Week3 Discussion 1 Stats
Week3 Discussion 1 Stats
Thechosen question is ‘Do social workers with fewer cases have highersuccess rates?”.
Thisquestion requires an independent sample t-test. This is because thestudy is comparing the success rates between the social workers withfewer cases and the social workers with more cases. The variables inour research question are success rates which are continuous,quantitative and have an interval scale of measurement. This is adependent variable. The second variable is the type of social workerwith two categories, which are social workers with fewer cases andsocial workers with more cases. The type of social worker variablecategorical and has a nominal scale of measurement. This is anindependent variable.
Thesetwo variables fit the qualifications of the selected statisticaltest, which is the independent sample t-test (Lowry, 2014). This isbecause we have only one independent categorical variable with twolevels and one dependent continuous variable which are the successrates.
Hypothesis
Nullhypothesis (H0):There is no difference in success rates between social workers withfewer cases and the social workers with more cases.
Alternativehypothesis (H1):There is a difference in the success rates between social workerswith fewer cases and the social workers with more cases.
Typesof Errors
Thereare two types of errors that could occur:
Type 1 error, which will occur if we reject our null hypothesis yet it is true from our analysis. That is if we conclude that there is a difference in success rates among workers with less cases and social workers with more cases, yet the evidence suggests that there is no difference in the success rates between the two groups.
Type 2 errors, which will occur if we fail to reject our null hypothesis yet the evidence suggests that we should reject it. That is we conclude that there is no difference in the success rates between the social workers with less cases and the ones with more cases while the evidence suggests that there is a difference in the success rates between the two groups (Lieberman & Cunningham, 2009).
References
Lieberman,M. D., & Cunningham, W. A. (2009). Type I and Type II errorconcerns in fMRI research: re-balancing the scale. Socialcognitive and affective neuroscience,nsp052.
Lowry,R. (2014). Concepts and applications of inferential statistics.