Answer:
1. H0: P1 = P2
2. Ha: P1 ≠ P2
3. pooled proportion p = 0.542
4. P-value = 0.0171
5. The null hypothesis failed to be rejected.
At a signficance level of 0.01, there is not enough evidence to support the claim that there is significant difference between the exercise habits of Science majors and Math majors
.
6. The 99% confidence interval for the difference between proportions is (-0.012, 0.335).
Step-by-step explanation:
We should perform a hypothesis test on the difference of proportions.
As we want to test if there is significant difference, the hypothesis are:
Null hypothesis: there is no significant difference between the proportions (p1-p2 = 0).
Alternative hypothesis: there is significant difference between the proportions (p1-p2 ≠ 0).
The sample 1 (science), of size n1=135 has a proportion of p1=0.607.
![p_1=X_1/n_1=82/135=0.607](https://tex.z-dn.net/?f=p_1%3DX_1%2Fn_1%3D82%2F135%3D0.607)
The sample 2 (math), of size n2=92 has a proportion of p2=0.446.
![p_2=X_2/n_2=41/92=0.446](https://tex.z-dn.net/?f=p_2%3DX_2%2Fn_2%3D41%2F92%3D0.446)
The difference between proportions is (p1-p2)=0.162.
![p_d=p_1-p_2=0.607-0.446=0.162](https://tex.z-dn.net/?f=p_d%3Dp_1-p_2%3D0.607-0.446%3D0.162)
The pooled proportion, needed to calculate the standard error, is:
The estimated standard error of the difference between means is computed using the formula:
![s_{p1-p2}=\sqrt{\dfrac{p(1-p)}{n_1}+\dfrac{p(1-p)}{n_2}}=\sqrt{\dfrac{0.542*0.458}{135}+\dfrac{0.542*0.458}{92}}\\\\\\s_{p1-p2}=\sqrt{0.001839+0.002698}=\sqrt{0.004537}=0.067](https://tex.z-dn.net/?f=s_%7Bp1-p2%7D%3D%5Csqrt%7B%5Cdfrac%7Bp%281-p%29%7D%7Bn_1%7D%2B%5Cdfrac%7Bp%281-p%29%7D%7Bn_2%7D%7D%3D%5Csqrt%7B%5Cdfrac%7B0.542%2A0.458%7D%7B135%7D%2B%5Cdfrac%7B0.542%2A0.458%7D%7B92%7D%7D%5C%5C%5C%5C%5C%5Cs_%7Bp1-p2%7D%3D%5Csqrt%7B0.001839%2B0.002698%7D%3D%5Csqrt%7B0.004537%7D%3D0.067)
Then, we can calculate the z-statistic as:
![z=\dfrac{p_d-(\pi_1-\pi_2)}{s_{p1-p2}}=\dfrac{0.162-0}{0.067}=\dfrac{0.162}{0.067}=2.4014](https://tex.z-dn.net/?f=z%3D%5Cdfrac%7Bp_d-%28%5Cpi_1-%5Cpi_2%29%7D%7Bs_%7Bp1-p2%7D%7D%3D%5Cdfrac%7B0.162-0%7D%7B0.067%7D%3D%5Cdfrac%7B0.162%7D%7B0.067%7D%3D2.4014)
This test is a two-tailed test, so the P-value for this test is calculated as (using a z-table):
![\text{P-value}=2\cdot P(z>2.4014)=0.0171](https://tex.z-dn.net/?f=%5Ctext%7BP-value%7D%3D2%5Ccdot%20P%28z%3E2.4014%29%3D0.0171)
As the P-value (0.0171) is bigger than the significance level (0.01), the effect is not significant.
The null hypothesis failed to be rejected.
At a signficance level of 0.01, there is not enough evidence to support the claim that there is significant difference between the exercise habits of Science majors and Math majors
.
We want to calculate the bounds of a 99% confidence interval of the difference between proportions.
For a 99% CI, the critical value for z is z=2.576.
The margin of error is:
![MOE=z \cdot s_{p1-p2}=2.576\cdot 0.067=0.1735](https://tex.z-dn.net/?f=MOE%3Dz%20%5Ccdot%20s_%7Bp1-p2%7D%3D2.576%5Ccdot%200.067%3D0.1735)
Then, the lower and upper bounds of the confidence interval are:
![LL=(p_1-p_2)-z\cdot s_{p1-p2} = 0.162-0.1735=-0.012\\\\UL=(p_1-p_2)+z\cdot s_{p1-p2}= 0.162+0.1735=0.335](https://tex.z-dn.net/?f=LL%3D%28p_1-p_2%29-z%5Ccdot%20s_%7Bp1-p2%7D%20%3D%200.162-0.1735%3D-0.012%5C%5C%5C%5CUL%3D%28p_1-p_2%29%2Bz%5Ccdot%20s_%7Bp1-p2%7D%3D%200.162%2B0.1735%3D0.335)
The 99% confidence interval for the difference between proportions is (-0.012, 0.335).