapping

Topics:

• Creating statistical plots using ggplot2
• Customizing plot colors, themes, labels, etc…
• Working with GIS data to create maps
• Modifying maps with overlays, custom aesthetics, and additional data

R 4: Statistical Modelling

Topics:

• Basic analysis, descriptive statistics, t-tests
• Creating linear models (multiple linear regression & logistic regression)
• Evaluating linear models and generating predictions
• Creating simple machine learning models (Time permitting)

This tutorial is the first of a two-part series on SPSS, a statistical software package that is widely used by scientists throughout the social sciences for analysis of quantitative data.

Please note: This tutorial focuses on using the point-and-click method for using SPSS; the syntax/code method is introduced briefly.

Topics

• Navigating SPSS
• Entering and importing data from different formats (such as text and Excel files)
• Defining variables (defining and labeling codes, selecting appropriate levels of measurement)
• Manipulating and transforming data (selecting cases and splitting files; recoding and computing variables)
• Running descriptive statistics
• Generating simple graphs

Prerequisites: None.

SPSS 2: Analyzing Data

This tutorial is the second of a two-part series on SPSS, a statistical software package that is widely used by scientists throughout the social sciences for analysis of quantitative data.

Please note: This tutorial focuses on using the point-and-click method for using SPSS; the syntax/code method is introduced briefly.

Topics

• Cross-tabulation and Chi-Square tests
• Analysis of Variance (ANOVA)
• T-tests
• Correlation analysis
• Multiple regression analysis

Prerequisites: Attendance at SPSS 1 preferred, or completion of Parts 1-6 of the Lynda.com "SPSS Statistics Essential Training" tutorial.

This is the first SAS tutorial in a two-part series. This interactive tutorial will introduce users to the SAS system. Applied, hands on, examples using real data will be used. NOTE: This tutorial is aimed at people who do not have experience using the SAS system. Those who have used SAS in the past may find this tutorial too foundational and are encouraged to attend our forthcoming advanced SAS sessions.

Topics:

• Reading data into SAS
• Conducting basic data cleaning and recoding
• Using basic SAS procedures (e.g., PROC CONTENTS, PROC PRINT, PROC FREQ) to view and understand data.
• PROC FREQ, PROC UNIVARIATE, and PROC MEANS will be demonstrated to complete basic descriptive statistics.
• An introduction to bivariate statistics in SAS.

Prerequisites: No prior experience with SAS is required. Basic understanding of univariate and bivariate statistics is helpful but not required.

SAS 2: Data Analysis

This is the second SAS tutorial in a two-part series. In this interactive tutorial, SAS users will go beyond the basics to develop comfort with more advanced statistical analyses using the SAS system. Applied, hands on, examples using real data will be used. NOTE: Basic knowledge of the SAS system will be helpful for those who want to participate in the applied portion of the tutorial.

Topics:

• Conducting bivariate and multivariable analyses using SAS procedures like PROC FREQ, PROC TTEST, PROC ANOVA, PROC GLM, PROC LOGISTIC, and PROC REG.
• Best practices for checking statistical assumptions, selecting appropriate statistical procedures, and reporting and visualizing results will be discussed.

Prerequisites: Basic knowledge of the SAS system will be helpful for those who want to participate in the applied portion of the tutorial. Basic understanding of bivariate and multivariable statistics is helpful.

This tutorial is the first of a three-part series on Stata. Stata is a statistical software package. Stata is widely used by scientists throughout the social sciences for analysis of quantitative data ranging from simple descriptive analysis to complex statistical modeling.

Please note: This tutorial completes all analysis using code. No previous knowledge of coding is required.

Topics:

• Opening data
• Generating variables (basic)
• Frequency distributions
• Analysis: summary statistics

Prerequisites: None.

Stata 2: Basic Data Analysis

This tutorial is the second in a three-part series on Stata. Stata is a statistical software package. Stata is widely used by scientists throughout the social sciences for analysis of quantitative data ranging from simple descriptive analysis to complex statistical modeling.

Please note: This tutorial completes all analysis using code. No previous knowledge of coding is required.

Topics:

• Generating variables (advanced)
• Analysis: Chi-square, ANOVA, regression
• Graphs
• Navigating help features

Prerequisites: Stata 1 or basic knowledge of Stata.

Stata 3: Advanced Data Analysis

This tutorial is the third in a three-part series on Stata. Stata is a statistical software package. Stata is widely used by scientists throughout the social sciences for analysis of quantitative data ranging from simple descriptive analysis to complex statistical modeling.

Please note: This tutorial completes all analysis using code. No previous knowledge of coding is required.

Topics:

• Troubleshooting code
• Generating scales
• 3, 4, and 5 way cross tabulations

Prerequisites: Stata 1 and Stata 2 or moderate knowledge of Stata.

This tutorial provides a short, high-level overview of Google Colab and how it relates to the other Python tutorials. 

Topics:

• Brief overview of Google Colab
• Uploading, managing, and saving data in Google Colab environment

Python & Data 1: Getting Started with Python

Topics:

• Using Google Colab and Jupyter to work with Python
• Python syntax, commands, functions, and packages/modules
• Opening, viewing, and exploring data
• Generating basic descriptive statistics from data

Python & Data 2: Manipulating & Transforming Data

Topics:

• Selecting, sub-setting, and manipulating data
• Transforming and generating variables
• Handling data with missing values
• Generating crosstabs / contingency tables

Python & Data 3: Visualizing Data & Creating Models

Topics:

• Plotting and visualizing data using Matplotlib and Seaborn
• Defining statistical models using both formulas and matrices
• Fitting and inspecting statistical models (e.g. anova, linear regression)

Fundamentals of supervised learning in Python; applying a rudimentary ML model using univariate linear regression (i.e., one feature).

Topics:

• Overview: “What is Machine Learning?”
• Univariate Linear Regression Model
• Mean-Squared Error Cost Function
• Gradient Descent Algorithm for Linear Regression

Prerequisites: Python & Data Series 0-3: https://lib.gsu.edu/rds-recordings

Python for Machine Learning (ML) 2: Multivariate Linear Regression