Data Analysis

Data Analysis of research data is determined by the type of research, the research questions asked and/or the statistical hypothesis to be tested, the type of sampling plan used, and the type of data obtained.  While there are many statistical procedures that can be used for data analysis, all have assumptions that must be satisfied to achieve a reliable analysis and interpretation of the data.

Gliem and Gliem, LLC, are familiar with and can provide many types of statistical procedures for use in data analysis.  An abbreviated listing of  the various types of statistical tools for use in data analysis is as follows:

• Univariate Analysis
  
  • Measures of Central Tendency (Mean, Median, Mode)
  • Measures of Variability (Range, IQR, Standard Deviation, Variance)
  • Measures of Association (Pearson, Spearman, Kendall, Phi, Gamma, Lambda, Chi-Square, Etc.)
  • Analysis of Variance (ANOVA), Factorial Analysis of Variance, Analysis of Covariance (ANCOVA), Repeated Measures ANOVA
  • Simple Regression
  • Effect Size Measures
     
• Multivariate Analysis
  
  • Multiple Linear Regression
  • Binary and Multinomial Logistic Regression
  • Discriminant Analysis
  • Canonical Correlations
  • Multivariate Analysis of Variance (MANOVA)
  • Principal Components Analysis
  • Factor Analysis
  • Cluster Analysis
  • Time Series/Forecasting Analysis
  • Chi-squared Automatic Interaction Detector Analysis (CHAID)
  • Classification and Regression Trees (CART)
  • Reliability/Item Analysis
  • Power Analysis
  • Nonparametric Statistics
  • Analysis of Complex Samples
  • Structural Equation Modeling (SEM)
     
• Statistical graphics are available for selected statistical procedures.