Chapter 10- Chi-Square Tests and One-Way ANOVA: Study Notes

Chi-Square Tests

Chi-Square Goodness-of-Fit Test

The chi-square goodness-of-fit test is used to determine whether the observed frequencies in categorical data match expected frequencies derived from a specific hypothesis. This test is commonly applied when assessing whether a sample distribution fits a theoretical distribution.

• Observed Frequencies (O): The actual counts obtained from the sample.

• Expected Frequencies (E): The counts expected under the null hypothesis, often based on equal proportions or known population proportions.

Example: Suppose a survey of 200 students yields the following distribution by year:

• First year: 60

• Second year: 45

• Third year: 52

• Fourth year: 43

If equal representation is expected (50 per year), the test evaluates whether the observed distribution significantly deviates from this expectation.

Hypotheses

• Null hypothesis (H0): O = E (Observed frequencies match expected frequencies)

• Alternative hypothesis (Ha): O ≠ E (Observed frequencies differ from expected frequencies)

Test Statistic

The test statistic is calculated as:

$\chi^2 = \sum \frac{(O - E)^2}{E}$

where O is the observed frequency and E is the expected frequency for each category.

Degrees of Freedom

The degrees of freedom (df) for the test is:

$df = k - 1$

where k is the number of categories.

Decision Rule

• Choose a significance level (α), commonly 0.05.

• Compare the calculated $\chi^2$ value to the critical value from the chi-square distribution table with the appropriate degrees of freedom.

• If $\chi^2$ is greater than the critical value, reject H0.

Conditions for Validity

• Observed frequencies must be from a random sample.

• Each expected frequency should be at least 5.

Summary Table: Steps in the Chi-Square Goodness-of-Fit Test

1. Verify random sampling and minimum expected frequency.

2. State the hypotheses (H0 and Ha).

3. Specify the significance level (α).

4. Calculate the test statistic $\chi^2$.

5. Determine the degrees of freedom and critical value.

6. Compare $\chi^2$ to the critical value and make a decision.

7. Interpret the result in context.

Chi-Square Test of Independence

The chi-square test of independence is used to determine whether two categorical variables are independent in a population. Data are organized in a contingency table (cross-tabulation).

• Null hypothesis (H0): The variables are independent.

• Alternative hypothesis (Ha): The variables are not independent.

Expected frequency for each cell:

$E_{ij} = \frac{(\text{Row total})_i \times (\text{Column total})_j}{\text{Grand total}}$

Degrees of freedom:

$df = (\text{number of rows} - 1) \times (\text{number of columns} - 1)$

The test statistic is calculated as in the goodness-of-fit test, and the decision is made by comparing to the critical value from the chi-square table.

Analysis of Variance (ANOVA)

Introduction to ANOVA

Analysis of Variance (ANOVA) is a statistical method used to compare means across three or more groups. The one-way ANOVA tests whether there are significant differences among group means by analyzing the variance within and between groups.

• Factor: The independent variable (e.g., teaching method).

• Levels: The different groups or categories of the factor.

ANOVA is preferred over multiple t-tests to control the overall Type I error rate.

Assumptions of One-Way ANOVA

• Each sample is randomly selected from a normal (or approximately normal) population.

• Samples are independent of each other.

• Population variances are equal (homogeneity of variance).

Steps in Performing a One-Way ANOVA

1. Verify assumptions (randomness, normality, equal variances).

2. State the hypotheses:

   • H0: All group means are equal ($\mu_1 = \mu_2 = \ldots = \mu_k$)

   • Ha: At least one group mean differs

3. Specify the significance level (α).

4. Calculate the test statistic (F):

   • Find the mean and variance of each sample.

   • Find the grand mean (mean of all data).

   • Compute the sum of squares between groups ($SS_B$) and within groups ($SS_W$).

   • Calculate mean squares:

     • $MS_B = SS_B / (k-1)$

     • $MS_W = SS_W / (N-k)$

   • Compute the F statistic:

     $F = \frac{MS_B}{MS_W}$

5. Determine the degrees of freedom:

   • Numerator: $df_N = k-1$

   • Denominator: $df_D = N-k$

6. Compare the calculated F to the critical value from the F-distribution table.

7. Make a decision and interpret the result in context.

ANOVA Summary Table

The ANOVA summary table organizes the calculations and results for the one-way ANOVA test:

Variation	Sum of squares	Degrees of freedom	Mean squares	F
Between	$SS_B$	$df_N = k-1$	$MS_B = SS_B / df_N$	$F = MS_B / MS_W$
Within	$SS_W$	$df_D = N-k$	$MS_W = SS_W / df_D$

Additional info: The F-test in ANOVA is always right-tailed, and a significant result indicates that at least one group mean is different, but post-hoc tests are needed to determine which groups differ.