Hypothesis Testing and Two-Group t-Test
Name
University of
PSYCH/625: Statistics for The Behavior Sciences
Name
August 24, 2020
Statistics Project, Part 2: Hypothesis Testing and Two-Group t-Test
Null Hypothesis. (H0): There is no statistically significant difference in the average score of workplace happiness between males and females.
Alternate Hypothesis (H1): There is a statistically significant difference in the average score of workplace happiness between male and female.
Independent sample t-test suits this type of analysis since male and females are two independent groups. The same “treatment” subjected to the two groups is workplace happiness rating.
The independent sample T-test was conducted to test if the workplace happiness rating among males and females are significantly different. The average score among 24 males was found to be 7.167, with a standard deviation of 1.659 whereas the average score among 26 males was found to be 7.62, with a standard deviation of 1.134 (Table 1). When equal variances between the two groups are assumed, the t-test results indicated that the difference is not statistically significant at 5 per cent level (t (48) = -1.124,p=0.267). Therefore, the null hypothesis is rejected, leading to the conclusion that there is no statistically significant difference in the average score of workplace happiness rating between males and females. The results imply that regardless of gender, employees have the same degree of workplace happiness.
Table 1: Independent T-Test Results
Male Female
Mean 7.167 7.615
Variance 2.754 1.286
Observations 24 26
Pooled Variance 1.989
Hypothesized Mean Difference 0
Df 48
t Stat -1.124
P(T<=t) one-tail 0.133
t Critical one-tail 1.677
P(T<=t) two-tail 0.267
t Critical two-tail 2.011
Note: Outcome variable: workplace happiness rating
Reference
Jackson, S. L. (2017). Statistics plain and simple, (4th ed.). Boston, MA: Cengage Learning.
Reinard, J. (2006 – Write a paper; Professional research paper writing service – Best essay writers). Communication research statistics. Thousand Oaks, Calif.; London: SAGE.
Chi-Square Worksheet
Part 1: Interpret Chi-Square Results
Review the following output from a chi-square test, and answer the questions below.
Chi-Square Test Frequencies:
Preference
Observed N Expected N Residual
Nuts & Grits 9 20.0 -11.0
Bacon Surprise 27 20.0 7.0
Dimples 16 20.0 -4.0
Froggy 17 20.0 -3.0
Chocolate Delight 31 20.0 11.0
Total 100
Test Statistics
Preference
Chi-Square 15.800a
df 4
Asymp. Sig. .003
a 0 cells (0.0%) have expected frequencies less than 5. The minimum expected cell frequency is 20.0.
Answer the following questions about this chi-square output in one to two sentences each:
1. How many categories are listed for analysis?
2. What is the expected N size?
3. What is the chi-square value?
4. How many degrees of freedom are there?
5. What it the test statistic and what does it tell you about the probability?
Part 2: Conduct a Chi-Square Test
Imagine you are the manager of a non-profit business, and you are looking to hire a recent college graduate. You list the position as paying $20,000/year. After interviewing candidates you decide that some will be offered the expected salary, while some will be offered more because of experience and interviewing skills. Others will be offered less than expected until they can demonstrate competence and their salary will increase when they are fully qualified.
Using Microsoft® Excel®, run a chi square Goodness of Fit test to determine whether these observed starting salaries are significantly different. What do the findings tell you?
Write a 75- to 100-word summary to describe your results.
Paste your Microsoft® Excel® output below your summary.
Expected Salaries Observed Salaries
Applicant 1 $20,000 $17,500
Applicant 2 $20,000 $20,000
Applicant 3 $20,000 $22,000
Applicant 4 $20,000 $20,500
Applicant 5 $20,000 $20,000
