Scribd
Upload
50 views2 pages

Embry 7.2 Assignment

The document outlines solutions for RSCH 665 Module 7 assignments, including a Chi-Square Goodness of Fit test for prototype preferences and a Chi-Square test for independence regarding pilots' reaction times to antihistamines. It discusses when to use non-parametric analysis over parametric analysis and lists disadvantages of non-parametric methods. Additionally, it matches non-parametric tests with their parametric counterparts.

Uploaded by

yz7f4c9542
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as DOCX, PDF, TXT or read online on Scribd
50 views2 pages

Embry 7.2 Assignment

The document outlines solutions for RSCH 665 Module 7 assignments, including a Chi-Square Goodness of Fit test for prototype preferences and a Chi-Square test for independence regarding pilots' reaction times to antihistamines. It discusses when to use non-parametric analysis over parametric analysis and lists disadvantages of non-parametric methods. Additionally, it matches non-parametric tests with their parametric counterparts.

Uploaded by

yz7f4c9542
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as DOCX, PDF, TXT or read online on Scribd
You are on page 1/ 2

Solutions to RSCH 665 Module 7

Assignment
Question 1
A Chi-Square Goodness of Fit test can be used to determine if one of the four prototypes is
significantly preferred by the participants. To perform the five-step hypothesis test:

1. State the hypotheses:


- H0 (null hypothesis): The participants equally prefer all four prototypes.
- H1 (alternative hypothesis): Participants prefer one or more prototypes over others.

2. Level of significance (α): We can set α = 0.05.

3. Calculate the expected frequencies:


- The total number of participants is 120, and if all prototypes are equally preferred, each
prototype would have an expected frequency of 30 (120/4).

4. Compute the test statistic: Use StatCrunch to input the observed values [18, 51, 27, 21],
compare them with the expected values [30, 30, 30, 30], and calculate the Chi-Square value.

5. Make a decision: Compare the Chi-Square value to the critical value for 3 degrees of
freedom at α = 0.05 and determine whether to reject or fail to reject the null hypothesis.

Question 2
To address the research study about reaction times for pilots taking antihistamines, we use
the following steps:

- Construct a contingency table based on the given data:


| | Taking Medication | Not Taking Medication |
| Adequate | 13 | 11 |
| Inadequate |9 | 11 |

- Use a Chi-Square test for independence to determine if the reaction time is independent of
taking antihistamines.
- Results: Calculate the Chi-Square statistic using the contingency table and note the degrees
of freedom.
- Problems: The small sample size limits the statistical power of the test, and the results may
not generalize well. A larger sample size would improve the reliability of the findings.
Question 3
Three cases where non-parametric analysis should be used instead of parametric analysis
are:
1. When the data does not follow a normal distribution.
2. When the sample size is too small to reliably estimate parameters.
3. When the data is ordinal, ranked, or categorical, rather than continuous and interval-
scaled.

Question 4
Disadvantages of using non-parametric analysis versus parametric analysis include:
1. Non-parametric tests are generally less powerful than parametric tests when the
assumptions of parametric tests are met.
2. Non-parametric tests may provide less precise estimates of population parameters.
3. Results from non-parametric tests are often harder to interpret as they do not estimate
the effect size in the same way as parametric tests.

Question 5
Matching the non-parametric versions of analysis with their parametric equivalents:
1. Mann-Whitney U -> Independent sample t-test
2. Kruskal-Wallis -> One-Way ANOVA
3. Wilcoxon Signed Rank -> Paired sample t-test
4. Friedman -> Repeated measures ANOVA
5. Spearman’s Rank -> Pearson correlation

You might also like