91Ó°ÊÓ

In a chi-square test, the concept of **expected frequency** is crucial. Expected frequency is the number of occurrences that we expect to find in each category, assuming the null hypothesis is true. We use this to compare against our observed data.
For our M&Ms example, if the manufacturer claims that 13% of the M&Ms should be brown, and we have 400 M&Ms in total, the expected number of brown M&Ms is calculated by: \ \(Expected~Brown = 0.13 * 400 = 52\).
We repeat this for each color: \ - Expected Yellow = 0.14 * 400 = 56 \ - Expected Red = 0.13 * 400 = 52 \-Expected Blue = 0.24 * 400 = 96 \ - Expected Orange = 0.20 * 400 = 80 \ - Expected Green = 0.16 * 400 = 64.
These expected numbers help us to understand if the observed frequencies deviate significantly from what we would anticipate.

The **null hypothesis** (often written as \(H_0\)) in statistical testing is our starting assumption. It usually states that there is no effect or no difference. For the M&Ms example, the null hypothesis is that the color distribution of the M&Ms in the bag follows the manufacturer's stated percentages.
This means that we assume the proportions they provided (13% brown, 14% yellow, etc.) are accurate, and any deviations in our sample are just due to random chance.
If our data strongly contradicts the null hypothesis, we have grounds to reject it, concluding that the actual distribution may be different from what the manufacturer claims.

In a chi-square test, **degrees of freedom** (df) are important because they help us determine the critical value from the chi-square distribution table.
The degrees of freedom in our test are calculated by taking the number of categories and subtracting one. For our M&Ms data, we have 6 colors, so df = 6 - 1 = 5.
The degrees of freedom reflect the number of values that are free to vary, considering we are using the data to estimate parameters. A higher number of degrees of freedom typically indicates a larger dataset and usually leads to more reliable results.

The **significance level** (often denoted by \(\alpha\)) is the threshold at which we decide whether to reject the null hypothesis. It represents the probability of rejecting the null hypothesis when it is actually true (a type I error).
Common significance levels are 0.05, 0.01, or 0.10. For the M&Ms example, we use \(\alpha = 0.05\), meaning we are willing to accept a 5% chance of wrongly rejecting the null hypothesis.
We compare our chi-square test statistic to the critical value corresponding to our significance level and degrees of freedom from the chi-square table. If our test statistic is greater than the critical value, we reject the null hypothesis.

The chi-square test is a form of **statistical hypothesis testing** used to see if there's a significant difference between the observed frequencies and the expected frequencies. This kind of testing involves the following steps:
1. State the null and alternative hypotheses. \ - \(H_0\): There is no significant difference between the observed and expected frequencies. \-\(H_a\): There is a significant difference between the observed and expected frequencies.
2. Calculate the expected frequencies based on the null hypothesis.
3. Use the chi-square formula \[ \chi^2 = \sum \frac{(O_i - E_i)^2}{E_i} \] where \(O_i\) is observed frequency and \(E_i\) is expected frequency.
4. Determine the degrees of freedom and find the critical value from the chi-square table.
5. Compare the calculated chi-square value to the critical value and make a decision.
6. Conclude whether to reject or fail to reject the null hypothesis based on this comparison.
This structured approach allows us to make objective decisions about the data.