Regression slope test: A t-test to determine if the population slope is significantly different from zero, indicating a linear relationship.
- State null and alternative hypotheses
- Calculate test statistic: t = (b - β₀) / SE_b
- Determine degrees of freedom: df = n - 2
- Find critical value or p-value
- Make decision to reject or fail to reject H₀
- Draw conclusion in context
H₀: β = 0 (no linear relationship)
H₁: β ≠ 0 (linear relationship exists)
t = (b - β₀) / SE_b = (3.4 - 0) / 0.8 = 4.25
df = n - 2 = 20 - 2 = 18
For α = 0.05, two-tailed test, df = 18
t_critical = ±2.101
|t| = 4.25 > 2.101, so we reject H₀
There is sufficient evidence to conclude that there is a significant linear relationship between hours studied and exam scores.
We reject the null hypothesis. There is sufficient evidence to conclude that there is a significant linear relationship between hours studied and exam scores at α = 0.05.
• Test statistic: t = (sample slope - hypothesized slope) / standard error
• Degrees of freedom: df = n - 2 for simple linear regression
• Decision rule: Reject H₀ if |t| > critical value
• The observed slope of 3.4 is significantly different from 0
• The relationship is statistically significant
• Each additional hour of study increases exam score by approximately 3.4 points
Right-tailed test: A hypothesis test where the alternative hypothesis specifies that the parameter is greater than the null value.
H₀: β ≤ 0 (calorie intake has no positive effect or negative effect)
H₁: β > 0 (calorie intake has positive effect)
t = (b - β₀) / SE_b = (0.08 - 0) / 0.03 = 2.67
df = n - 2 = 18 - 2 = 16
For α = 0.01, right-tailed test, df = 16
t_critical = 2.583
t = 2.67 > 2.583, so we reject H₀
There is sufficient evidence to support the claim that calorie intake positively affects weight gain.
We reject the null hypothesis. There is sufficient evidence at α = 0.01 to conclude that daily calorie intake has a positive effect on weight gain.
• Right-tailed test: Critical value is only on the positive side
• Directional hypothesis: Specifies positive relationship
• Decision rule: Reject H₀ if t > critical value
• The slope of 0.08 is significantly greater than 0
• Each additional calorie increases weight by approximately 0.08 units
• The relationship is positive and statistically significant
Left-tailed test: A hypothesis test where the alternative hypothesis specifies that the parameter is less than the null value.
H₀: β ≥ 0 (screen time has no negative effect or positive effect)
H₁: β < 0 (screen time has negative effect)
t = (b - β₀) / SE_b = (-0.42 - 0) / 0.15 = -2.80
df = n - 2 = 25 - 2 = 23
For α = 0.05, left-tailed test, df = 23
t_critical = -1.714
t = -2.80 < -1.714, so we reject H₀
There is sufficient evidence to support the claim that screen time negatively affects sleep quality.
We reject the null hypothesis. There is sufficient evidence at α = 0.05 to conclude that increased screen time negatively affects sleep quality.
• Left-tailed test: Critical value is only on the negative side
• Negative slope: Indicates inverse relationship
• Decision rule: Reject H₀ if t < critical value
• The slope of -0.42 is significantly less than 0
• Each additional hour of screen time decreases sleep quality by approximately 0.42 units
• The relationship is negative and statistically significant
Population slope (β): The true slope parameter in the population regression line.
Sample slope (b): The estimated slope from the sample data.
Standard error of slope (SE_b): Measures the variability of the slope estimate.
Simple linear regression: A model that relates one independent variable to one dependent variable using a straight line.
Type I error: Rejecting the null hypothesis when it is actually true (false positive).
Type II error: Failing to reject the null hypothesis when it is actually false (false negative).
