Survey research and design in psychology/Assessment/Lab reports/2

From Wikiversity
Jump to navigation Jump to search

Lab report 2

Task[edit | edit source]

Describe and graph the correlational relationship between: (a) two variables, at least one of which has a nominal or ordinal level of measurement; and (b) two variables, neither of which have a nominal or ordinal level of measurement.

Marking criteria[edit | edit source]

In addition to the generic guidelines, this report should include:

  1. 5%. Title/Abstract: Provide a succint overview of the study.
    1. Sumarise the study's purpose, method, findings, and implications in less than 150 words.
  2. 10%. Introduction: Clearly introduce the topic and the hypotheses:
    1. 5%. Background: Briefly introduce the theoretical concepts and related research, using relevant academic citations
    2. 5%. Research questions: Propose logically-derived research question(s) (which are addressed in the Results)
  3. 10%. Method: Clearly explain how the study was conducted
    1. 5%. Participants:
      1. Provide a solid overall picture and description of the sample
      2. Note: It may be appropriate to provide detailed description of specific aspects of the sample in subsequent lab reports; only a general overview is required for this lab report
    2. 5%. Procedure:
      1. Describe the research procedure, with sufficient detail to permit critique of the methodology and full replication.
      2. Include an electronic APA style citation to the survey administration guidelines (but do not provide these in an appendix)
      3. Describe your own survey administration procedures and experiences (e.g., where/when/how did you collect data, response rate, anomalies (i.e., what didn't go according to plan, what could have unwittingly affected the results))
  4. 50%. Results: Appropriate tests conducted and reported in APA style
    1. 25%. Correlation 1: Describe and present descriptive statistics and graph(s) for the the correlational relationship between at least two variables, at least one of which has a nominal or ordinal level of measurement.
    2. 25%. Correlation 2: Describe and present descriptive statistics and graph(s) for the the correlational relationship between at least two variables, neither of which have a nominal or ordinal level of measurement.
  5. 25%. Discussion: Explain results and implications:
    1. Explain what the results indicate about the research question(s).
    2. Consider the implications of what was found.
    3. Comment on the strengths and weaknesses of the Procedure. How could it be (practically) improved?

General feedback[edit | edit source]

  1. Word count
    1. Many reports were over the word count. However, word count penalty was applied leniently (only for word count > 1000 words from Introduction to Discussion) due to an old link about word count on the coversheet (to 2011 guidelines). The coversheet word count link has been corrected to the 2012 guidelines. Word count penalty will be applied more strictly for Lab reports 3, 4 and 5.
    2. There was considerable discussion about this on the Moodle discussion forum in order to clarify what had happened, including explaining why the sample HD report was over the word count but not penalised, and to address the concerns of those who had followed the word count rules and felt that it was unfair that others were not penalised (effectively others had been allowed greater word count to address the marking criteria). The convener apologised for the error and explained that the decision had been taken towards being lenient in applying the word count penalty due to the error in having links to the 2011 word count guidelines (which were more lenient) on the assignment coversheet rather than the 2012 word count guidelines.
  2. APA style
    1. Use of APA style for reporting statistical results often not used (e.g., r and p etc. in italics, leaving spaces before and after = (treat it as a word in a grammatical sentence)
  3. Title
    1. A title page was sometimes not included
    2. A running head was often not included (put it in the header)
  4. Abstract
    1. Often the results were not clearly summarised
    2. Sometimes correlational results were confused as indicating a causal relationship between variables
  5. Introduction
    1. Often too long
    2. Should be focused on succintly reporting on the theoretical and/or research justification for each hypothesis/research question
  6. Method
    1. Participants:
      1. Often a simplistic description of the sample was provided
    2. Procedure:
      1. Generally well done
      2. The sampling method was often not described; many incorrectly described it as random sampling
      3. Often the survey admin guidelines were not referenced
      4. Sometimes the researcher's own procedure was not described in enough detail
  7. Results
    1. Generally well done
    2. Sometimes the wrong correlational tests were used (e.g., Pearson product-moment correlation instead of a chi-square test of contingencies)
    3. Sometimes bivariate graphs were not presented, and often these were not edited into APA style
    4. Often the direction, strength and statistical significance of the relationship between the variables was not clearly explained
    5. Coefficient of determination was often not reported and discussed
    6. Testing normality: Shapiro-Wilks is an overly sensitive test with a large sample size. Hence in this unit it has been recommended that to use skewness and kurtosis and visual inspection of a histogram to determine whether normality assumptions are met.
  8. Discussion
    1. Generally well done
    2. Sometimes causality was assumed - be wary of interpreting correlations as causality
    3. Stronger discussions explained how methodological limitations may have affected the results in the current study; weaker discussions tended to more vague and general about study limitations
  9. Formatting
    1. Often multiple line spaces were used instead of page breaks