No persisted videos match this date range.
Correlation Analysis
Analysis of relationships between different video metrics
Analyzed 0 videos • Generated 2026-11-12 20:53 UTC
Correlation Matrix
| Metric | Views | Likes | Comments |
|---|---|---|---|
| Views |
1.00
Perfect
|
0.000
Very Weak/None
|
0.000
Very Weak/None
|
| Likes |
0.000
Very Weak/None
|
1.00
Perfect
|
0.000
Very Weak/None
|
| Comments |
0.000
Very Weak/None
|
0.000
Very Weak/None
|
1.00
Perfect
|
Correlation Interpretation Guide
| Value Range | Strength | Interpretation |
|---|---|---|
| 0.8 to 1.0 | Very Strong | Metrics move almost perfectly together |
| 0.6 to 0.8 | Strong | Clear relationship exists |
| 0.4 to 0.6 | Moderate | Noticeable relationship |
| 0.2 to 0.4 | Weak | Slight relationship |
| 0.0 to 0.2 | Very Weak/None | Little to no relationship |
Key Insights
- Positive Correlation: Metrics increase together
- Negative Correlation: One metric increases as the other decreases
- No Correlation: Metrics are independent
- Correlation ≠ Causation: Relationship doesn't imply cause-effect
Note: Correlation coefficients range from -1 to 1.
Values closer to 1 indicate strong positive relationships,
values closer to -1 indicate strong negative relationships,
and values near 0 indicate no relationship.
Scatter Plot Analysis
Views vs Likes Correlation
Views vs Comments Correlation
Correlation Analysis Insights
Expected Relationships
- Views ↔ Likes: Typically strong positive correlation. More views generally lead to more likes.
- Views ↔ Comments: Usually moderate positive correlation. Higher view counts often generate more comments.
- Likes ↔ Comments: Often strong positive correlation. Engagement metrics tend to move together.
Business Implications
- Understanding these relationships helps predict video performance
- Content creators can focus on metrics that drive overall engagement
- Platforms can optimize recommendation algorithms
- Marketers can identify key performance indicators
Comparison with Python Notebook
The Python EDA notebook performed extensive correlation analysis including:
- Pearson correlation coefficient calculations
- Correlation matrix visualization with heatmaps
- Scatter plots with regression lines
- Statistical significance testing
- Correlation by category analysis
Python Notebook Findings
The notebook analysis revealed:
- Views vs Likes: Very strong positive correlation (r ≈ 0.85)
- Views vs Comments: Moderate positive correlation (r ≈ 0.45)
- Likes vs Comments: Strong positive correlation (r ≈ 0.65)
- Category Variations: Correlation strength varied by content type
Statistical Note: Correlation analysis assumes linear relationships.
Non-linear relationships may exist that aren't captured by Pearson correlation.
The Python notebook also explored Spearman rank correlation for non-linear relationships.
Statistical Methodology
Pearson Correlation Coefficient
The Pearson correlation coefficient (r) measures the linear relationship between two variables. It's calculated as:
r = Σ[(xᵢ - x̄)(yᵢ - ȳ)] / √[Σ(xᵢ - x̄)² Σ(yᵢ - ȳ)²]
Where xᵢ and yᵢ are individual sample points, and x̄ and ȳ are the sample means.
Implementation Details
This implementation calculates Pearson correlation using:
public double CalculatePearsonCorrelation(double[] x, double[] y)
{
double sumX = 0, sumY = 0, sumXY = 0, sumX2 = 0, sumY2 = 0;
int n = x.Length;
for (int i = 0; i < n; i++)
{
sumX += x[i];
sumY += y[i];
sumXY += x[i] * y[i];
sumX2 += x[i] * x[i];
sumY2 += y[i] * y[i];
}
double numerator = n * sumXY - sumX * sumY;
double denominator = Math.Sqrt((n * sumX2 - sumX * sumX) *
(n * sumY2 - sumY * sumY));
return denominator == 0 ? 0 : numerator / denominator;
}