- Verify conditions: Check linearity, independence, normality, and equal variance
- State hypotheses: Define H₀ and H₁ about the population slope
- Choose significance level: Select α (typically 0.05 or 0.01)
- Calculate test statistic: Use t = (b - β₀) / SE_b
- Determine degrees of freedom: df = n - 2
- Find critical value or p-value
- Make decision: Compare test statistic with critical value
- Draw conclusion: Interpret in context of the research question
• Two-tailed: Reject H₀ if |t| > t_critical
• Right-tailed: Reject H₀ if t > t_critical
• Left-tailed: Reject H₀ if t < t_critical
• P-value approach: Reject H₀ if p-value ≤ α
• Hypothesis tests only indicate statistical significance, not practical importance
• Large samples can make trivial differences significant
• Outliers can greatly influence the regression line and test results
• Always plot the data to visually assess the linear relationship
P-value approach: Compare the p-value with the significance level α to make a decision, rather than using critical values.
H₀: β = 1.0
H₁: β ≠ 1.0
t = (b - β₀) / SE_b = (1.8 - 1.0) / 0.65 = 1.23
df = n - 2 = 30 - 2 = 28
This is a two-tailed test
p-value = 2 × P(T > |1.23|) = 2 × P(T > 1.23)
Using t-table with df = 28: p-value ≈ 0.229
p-value = 0.229 > α = 0.05
We fail to reject H₀
There is insufficient evidence to conclude that the slope differs from 1.0.
We fail to reject the null hypothesis. There is insufficient evidence at α = 0.05 to conclude that the slope differs from 1.0.
• P-value method: Compare p-value with α
• Decision rule: Reject H₀ if p-value ≤ α
• Two-tailed test: Multiply probability by 2
Testing against specific value: Testing whether the slope equals or differs from a specific theoretical or historical value.
H₀: β ≤ 0.5
H₁: β > 0.5
t = (b - β₀) / SE_b = (0.68 - 0.5) / 0.12 = 0.18 / 0.12 = 1.50
df = n - 2 = 22 - 2 = 20
For α = 0.05, right-tailed test, df = 20
t_critical = 1.725
t = 1.50 < 1.725
We fail to reject H₀
There is insufficient evidence to conclude that the slope is significantly greater than 0.5.
We fail to reject the null hypothesis. There is insufficient evidence at α = 0.05 to conclude that the slope is significantly greater than 0.5.
• Specific value test: Compare slope to theoretical value
• Directional test: Right-tailed for "greater than"
• Decision rule: Reject H₀ if t > critical value
Linear regression: A statistical method that models the relationship between a dependent variable and one or more independent variables using a linear equation.
Population regression line: The true linear relationship in the population: μ_y = α + βx.
Sample regression line: The estimated relationship from sample data: ŷ = a + bx.
Residuals: The differences between observed and predicted values: e_i = y_i - ŷ_i.
Sampling distribution: The distribution of all possible values of the sample slope across different samples.
Statistical significance: When the p-value is less than or equal to the significance level, indicating evidence against the null hypothesis.
Practical significance: Whether the observed effect is meaningful in the real world, regardless of statistical significance.
- Model verification: Confirm that linear regression assumptions are met
- Parameter extraction: Obtain slope estimate and its standard error from regression output
- Hypothesis formulation: Define appropriate null and alternative hypotheses
- Significance level selection: Choose α based on consequences of Type I error
- Degree of freedom calculation: df = n - 2 for simple regression
- Test statistic calculation: Apply t-statistic formula correctly
- Critical value or p-value: Determine based on test type and α
- Decision making: Apply correct decision rule
- Contextual interpretation: State results in terms of the original research question
- Practical assessment: Evaluate whether results have real-world significance
• Test statistic: t = (b - β₀) / SE_b
• Degrees of freedom: df = n - 2
• Standard error: SE_b = s/[s_x√(n-1)]
• Decision rule: Reject H₀ if |t| > t_critical (two-tailed)
• P-value approach: Reject H₀ if p-value ≤ α
• The t-distribution approaches normal distribution as sample size increases
• Multiple regression extends these concepts to multiple predictors
• Power analysis can help determine required sample size
• Effect size measures complement significance testing