1 / 32

Research Skills

Research Skills. Week 9: Regression. Last week. Looked at data from maths questionnaire. Hypotheses. Chi-Square problem sheet. Today. Lab report reminders. Regression problem sheet. Word limit: 2000 (not including title, abstract, or references). Title.

lorant
Télécharger la présentation

Research Skills

An Image/Link below is provided (as is) to download presentation Download Policy: Content on the Website is provided to you AS IS for your information and personal use and may not be sold / licensed / shared on other websites without getting consent from its author. Content is provided to you AS IS for your information and personal use only. Download presentation by click this link. While downloading, if for some reason you are not able to download a presentation, the publisher may have deleted the file from their server. During download, if you can't get a presentation, the file might be deleted by the publisher.

E N D

Presentation Transcript

  1. Research Skills Week 9: Regression.

  2. Last week • Looked at data from maths questionnaire. • Hypotheses. • Chi-Square problem sheet.

  3. Today • Lab report reminders. • Regression problem sheet.

  4. Word limit: 2000 (not including title, abstract, or references)

  5. Title • Straightforward and informative (not more than 15 words) • Enough to explain your study without going into too much detail • Examples: • Too little detail: Fast food purchases • Too much detail: Differences in the fast food purchasing habits of men and women in the last month in Brighton • Just right: Differences in the fast food purchasing habits of men and women 2 marks: identifies the IV and DV, not too vague or too long, encapsulates the purpose of the report well.

  6. Abstract • Must have: • Explanation of research area • Aims • Main results and interpretations • Implications of your results for science and/or society • 100-150 words 8+ marks: clear and succinct (150 words at most) summary of the aims, methods, results and conclusions of the study. Includes all the necessary information, and is well written.

  7. Introduction • Quick explanation of research area • Summary of relevant past research (and perhaps its flaws) • Purpose of study • Brief description of methods • Hypothesis • 650-700 words 15+ marks: clearly written, well structured, with evidence of relevant extra reading, flows well. Identifies the main aims, and ends with a clear outline of the study's hypotheses. Also has something novel in it, compared to the handouts that were supplied, and includes the rationale for performing the study.

  8. Method • Give enough information so that it is obvious what you did • Subsections: • Participants • Materials • Design • Procedure Write in paragraphs (no lists!)

  9. Participants • Number of participants • Sex (# of men, # of women) • Who (students, women, the retired, etc) • Volunteers or paid? • Any other demographics that might be necessary

  10. Materials • Things you used: • Questionnaire (do not include the whole thing!) • Any other materials you think are necessary to include • DON’T INCLUDE: Pen, A4 paper, etc.

  11. Design • Identify: • Independent variable(s) • Dependent variable(s) • Design: within-subjects, between-subjects or mixed? • Don’t worry about this section this term • Just say you used a questionnaire design

  12. Procedure • Explain how the experiment was carried out • Step by step breakdown of what was done • Informed consent

  13. Results • Inferential statistics (Chi-Square test; regression; correlation). • Figure (Chi-square – frequency; regression/correlation – scatter plot). • N.B. if it’s a bar chart report the Frequencies/means & SEs in text.

  14. Frequency graph Figure 1: the frequency of monster attacks by Aliens and Predators in America, Britain and China.

  15. Scatter plot

  16. Discussion • Summary of purpose and results • Comparison to previous research • Possible faults • Wider implications (back up your assertions) • Future directions • Conclusions • 500-550 words 15+ marks: clear summary of main results, followed by a successful attempt to relate the findings to relevant previous theoretical and empirical research. Intelligent evaluation of the strengths, weaknesses and limitations of the study that was performed, and sensible suggestions for possible improvements and extensions to it. Well organised and clearly written.

  17. Other things: • APA formatting (references) • Purple prose • Orwell’s 6 rules

  18. Regression problem sheet

  19. Why use regression? Sooty suspects that his magic wand is prone to changing its length as the temperature varies: on cold days, he's sure that it's shorter than on warm days. He decides to investigate this, so on each of 50 days he measures the length of his wand with his little ruler.

  20. Click on Analyze> Descriptive Statistics> Descriptives…

  21. Put wand_length in variables window…

  22. Length of Sooty’s magic wand… • This suggests the length of Sooty’s wand is 63.50cm no matter what the temperature.

  23. Why use regression? Sooty suspects that his magic wand is prone to changing its length as the temperature varies: on cold days, he's sure that it's shorter than on warm days. He decides to investigate this, so on each of 50 days he measures the temperature with his little thermometer andmeasures the length of his wand with his little ruler.

  24. Temperature and the length of Sooty’s magic wand

  25. Predicted variable goes in here Predictor variable goes in here

  26. Normally, redo graphs in Excel – but for this scatterplot, edit it within SPSS (by double-clicking on the graph).

  27. A silly example... This baby is “temperature”. This chocolate cake represents all the variance in the length of Sooty’s wand

  28. We want to find out if temperature will eat up some of our chocolate cake (variance)... The proportion of cake (variance) that temperature eats is the R2 value

  29. Whatever is left of our chocolate cake is our unexplained variance (the variance that can’t be accounted for by temperature.

  30. ANOVA: is our model better than the mean at explaining the length of Sooty’s wand? Our model The mean

  31. ANOVA: is our model better than the mean at explaining the length of Sooty’s wand? Our model The mean

  32. Next week • Correlation problem sheet • Lab report Q & A

More Related