Question

how can power and confidence of results be increased using t test ( one sample t test, 2-independent and paired samples t test).

Answer 1

1)You want to test if a medication lowers cholesterol. You sampled 32 subjects, and obtained their cholesterol levels at baseline, and then again after 4 weeks on medication.

Dependent samples,hence paired Sample t test will be used

2). Annual salary information was collected from doctors from 4 specialities- 5 radiologists, 6 cardiologists, 7 neurologists, and 4 oncologists. How would you test if there was a difference in salary among the specialities

ANOVA will be used,as we will be testing mean salary of all groups are equal or not.

3)Daily caloric intake was sampled on 45 people. What test would you use to see if the data is normally distributed

The Shapiro-Wilk test for normality is available when using the Distribution platform to examine a continuous variable. The null hypothesis for this test is that the data are normally distributed. The Prob < W value listed in the output is the p-value.

4) SAT scores were sampled in 131 students. You believe the students scored higher than the national average of 1020. What test would you use

One sample t-test

5) Data is collected on daily exercise (in minutes) and weight. You want to test if there is a relationship between the two variables, and more specifically, to quantify this relationship. What test would you use

Linear Regression(to quantify the relationship)

(Note :Chi square test of independence is used only to check whether variables are independent or dependent)