In our department, experimental research is becoming more and more common. Doing experimental research and analyzing data requires some knowledge about methodology and statistics.
Statistical consultation – who is it for?
For ILS researchers we have a statistics adviser, to help guide you through the abundant possibilities and resources and advise you on research design, and which methods and statistical analysis to use. The statistics advisor is Kirsten Schutter.
If you are a BA, MA or RMA student in need of statistical advice, you should be getting it from your supervisor, not from the statistics adviser.
Tip: Kirsten organizes monthly meetings where researchers can present and discuss their quantitative research design. Research master students can sign up for these events to present and discuss their design. These meetings are announced in the ILS newsletter.
How does statistical consultation work?
What to expect when you make an appointment with our statistics adviser
To get an overview of your study, the following topics will (have to) be discussed:
- Methodology: What does your research design look like? This includes your research question, hypotheses/predictions, research population, variables of interest, operationalization of variables.
- Statistics: What type of analysis do you need in order to answer your research question(s)? If you have already collected data: Is your data appropriate for answering your research question and the desired statistical analysis?
The extent to which these topics need to be discussed depends on the stage your study is in, and your level of methodological and statistical knowledge/skills. You can expect the statistics adviser to help you:
- Optimize your research question;
- Create a study design that is optimal for answering your research question;
- Decide on the appropriate statistical analysis;
- Decide what statistical software to use (e.g., SPSS or R);
- Interpret the results of statistical analyses;
- Find relevant literature and/or (online) courses on methodology/statistics.
This implies that:
- You should have some basic statistical knowledge to build on. Some references to get you started can be found below.
- If you do not (yet) have a lot of statistical knowledge it is recommended that you avoid formulating complicated research questions that require advanced statistical modeling. The statistics adviser can look through your questions with you to check that you have adequate knowledge to deal with them.
- Even though the statistics adviser provides help and coaching, you as a researcher bear full responsibility for your study, including any methodological and statistical aspects. This implies that you should familiarize yourself with the methodological and statistical topics that concern your study. You can of course ask the statistics adviser for references, but you are expected to also look for any relevant literature yourself, and digest it. You should not expect the statistics adviser to take over the statistical part of your study, or to teach you complicated methods that go beyond your own knowledge.
Some references to get you started:
- A book on experimental methods (in Language acquisition research):
Blom, E., & Unsworth, S. (Eds.). (2010). Experimental methods in language acquisition research. Amsterdam/Philadelphia: John Benjamins Publishing.
- Coursera course on the basics of quantitative research methods:
- Statistics book with SPSS examples in linguistics (you can read it online via UB):
Eddington, D. (2015). Statistics for Linguists: A Step-by-Step Guide for Novices. Cambridge: Cambridge Scholars Publishing.
- A book on experimental methods (in social sciences):
Field, A., & Hole, G. (2002). How to design and report experiments. London: Sage.
- Statistics book with SPSS examples in social sciences:
Field, A.P. (2013). Discovering statistics using IBM SPSS Statistics (4th ed.). London: Sage.
- Statistics book with R examples in social sciences:
Field, A.P., Miles, J. & Field, Z. (2012). Discovering statistics using R. London: Sage.
- Very accessible tutorial for linear models and linear mixed effects models in R:
Winter, B. (2013). Linear Models and Linear Mixed Effects Models in R With Linguistic Applications. arXiv preprint arXiv:1308.5499
- Website with step-by-step tutorials for a lot of basic analyses in SPSS, including a ‘Statistical Test Selector’ – you pay a small fee for 1/3/6 months access:
- Handy website ‘Choosing the correct statistical test in SAS, Strata, SPSS and R’:
- A free online Multilevel modelling course from Bristol University:
- Articles about the importance of sample size and power and examples for application:
Anderson et al. (2017). Sample-Size Planning for More Accurate Statistical Power: A Method Adjusting Sample Effect Size for Publication Bias And Uncertainty. Psychological Science, 28, 1547-1562.
Lenth, R. V. (2001). Some Practical Guidelines for Effective Sample Size Determination. The American Statistician, 55, 187-193
- An introduction to the theory of mixed models:
This set of modules offers you and introduction into common concepts in statistics, helps you find the correct way to analyse your data and helps you to apply these methods in both SPSS and R. The modules are written by Laura Boeschoten, and are still under development. If you have any remarks, please let the current statistics advisor know. The modules are based on the following literature:
- Gravetter, F. J., & Wallnau, L. B. (2008). Statistics for the behavioral sciences, 6th edition. London: Thomson Wadsworth.
- Peck, R., & Devore, J. (2008). Statistics, The exploration and Analysis of Data, 6th edition. Belmont: Thomson Brooks/Cole.
- Field, A. (2013). Discovering statistics using IBM SPSS Statistics, 4th edition. London: Sage.
- Field, A., Miles, J. & Field, Z. (2012). Discovering statistics using R. London: Sage.
The datasets used in the modules are provided by Andy Field.
Please note that the modules are mainly for reference after a consultation with the statistics adviser; as noted in the how-to for planning an experiment.
|0||Step by step guide into performing statistical analysis|
|1||Introduction to Statistics||Data|
|7||Probability and Samples|
|8||Introduction to Hypothesis Testing|
|9||The correlational method||Data|
|10||A Chi Square Test of Independence||Data|
|11||Introduction to the t Statistic|
|12||The t Test for Two Independent Samples||Data|
|13||The paired samples t test||Data|
|14||Introduction to Analysis of Variance|
|15||One Way ANOVA||Data|
|16||Repeated Measures ANOVA||Data|