Past Workshops and Events
Introduction to SPSS
This hands-on workshop introduces researchers to the basic procedures for analyzing large survey data sets.
Although the emphasis will be on the requirements for analyzing Statistics Canada micro data, the topics covered are essential for all researchers who plan to use large survey data sets for part of their research.
Workshop participants will learn to use SPSS syntax, one of several popular statistical software programs, in the actual exploratory analysis of a large survey data set.
- Data management with SPSS
- Using the “click and paste” function to learn SPSS syntax
- Constructing a working data file
- Applying appropriate sampling weights
- Recoding variables
- Basic descriptive statistics
Who should attend
This workshop is intended for those who have had no prior experience using SPSS syntax to analyze data, but who would like to be able to perform simple data management and basic descriptive statistical analyses (frequency tables, charts, cross-tabulations, means) on large survey data sets. It is especially appropriate for:
- Qualitative researchers/professors who want to develop sufficient competence in accessing and analyzing survey data to place their qualitative data into a broader statistical profile
- Faculty members who already understand the basic logic of quantitative data analysis but who are not familiar with SPSS
- Students who want to write a term paper or thesis using one of the publicly available DLI survey sets
- Research assistants who are working with a professor who has been granted access to the Statistics Canada surveys housed in the Atlantic Research Data Centre
A main strength of the SPSS software package is its extensive and simple data manipulation features. This half-day workshop provides hands-on instruction for recoding variables, combining variables, constructing and evaluating various types of scales, and creating indicator (or dummy) variables from categorical variables. This workshop also covers data modification procedures, such as centering variables, that are recommended when applying any form of regression analysis, including logistic regression.
Participants must either have taken the Getting Started with SPSS module, or have a basic understanding of SPSS syntax.
The specific SPSS commands that will becovered are:
- Functions (MEAN, SD, MIN, etc.)
- DO REPEAT…END REPEAT
- DO IF…END IF
Introduction to SAS
Of the three statistical software packages most commonly used by social scientists, SAS is likely best at manipulating large datasets. This is why SAS remains the statistical software of choice within Statistics Canada. As such, some of the datasets that are produced by Statistics Canada and found in the Atlantic Research Data Centre are in only SAS format -- due to the size of the files (example: Census) or the data extraction tools that Statistics Canada has developed (example: the Survey of Labour and Income Dynamics).
This hands-on introductory workshop is designed to provide novice users with the skills to convert ASCII or .txt files into the SAS format, to reduce or delete variables from the dataset, to recode variables, remove missing values, produce descriptive statistics (frequencies, means), merge data files and export data files into another statistical software. Therefore, this workshop is geared toward the interests of both novice users who are interested in producing descriptive statistics and to the more advanced users of other statistical software, who find that they have to work initially with SAS, until they can convert their data to statistical software of their choice.
In the Introduction to SAS Workshop, participants learned how to open datasets, merge data files, recode variables and produce descriptive statistics.
This next workshop assumes that users have already worked with their data to produce their dependent and independent variables and are ready to conduct various tests of significance and measures of association. Participants will learn how to produce and interpret chi-square tests, t-tests, Pearson product moment correlation matrices, reliability analyses, analysis of variance and ordinary least squares regression results using SAS software with public-use micro-data. As this is an applied or hands-on workshop, all attempts will be made to limit discussions concerning the theory behind these various statistical techniques.
Therefore, it is assumed that participants come to the workshop with some prior knowledge as to the theory and uses of the statistical tests covered by the workshop. At least one hour is guaranteed to be the hands-on component – where the participants have the opportunity to work with the dataset in SAS to produce these various statistical tests.
Introduction to STATA
Purpose of workshop
This workshop will introduce students and researchers to the STATA software package. It will provide a general overview of its features and discuss some of its unique functions. It will cover how to create logs as well as commands for basic descriptive and inferential statistics, data manipulation, regression, and weights. The session will also offer a hands-on lab.
Overview of the workshop
- Why consider STATA?
- Introduction to the software and transferring files between packages
- Commands and lab for basic descriptive and inferential statistics
- Commands and lab for data manipulation and regression
Purpose of workshop
The workshop will introduce you how to run various types of regression models in STATA. Starting with the OLS, it will provide instructions on how to handle dummy variables, and how to model categorical dependent variable. Also, it will end with instruction to estimating unbiased standard error with bootstrap weights for both cross‐sectional, which is required for analysis of most RDC data.
It is recommended that participants have taken the Introduction to STATA session, or have a basic understanding of STATA software.