Multilevel models (also referred to as hierarchical models or mixed models) are a class of statistical models that can be used when observations are not independent. Non-independence can occur when data is clustered due to the study design (e.g., data collected on households and their individual members or blocked agricultural studies) or when data is […]
In a longitudinal study data has been collected on the same observation over time. Since the repeated measures taken on the same observations are not independent from each other this is a type of multilevel data and special care needs to be taken during the analysis to account for this non-independence. These types of data […]
This workshop is intended for people who feel comfortable with the material covered in our Introductory Statistics Using Stata workshop. We will use hands-on examples to cover: Sub-setting by observations or by variables Creating new variables as functions of existing variables Aggregation/summarizing by observations or by variables Reshaping (pivoting) from wide to tall or from […]
Panel data, also known as longitudinal data, consists of multiple observations of the same subject over time. Many disciplines will analyze such data using a random intercept or random coefficients model. In this workshop, another way of modeling such data will be discussed: using fixed effects. Fixed effects methods can be used in longitudinal studies […]
Missing data are very common in all types of data sets, but most statistical procedures assume that all data are observed. The result is that most standard statistical software packages automatically drop from the analysis all observations with any missing data. This approach can lead to very low sample sizes and biased results. This two-part […]
Time series analysis concerns with methods for visualization and statistical analysis of data collected sequentially over time. This workshop is designed to introduce researchers to basics of time series data exploration and modeling. After attending the workshop, you should be able to use standard R packages to: perform exploratory data analysis with time series;- correct […]
Fractional factorial designs are often used for screening a large number of factors potentially related to a continuous response variable of interest. Attendees will learn about: Design generators, alias structure and design resolution Plackett-Burman designs Central composite designs Box-Behnken designs The designs and methodology will be illustrated using examples and the statistical software packages, JMP […]
To answer statistical research questions, data must be arranged correctly to apply the appropriate model. Often data comes to a researcher in the wrong arrangement, and a researcher must reconfigure the format or combine data from several sources before a model can be used. In this workshop we will go over the most common “data […]
Partial least squares (PLS) is a data reduction method that can be useful when dealing with multicollinearity in multiple linear regression. PLS is often used in predictive analyses and discriminant analyses. The PLS algorithm creates new uncorrelated variables from old variables, but in a different way than PCA. PLS regression is considered one of the […]
Item response theory (IRT) consists of a family of mathematical models which can be used to estimate and evaluate the relationship between observed variables and a latent trait. Different IRT models exist for different types of observed variables. In this workshop, we will mainly focus on IRT models for binary observed variables. These types of […]