Study Notes: Tests of Inference in Statistics

Tests of Inference in Statistics

Introduction to Statistical Inference

Statistical inference involves using data from a sample to draw conclusions about a population. Common inference procedures include hypothesis testing and estimation. These methods allow researchers to make decisions or predictions based on sample data, while accounting for variability and uncertainty.

• Hypothesis Testing: A formal procedure for comparing observed data with a claim (hypothesis) about a population parameter.

• Significance Level (α): The probability of rejecting the null hypothesis when it is actually true, commonly set at 0.05.

• P-value: The probability, under the null hypothesis, of obtaining a result as extreme or more extreme than the observed result.

Inference for Means

One-Sample t-Test for Means

This test is used to determine whether the mean of a single population differs from a specified value. It is appropriate when the population standard deviation is unknown and the sample size is small.

• Null Hypothesis (H0): $\mu = \mu_0$ (the population mean equals a specified value)

• Alternative Hypothesis (Ha): $\mu \neq \mu_0$, $\mu > \mu_0$, or $\mu < \mu_0$ (depending on the research question)

• Test Statistic: $t = \frac{\bar{x} - \mu_0}{s/\sqrt{n}}$ where $\bar{x}$ is the sample mean, $s$ is the sample standard deviation, and $n$ is the sample size.

• P-value: Calculated from the t-distribution with $n-1$ degrees of freedom.

Example: Testing whether the mean calcium level in healthy pregnant women differs from 10 mg/dl.

Inference for Two Means

Two-Sample t-Test

This test compares the means of two independent groups to determine if there is a statistically significant difference between them.

• Null Hypothesis (H0): $\mu_1 = \mu_2$

• Alternative Hypothesis (Ha): $\mu_1 \neq \mu_2$, $\mu_1 > \mu_2$, or $\mu_1 < \mu_2$

• Test Statistic: $t = \frac{\bar{x}_1 - \bar{x}_2}{\sqrt{\frac{s_1^2}{n_1} + \frac{s_2^2}{n_2}}}$ where $\bar{x}_1, \bar{x}_2$ are sample means, $s_1, s_2$ are sample standard deviations, and $n_1, n_2$ are sample sizes.

• P-value: Calculated using the t-distribution with appropriate degrees of freedom.

Example: Comparing ACT scores between juniors and seniors.

Inference for Proportions

One-Sample Proportion Test

This test is used to determine if the proportion of a certain outcome in a population differs from a specified value.

• Null Hypothesis (H0): $p = p_0$

• Alternative Hypothesis (Ha): $p \neq p_0$, $p > p_0$, or $p < p_0$

• Test Statistic: $z = \frac{\hat{p} - p_0}{\sqrt{\frac{p_0(1-p_0)}{n}}}$ where $\hat{p}$ is the sample proportion and $n$ is the sample size.

• P-value: Calculated from the standard normal distribution.

Example: Testing the claim that 2% of M&Ms are orange.

Inference for Categorical Data

Chi-Square Test for Independence

This test determines whether there is an association between two categorical variables in a contingency table.

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

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

• Test Statistic: $\chi^2 = \sum \frac{(O - E)^2}{E}$ where $O$ is the observed frequency and $E$ is the expected frequency.

• P-value: Calculated from the chi-square distribution with appropriate degrees of freedom.

Example: Examining the relationship between gender and personal goals in children.

Analysis of Variance (ANOVA)

One-Way ANOVA

One-way ANOVA is used to compare the means of three or more independent groups to determine if at least one group mean is different from the others.

• Null Hypothesis (H0): $\mu_1 = \mu_2 = \cdots = \mu_k$

• Alternative Hypothesis (Ha): At least one group mean is different.

• Test Statistic: $F = \frac{\text{Between-group variance}}{\text{Within-group variance}}$

• P-value: Calculated from the F-distribution.

Example: Comparing mean crawling ages of babies born in different months.

Correlation and Regression

Pearson Correlation Coefficient

The Pearson correlation coefficient measures the strength and direction of the linear relationship between two quantitative variables.

• Formula: $r = \frac{\sum (x_i - \bar{x})(y_i - \bar{y})}{\sqrt{\sum (x_i - \bar{x})^2 \sum (y_i - \bar{y})^2}}$

• Interpretation: $r$ ranges from -1 (perfect negative correlation) to +1 (perfect positive correlation).

Example: Investigating the correlation between cholesterol levels of husbands and wives.

Tabular Data: Example

The following table summarizes cholesterol levels for couples:

	Couple	Husband's cholesterol	Wife's cholesterol
1	257	210
2	310	270
3	245	258
4	324	249
5	318	238
6	274	236

Additional info: The table is used to illustrate correlation analysis between paired data.

Summary Table: Common Inference Tests

Test	Purpose	Key Statistic	Example
One-sample t-test	Compare sample mean to population mean	t	Calcium level in pregnant women
Two-sample t-test	Compare means of two groups	t	ACT scores: juniors vs. seniors
One-sample proportion test	Compare sample proportion to population proportion	z	Proportion of orange M&Ms
Chi-square test	Test association between categorical variables	$\chi^2$	Gender vs. personal goals
One-way ANOVA	Compare means of 3+ groups	F	Crawling age by birth month
Pearson correlation	Measure linear relationship	r	Husband's vs. wife's cholesterol

Conclusion

Understanding and applying the correct inference test is essential for drawing valid conclusions from data. Always begin by identifying the type of data and research question, then select the appropriate test, state hypotheses, calculate the test statistic and P-value, and interpret the results in context.