In: Statistics and Probability
A team of researchers wanted to assess the effectiveness of the 4 components of a weight loss program by comparing the distribution of weight status across 4 different treatment groups. The data is summarized in the table below:
Weight Status |
|||
Intervention Component |
Normal Weight |
Overweight |
Obese |
Control Group (n=100) |
50 |
35 |
15 |
Calorie Counting (n=100) |
70 |
20 |
10 |
Physical Activity (n=100) |
73 |
15 |
12 |
Combination (n=100) |
80 |
15 |
5 |
Is there a difference in weight status by intervention component? (Hint: Are intervention component and weight status independent?) Run the appropriate test at a 5% level of significance.
Intervention Component | Normal Weight | Overweight | Obese | Total |
Control Group (n=100) | 50 | 35 | 15 | 100 |
Calorie Counting (n=100) | 70 | 20 | 10 | 100 |
Physical Activity (n=100) | 73 | 15 | 12 | 100 |
Combination (n=100) | 80 | 15 | 5 | 100 |
Total | 273 | 85 | 42 | 400 |
Null hypothesis : Ho : intervention component and weight status are independent
Alternate Hypothesis : Ha : intervention component and weight status are not independent
Test Statistic :
O : Observed Frequency
E: Expected Frequency
E :
Intervention Component | Normal Weight | Overweight | Obese | Total |
Control Group (n=100) | (100*273)/400 | (100*85)/400 | (100*42)/400 | 100 |
Calorie Counting (n=100) | (100*273)/400 | (100*85)/400 | (100*42)/400 | 100 |
Physical Activity (n=100) | (100*273)/400 | (100*85)/400 | (100*42)/400 | 100 |
Combination (n=100) | (100*273)/400 | (100*85)/400 | (100*42)/400 | 100 |
Total | 273 | 85 | 42 | 400 |
Intervention Component | Normal Weight | Overweight | Obese | Total |
Control Group (n=100) | 68.25 | 21.25 | 10.5 | 100 |
Calorie Counting (n=100) | 68.25 | 21.25 | 10.5 | 100 |
Physical Activity (n=100) | 68.25 | 21.25 | 10.5 | 100 |
Combination (n=100) | 68.25 | 21.25 | 10.5 | 100 |
Total | 273 | 85 | 42 | 400 |
O | E | (O-E) | (O-E)2 | (O-E)2/E |
50 | 68.25 | -18.25 | 333.063 | 4.88 |
70 | 68.25 | 1.75 | 3.0625 | 0.0449 |
73 | 68.25 | 4.75 | 22.5625 | 0.3306 |
80 | 68.25 | 11.75 | 138.063 | 2.0229 |
35 | 21.25 | 13.75 | 189.063 | 8.8971 |
20 | 21.25 | -1.25 | 1.5625 | 0.0735 |
15 | 21.25 | -6.25 | 39.0625 | 1.8382 |
15 | 21.25 | -6.25 | 39.0625 | 1.8382 |
15 | 10.5 | 4.5 | 20.25 | 1.9286 |
10 | 10.5 | -0.5 | 0.25 | 0.0238 |
12 | 10.5 | 1.5 | 2.25 | 0.2143 |
5 | 10.5 | -5.5 | 30.25 | 2.881 |
Total | 24.974 |
Compute the test statistic and indicate the outcome:
Ans : a. 24.974
Degrees of freedom =(Number of rows -1)(Number of columns -1) = (4-1)(3-1) = 3*2=6
p-value:
: 0.05
As p-value : 0.0000 less than the level of significance (0.05) Reject null hypothesis.;
Statistically significant evidence that intervention component and weight status are not independent.
We DO NOT have statistically significant evidence at α=0.05 to show that intervention component and weight status are not independent.
Ans:
a. True
p-value = 0.000
Most accurate p-value :
d. p < 0.005
even a p = not significant is also correct