Home Coursework Help WhatsApp Us About us

Posts under category Experimental statistics

Data Analysis Using Minitab
(Using Minitab Answer the following) Consider a manufacturing plant that produces high-quality products primarily using skilled labor. They are concerned about defects found in the surface coating for their product and have been exploring potential improvement strategies. Note that each prompt below may require more than one visualization and/or analysis to fully answer.

  1. Previous study showed that there is a difference in Quality ratings based on the Team. Considering this, they would like to test four potential factors (Line, Method, Temperature, and Humidity) while controlling for the effect of Team. Using the provided data, create a 2k factorial model by restructuring the Method factor as two, two-level factors and treating Team as a four-level blocked variable. Use Minitab to generate a 25-2 model blocked by replicates and extract the relevant data from the provided dataset to complete the analysis. Discuss the validity, fit, and reliability of the model and interpret the results including addressing any important aliased relationships.
  2. Identify the treatment combinations that would be needed to complete the full fold-over for this design and briefly discuss how the fold-over model would help to interpret the results from Part 2. Complete the full fold-over, discuss the validity, fit, and reliability of the model, and interpret the results.
  3. Use a general full factorial DOE model to evaluate the original five factors using their defined levels (a mixed-level design). Discuss the validity, fit and reliability of the model and interpret the results.

Understanding Validity

  1. What is experimental control?
    a. Ensuring that noting happens in an experiment without the experimenter knowing about it.
    b. Ensuring that every subject gets to experience every condition in the experiment.
    c. Ensuring that measures are made correctly and precisely.
    d. Ensuring that systematic differences in observed responses can be attributed to systematic changes in manipulated factors.
    e. None of the above
  2. Which of the following are examples of potential confounds? (Mark all that apply.)
    a. In website A/B test, every visitor was different from every other visitor.
    b. In a website A/B test, males all saw website “A” and females saw Website “B”.
    c. In a website A/B test, every visitor hitting the site before noon saw website “A”, while every visitor hitting the site after noon saw website “B”
    d. In a website A/B test, site “A” was different from site “B”
    e. In a Website A/B test, sites “A” and “B” were measured a second time with a new batch of visitors, just to be sure.
  3. Ecological validity and experimental control cannot bot be maximized.
    a. True
    b. False
  4. Which of the following was not an option discussed in lecture for handling a potential confound?
    a. Manipulate it, systematically vary it to see if doing so causes systematic changes in the response.
    b. Control for it – ensure that its effects are spread evenly across all subjects.
    c. Measure it – at least record its value so it cant be later examined for possibly having had an effect
    d. Hide it – don’t let subjects encounter it in the first place
    e. All of the above are options
  5. Which of the following is not another term for the response in an experiment?
    a. Dependent variable
    b. Measure
    c. Outcome
    d. Y
    e. Factor
  6. Which of the following are assumptions of ANOVA? (Mark all that apply.)
    a. Reliability of residuals
    b. Normality
    c. Homoscedasticity
    d. Independence
    e. Homogeneity of variance
  7. Which of the following was not a common data distribution reviewed in lecture?
    a. Normal
    b. Lognormal
    c. Bimodal
    d. Exponential
    e. Gamma
    f. Poisson
    g. Binomial
    h. Multinomial
  8. For what kind of experiment would a multinomial distribution be relevant?
    a. For an experimental in which the response is categorical with more than two categories
    b. For an experiment in which the response is bimodal
    c. For an experiment in which the response is scalar.
    d. For an experiment in which the response is Poisson
    e. None of the above
  9. Most precisely, parametric analyses differ from nonparametric analyses in what way?
    a. Parametric analyses operate on ranks.
    b. Parametric analyses make assumptions about the spread of data.
    c. Parametric analyses make assumptions about the distribution of the response within the population
    d. Parametric analyses are easier to use.
    e. None of above
  10. Typically, an advantage of parametric analyses over nonparametric analyses is statistical power, i.e the ability to detect differences.
    a. True
    b. False
  11. Nonparametric analyses must meet the three assumptions of ANOVA
    a. True
    b. False
  12. Nonparametric analyses typically operate on ranks.
    a. True
    b. False