Petri Nokelainen (petri.nokelainen@tuni.fi)
Lectures [PPT]
Articles
1. Cross-sectional multilevel modeling3. t-test, M-W U-test, regression analysis, ANOVA
Abelson,
R. P. (1995). Statistics as Principled Argument. Hillsdale, NJ: Lawrence
Erlbaum Associates.
Booth,
W. C., Colomb, G. G., Williams, J. M., Bizup, J., & Fitzgerald, W. T.
(2016). The
Craft of Research. Fourth edition. Chicago: The University of Chicago
Press.
Jackson, S. (2006).
Research Methods and Statistics. A Critical Thinking Approach. Second
edition. Belmont, CS: Thomson.
Bannan-Ritland, B.
(2003). The Role of Design in Research: The Integrative Learning Design
Framework. Educational Researcher, 32(1), 21-24.
Tabachnick,
B., & Fidell, L. (2013). Using
Multivariate Statistics. Sixth edition. Essex: Pearson.
Thiese, M. (2014). Observational and interventional study design types; an
overview. Biochemia Medica, 24(2), 199-210.
Tirri,
K., Nokelainen, P., & Komulainen, E. (2013).
Multiple intelligences: Can they be measured?
Psychological Test and Assessment Modeling, 55(4), 438-461.
Wasserman, L.
(2004). All of Statistics. A Concise Course in Statistical Inference.
New York: Springer.
Wickrama, K.,
Kyoung Lee, T., Walker O’Neal, C., & Lorenz, F. (2016). Higher Order Growth Curves and Mixture Modeling
with Mplus. New
York: Routledge.
Different types of variables
categorical (nominal, ordinal) and continuous (interval,
ratio), independent (IV) and dependent (DV)
To
compare differences between groups
two groups: t-test
(normal distribution) or Mann-Whitney U-test (non-normal distribution)
more than two groups: Analysis of variance (ANOVA, normal distribution) or Kruskal-Wallis H-test (non-normal distribution)
multivariate approach to analyse differences between groups and predict group
membership: linear discriminant analysis (multivariate normal
distributions, linear relationships)
To
investigate associations between variables
correlation: Pearson product moment (interval or ratio scale, normal
distribution, linear relationship, no outliers) or Spearman rank order (ordinal, interval or ratio scale,
monotonous relationship)
To
predict dependent variable values
regression: linear (interval or ratio scale, normal distribution,
linear relationship, no outliers) or logistic (DV: dichotomous, IV(s): categorical or
continuous, linear relationship between DV and IV(s))
To
reduce number of variables
principal component analysis
1. Write a 2000 word essay where you evaluate the design approaches of
three articles that you have selected.
Minimum requirement is that you base your evaluation on the lecture material,
but you are encouraged to use other sources (e.g., books or articles provided
in the lecture). The essay should begin with a short overview of the three
selected articles (e.g., describing their topic, research questions) and then
provide analysis of their designs (e.g., cross-sectional or longitudinal
design, what kind of samples and methods are used to answer to the research
questions). You need to create a reference list at the end of the essay and
have in-text citations in APA
style.