Chapter 11

  1. research questions
    used frequently in problem or policy-oriented studies where the researcher is not interested in testing the statistical significance of the findings
  2. exploratory research
    • researchers have no clear idea what they may find
    • they have no prior info to use for predictions
    • search for data indications rather than to attempt to find causality
    • gather preliminary data
  3. hypothesis
    • asks, "Do we have firm evidence that such-and-such is happening (or has happened)?"
    • only different from research questions in that it predicts an outcome
  4. null hypothesis (hypothesis of no difference)
    • asserts that the statistical differences or relationships discovered in an analysis are due to chance or random error
    • logical alternative to research hypothesis
  5. probability level (significance level)
    a predetermined value against which the null hypothesis is tested
  6. reject
    if the results of the study indicate a probability level lower than this level, the researcher can _____ the null hypothesis.
  7. fail to reject (accept)
    if the research outcome has a high probability, the researcher must _____ the null hypothesis.
  8. one-tail test
    • predicts that the results will fall in only one direction (either positive or negative)
    • used when researchers have knowledge of the area and are able to more accurately predict the outcome of the study
  9. two-tail test
    • does not predict a direction
    • used when little info is available about the research area
  10. statistically significant
    there is no difference in value between a study that finds _______________ results and a study that does not.
  11. Type I error (Alpha)
    • the rejection of a null hypothesis that should be accepted
    • under direct control of researcher
  12. Type II error (Beta)
    • the acceptance of a null hypothesis that should be rejected
    • no direct control
  13. power analysis
    • provides an estimate of the minimum number of respondents needed to provide the best chance to discover if something does or does not exist. 
    • indicates the probability that a stat test of a null hypothesis will conclude that the phenomenon under study actually exists
  14. effects size
    • the degree to which the null hypothesis is rejected
    • can be stated either generally or exactly
    • the larger, the greater the degree to which the phenomenon is present
  15. Cohen's D
    measures the effects size
Card Set
Chapter 11
research methods exam 3 chapter 11