Advanced Statistics Series
Table of Content
Hierarchical Linear Modeling Overview
Description: Hierarchical linear modeling (HLM) is an extension of regression that is used for data that are clustered into groups. It can be applied to a variety of clustered data types to examine environmental effects at different group levels, such as hospital effects on patient recovery outcomes. This video provides an introduction to the structure, advantages, and uses of HLM.
Duration: 9:27
Content created by: Pamela Sheffler, Yena Kyeong, Cecilia Cheung
Narrated by: Pamela Sheffler
Hierarchical Linear Modeling Example
Duration: 10:05
Content created by: Pamela Sheffler, Cecilia Cheung
Narrated by: Pamela Sheffler
Article discussed: Hecker, K., & Violato, C. (2008). How much do differences in medical schools influence student performance? A longitudinal study employing hierarchical linear modeling. Teaching and Learning in Medicine, 20(2), 104-113. https://doi.org/10.1080/10401330801991915
Structural Equation Modeling Overview
Description: Structural equation modeling (SEM) represents a family of powerful statistical techniques for analyzing complex relationships between observed and unobserved variables. It is used for testing model fit, model comparison, and model development. This video provides an introduction to the foundations of SEM, its advantages, and applications.
Duration: 9:14
Content created by: Pamela Sheffler, Yena Kyeong, Cecilia Cheung
Narrated by: Pamela Sheffler
Structural Equation Modeling Example
Duration: 8:04
Content created by: Pamela Sheffler, Cecilia Cheung
Narrated by: Pamela Sheffler
Article discussed: Ye, Z. J., Liang, M. Z., Li, P. F., Sun, Z., Chen, P., Hu, G. Y., ... & Qiu, H. Z. (2018). New resilience instrument for patients with cancer. Quality of Life Research, 27(2), 355-365. https://doi.org/10.1007/s11136-017-1736-9
Path Analysis Overview
Description: Path analysis is a subset of structural equation modeling that is used to examine the relationships between a system of observed variables. Researchers often use path analysis when examining a sequence of unfolding events that ocurr in a specific order, such as the relationship between commute time, stress, and job performance. This video provides an introduction to the structure and application of path analysis with examples.
Duration: 7:21
Content created by: Cecilia Cheung
Narrated by: Cecilia Cheung
Path Analysis Example (Part 1)
Duration: 7:11
Content created by: Pamela Sheffler, Cecilia Cheung
Narrated by: Pamela Sheffler
Article discussed: Starr, C. R., Hunter, L., Dunkin, R., Honig, S., Palomino, R., & Leaper, C. (2020). Engaging in science practices in classrooms predicts increases in undergraduates' STEM motivation, identity, and achievement: A short‐term longitudinal study. Journal of Research in Science Teaching, 57(7), 1093-1118. https://doi.org/10.1002/tea.21623
Path Analysis Example (Part 2)
Duration: 5:06
Content created by: Pamela Sheffler, Cecilia Cheung
Narrated by: Pamela Sheffler
Article discussed: Starr, C. R., Hunter, L., Dunkin, R., Honig, S., Palomino, R., & Leaper, C. (2020). Engaging in science practices in classrooms predicts increases in undergraduates' STEM motivation, identity, and achievement: A short‐term longitudinal study. Journal of Research in Science Teaching, 57(7), 1093-1118. https://doi.org/10.1002/tea.21623
Nested Model Comparison Overview
Description: Nested model comparison is a technique in the structural equation modeling family that compares a model to an alternative model with additional parameters. This technique is employed when a researcher seeks the best fitting model for the data, and is suitable for many types of analyses, including mediation, multigroup comparison, and latent growth curve modeling. This video provides an introduction to nested model comparison with examples of its applications.
Duration: 8:22
Content created by: Yena Kyeong, Pamela Sheffler, Cecilia Cheung
Narrated by: Yena Kyeong
Nested Model Comparison Example
Duration: 9:24
Content created by: Pamela Sheffler, Cecilia Cheung
Narrated by: Pamela Sheffler
Article discussed: Simães, C., Gomes, A. R., & Costa, P. (2019). A multigroup analysis of the effect of cognitive appraisal on nurses' psychological distress. Nursing Research, 68(3), E1-E11. https://doi.org/10.1097/NNR.0000000000000352
Latent Growth Curve Modeling Overview
Description: Latent growth curve modeling is a structural equation modeling technique specifically for longitudinal data. Researchers use latent growth curve modeling to examine stability or change in a given variable over time, such as examining improvements in patients' symptoms during the course of treatment. This video provides an introduction to latent growth curve modeling and how it may be applied to longitudinal data.
Duration: 6:50
Content created by: Yena Kyeong, Pamela Sheffler, Cecilia Cheung
Narrated by: Pamela Sheffler
Latent Growth Curve Modeling Example
Duration: 8:38
Content created by: Pamela Sheffler, Cecilia Cheung
Narrated by: Pamela Sheffler
Article discussed: Kaar, J. L., Schmiege, S. J., Kalkwarf, H. J., Woo, J. G., Daniels, S. R., & Simon, S. L. (2020). Longitudinal assessment of sleep trajectories during early childhood and their association with obesity. Childhood Obesity, 16(3), 211-217. https://doi.org/10.1089/chi.2019.0126
Power Analysis Overview
Description: Statistical power refers to the probability of correctly detecting a true effect. Power analysis speaks to the validity of a study's results and is an essential step in good research design. This video provides an introduction to power and power analysis.
Duration: 9:11
Content created by: Pamela Sheffler, Cecilia Cheung
Narrated by: Pamela Sheffler
G*Power link: https://www.psychologie.hhu.de/arbeitsgruppen/allgemeine-psychologie-und-arbeitspsychologie/gpower
Power Analysis Example
Duration: 9:33
Content created by: Pamela Sheffler, Cecilia Cheung
Narrated by: Pamela Sheffler
G*Power link and article: https://www.psychologie.hhu.de/arbeitsgruppen/allgemeine-psychologie-und-arbeitspsychologie/gpower
Faul, F., Erdfelder, E., Lang, A.-G., & Buchner, A. (2007). G*Power 3: A flexible statistical power analysis program for the social, behavioral, and biomedical sciences. Behavior Research Methods, 39, 175–191. https://doi.org/10.3758/BF03193146
Transactional Models Overview
Description: Transactional models are used to examine dynamic relationships between variables. Researchers often apply this type of model to longitudinal data to assess causal effects and influences over time. This video provides an introduction to transacational models, with a special focus on cross-lagged panel models, a popular type of transactional model that requires a lag between timepoints.
Duration: 8:22
Content created by: Pamela Sheffler, Cecilia Cheung
Narrated by: Pamela Sheffler