Survey Analysis: Analyzing Your Data

There are a number of software programs designed to analyze research data. Before starting your analysis, the data should be reviewed to identify and correct errors which may have occurred as the information was gathered. See Professional Services for a list of offices on-campus who can help you analyze your survey materials.

Below is a description of the most popular data analysis packages used at the University of Minnesota:

Program Description
Microsoft Excel Can be used for basic data analysis. With Excel, you can create a database, code, enter, clean, and analyze your data.
SAS Is a full-featured package that enables the programmer to perform powerful statistical analyses.
SPSS Integrates and analyzes marketing, client, and operational data in key vertical markets.
AMOS Provides structural modeling and analysis of covariance structures or casual modeling.
HLM Analyzes data in a clustered, or nested, structure.
PRELIS 
LISREL
Conducts structural equation modeling and similar analyses.
Mplus Offers exploratory factor analysis, confirmatory factor analysis, and structural equation modeling.

Sometimes the language used to analyze survey data can be confusing. Here is an explanation of common terms:

  • Descriptive Statistics: statistics that describe the sample data without drawing inferences about the larger population
  • Inferential Statistics: statistics that describe the sample data by drawing inferences about parameters of the population(s) you have sampled
  • Cumulative Frequency: the sum of the number of occurrences within a given answer, including all responses up to the present; increases with each successive addition
  • Frequency: the number of occurrences within a given answer
  • Mean: the average, or sum of responses divided by the number of responses
  • Median: the mid-point; a numeric value separating the lower half of the results from the upper half
  • Response Rate: the number of people who answered the survey request divided by the number of people in the sample; usually expressed as a percentage
  • Standard Deviation: a measure of the variability from the average response; the average distance of scores from the mean score

The task of data analysis becomes more complex when the number of items or questions is large. A frequency table can be constructed for each item on the survey, but this can result in upwards of 50 or 100 tables. As the volume of statistics increases, the problem becomes one of organizing the results into a coherent and meaningful set of findings. Read Reporting Your Findings for more information on report organization and formatting.