Does college major depend on whether you are an athlete or not? A survey asks a group of college students about their majors. It also groups the students by whether they are athletes or not. The data are recorded in the contingency table below, and a chi-square Test of Independence at the [tex]$5\%$[/tex] significance level is performed.

\begin{tabular}{|c|c|c|c|c|}
\hline & Arts & Humanities & Sciences & Row Total \\
\hline Athlete & 17 & 24 & 15 & 56 \\
\hline Non-Athlete & 19 & 11 & 9 & 39 \\
\hline Column Total & 36 & 35 & 24 & 95 \\
\hline
\end{tabular}

(a) The null and alternative hypotheses are:
- [tex]$H_0$[/tex]: The two variables are independent, so being an athlete does not affect college major.
- [tex]$H_a$[/tex]: The two variables are dependent, so being an athlete does affect college major.

(b) Compute the test statistic, rounded to one decimal place. (Use expected frequencies that are also rounded to one decimal place.)



Answer :

To determine if there is a significant relationship between being an athlete and choosing a particular college major, we can perform a Chi-Square Test of Independence. Here is a detailed breakdown of the steps involved in this analysis:

### Step 1: Set Up the Hypotheses
The hypotheses for the Chi-Square Test of Independence are:
- Null Hypothesis ([tex]$H_0$[/tex]): The variables "being an athlete" and "major choice" are independent.
- Alternative Hypothesis ([tex]$H_a$[/tex]): The variables "being an athlete" and "major choice" are dependent.

### Step 2: Create the Contingency Table
We start with the given contingency table:

[tex]\[ \begin{array}{|c|c|c|c|c|} \hline \text{} & \text{Arts} & \text{Humanities} & \text{Sciences} & \text{Row Total} \\ \hline \text{Athlete} & 17 & 24 & 15 & 56 \\ \hline \text{Non-Athlete} & 19 & 11 & 9 & 39 \\ \hline \text{Column Total} & 36 & 35 & 24 & 95 \\ \hline \end{array} \][/tex]

### Step 3: Calculate the Expected Frequencies
The expected frequency for each cell in the contingency table is calculated using the formula:

[tex]\[ E_{ij} = \frac{(\text{Row Total for row } i) \times (\text{Column Total for column } j)}{\text{Grand Total}} \][/tex]

Where [tex]\(E_{ij}\)[/tex] represents the expected frequency for the cell in the [tex]\(i\)[/tex]-th row and [tex]\(j\)[/tex]-th column.

1. Arts:
- Athlete: [tex]\(\frac{56 \times 36}{95} \approx 21.2\)[/tex]
- Non-Athlete: [tex]\(\frac{39 \times 36}{95} \approx 14.8\)[/tex]

2. Humanities:
- Athlete: [tex]\(\frac{56 \times 35}{95} \approx 20.6\)[/tex]
- Non-Athlete: [tex]\(\frac{39 \times 35}{95} \approx 14.4\)[/tex]

3. Sciences:
- Athlete: [tex]\(\frac{56 \times 24}{95} \approx 14.1\)[/tex]
- Non-Athlete: [tex]\(\frac{39 \times 24}{95} \approx 9.9\)[/tex]

### Step 4: Compute the Chi-Square Test Statistic
The Chi-Square test statistic is calculated as follows:

[tex]\[ \chi^2 = \sum \frac{(O_{ij} - E_{ij})^2}{E_{ij}} \][/tex]

Where [tex]\(O_{ij}\)[/tex] is the observed frequency and [tex]\(E_{ij}\)[/tex] is the expected frequency.

Using the observed and expected frequencies:

1. Arts (Athlete): [tex]\(\frac{(17 - 21.2)^2}{21.2} \approx 0.832\)[/tex]
2. Arts (Non-Athlete): [tex]\(\frac{(19 - 14.8)^2}{14.8} \approx 1.181\)[/tex]

3. Humanities (Athlete): [tex]\(\frac{(24 - 20.6)^2}{20.6} \approx 0.557\)[/tex]
4. Humanities (Non-Athlete): [tex]\(\frac{(11 - 14.4)^2}{14.4} \approx 0.805\)[/tex]

5. Sciences (Athlete): [tex]\(\frac{(15 - 14.1)^2}{14.1} \approx 0.064\)[/tex]
6. Sciences (Non-Athlete): [tex]\(\frac{(9 - 9.9)^2}{9.9} \approx 0.082\)[/tex]

Adding these values together:

[tex]\[ \chi^2 = 0.832 + 1.181 + 0.557 + 0.805 + 0.064 + 0.082 \approx 3.521 \][/tex]

We round the final chi-square test statistic to one decimal place:

[tex]\[ \chi^2 \approx 3.5 \][/tex]

### Step 5: Interpret the Result
The test statistic [tex]\(\chi^2\)[/tex] is 3.5. This value would be compared to the critical value from the Chi-Square distribution table at the 5% significance level and with appropriate degrees of freedom (in this case, [tex]\((2-1) \times (3-1) = 2\)[/tex] degrees of freedom).

If the test statistic is less than the critical value, we do not reject the null hypothesis; hence, there is insufficient evidence to suggest that college major depends on whether a student is an athlete or not.

Given our test statistic of 3.5, we'd look up the critical value for [tex]\(\chi^2\)[/tex] with 2 degrees of freedom at the 5% significance level, which is approximately 5.991. Since 3.5 < 5.991, we fail to reject the null hypothesis.

Hence, we conclude that there is no strong evidence to suggest that being an athlete significantly affects the choice of college major.