P-value: The probability of observing a test statistic as extreme or more extreme than the one calculated, assuming the null hypothesis is true.
- Compare p-value with significance level (α)
- Make statistical decision (reject/fail to reject H₀)
- State conclusion in context
- Consider practical significance
p-value = 0.0146
α = 0.05
Since 0.0146 < 0.05, we reject H₀
We reject the null hypothesis of independence
There is sufficient evidence to conclude that there is an association between education level and job satisfaction.
The observed association is statistically significant at the 5% level.
We reject the null hypothesis. There is a statistically significant association between education level and job satisfaction at α = 0.05.
• Decision rule: Reject H₀ if p-value ≤ α
• Statistical significance: Evidence against H₀ exists
• Association: Variables are not independent
• The probability of observing χ² = 8.45 or more extreme, if variables were truly independent, is only 1.46%
• This is unlikely enough to reject independence
• The association is statistically significant
Non-significant result: When the p-value exceeds α, we fail to reject the null hypothesis.
p-value = 0.140
α = 0.05
Since 0.140 > 0.05, we fail to reject H₀
We fail to reject the null hypothesis of independence
There is insufficient evidence to conclude that there is an association between coffee consumption and sleep quality.
Failing to reject H₀ does NOT prove independence; it means evidence is insufficient to conclude otherwise.
We fail to reject the null hypothesis. There is no statistically significant association between coffee consumption and sleep quality at α = 0.05.
• Decision rule: Fail to reject H₀ if p-value > α
• No evidence: Insufficient evidence for association
• Not proof: Failing to reject ≠ proving independence
• The probability of observing χ² = 2.18 or more extreme, if variables were truly independent, is 14%
• This is not unlikely enough to reject independence
• No statistically significant association found
Significance level (α): The threshold for determining statistical significance, representing the maximum acceptable probability of Type I error.
p-value = 0.034
α = 0.01
Since 0.034 > 0.01, we fail to reject H₀
p-value = 0.034
α = 0.05
Since 0.034 < 0.05, we reject H₀
p-value = 0.034
α = 0.10
Since 0.034 < 0.10, we reject H₀
Results are significant at α = 0.05 and α = 0.10, but not at α = 0.01
At α = 0.01: Fail to reject H₀. At α = 0.05 and α = 0.10: Reject H₀. The result is significant at the 5% and 10% levels but not at the 1% level.
• Level dependency: Same result can be significant or not depending on α
• Stricter α: Lower α makes rejection harder
• Context matters: Choose α based on consequences of errors
• The evidence is strong enough for moderate significance levels
• But not strong enough for very strict significance level
• The association is moderately significant
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.
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).
- Examine the p-value: Compare with the chosen significance level
- Make statistical decision: Reject or fail to reject the null hypothesis
- State conclusion: Express in terms of the original research question
- Consider practical significance: Evaluate the real-world importance
- Assess effect size: Determine the strength of the association
- Discuss limitations: Consider sample size and potential biases
- Draw final interpretation: Combine statistical and practical considerations
• Decision rule: Reject H₀ if p-value ≤ α
• Fail to reject: Does NOT prove H₀ is true
• Statistical vs practical: Distinguish between the two
• Effect size: Report strength of association
• Context: Always interpret in research context
• P-value = probability that H₀ is true (incorrect!)
• P-value = probability that results occurred by chance (misleading)
• Non-significant = proves no effect (incorrect!)
• Significant = important in practice (not necessarily)
Sample size effect: Larger samples can detect smaller effects as statistically significant.
χ² = 3.84, df = 1, p-value = 0.05
At α = 0.05: p-value = α, barely significant
Small sample, detected effect may be substantial
χ² = 3.84, df = 1, p-value = 0.05
At α = 0.05: p-value = α, barely significant
Large sample, detected effect may be small
Same test statistic implies same strength of association
But practical importance may differ due to sample size
Cramér's V = √(χ²/n) = √(3.84/50) = 0.28 (for Study A)
Cramér's V = √(3.84/500) = 0.089 (for Study B)
Both studies show statistical significance at α = 0.05, but Study A shows a stronger practical association (larger effect size) than Study B despite identical test statistics.
• Sample size impact: Larger n increases power to detect effects
• Effect size: Essential for practical interpretation
• Statistical vs practical: Distinguish between significance and importance
Cramér's V: A measure of association strength for chi-square tests, ranging from 0 (no association) to 1 (perfect association).
V = √[χ²/(n × min(r-1, c-1))]
For a 2×4 table: min(r-1, c-1) = min(1, 3) = 1
V = √[25.6/(400 × 1)] = √(25.6/400) = √0.064 = 0.253
p-value = 0.0001 < α = 0.05
We reject H₀: There is a statistically significant association
V = 0.253 (small to medium effect)
The association is weak to moderate in strength
While statistically significant, the association explains only about 6.4% of variance
There is a statistically significant association between social media usage and age group (p < 0.001), but the effect size (V = 0.253) indicates a small to moderate association strength.
• Effect size calculation: Cramér's V provides standardized measure
• Strength interpretation: V ≈ 0.1 is small, 0.3 is medium, 0.5 is large
• Statistical vs practical: Both aspects matter in interpretation
P-value: The probability of obtaining results as extreme or more extreme than those observed, given that the null hypothesis is true.
Statistical significance: The result is unlikely to have occurred by chance alone, according to the chosen significance level.
Practical significance: Whether the observed effect is meaningful or important in real-world applications.
Effect size: A quantitative measure of the magnitude of a phenomenon, independent of sample size.
Power: The probability of correctly rejecting a false null hypothesis.
- Examine test statistics: Review χ² value, degrees of freedom, and sample size
- Analyze p-value: Compare with significance level α
- Make statistical decision: Reject or fail to reject null hypothesis
- Calculate effect size: Use Cramér's V or other appropriate measures
- Interpret effect size: Determine practical significance
- Contextualize findings: Relate to research question and field of study
- Assess limitations: Consider sample characteristics and study design
- Draw comprehensive conclusion: Integrate statistical and practical interpretations
• Decision rule: Reject H₀ if p-value ≤ α
• Cramér's V: V = √[χ²/(n × min(r-1, c-1))]
• Effect size interpretation: Small ≈ 0.1, Medium ≈ 0.3, Large ≈ 0.5
• P-value interpretation: Probability under null hypothesis
• Practical significance: Consider real-world impact
1. Statistical significance does not imply practical importance
2. Large samples can make trivial differences significant
3. Small samples may miss important effects
4. Association does not imply causation
5. Always consider the research context
6. Report both statistical and practical findings