Step 1 — Upload your dataset
CSV files only. Maximum 5 MB / 10,000 rows.
Drag & drop a CSV here
or
💡 Tip: For best results, make sure your column headers are in row 1
and data starts immediately below. We'll try to detect headers automatically if they're elsewhere,
but some messy files may need cleaning first.
Step 2 — Select columns to analyse
Only numeric columns can be correlated. Select at least 2.
Results
Key findings
What do these numbers mean?
Pearson r
Measures how closely two variables move together. Ranges from −1 (perfectly opposite — as one goes up the other goes down) through 0 (no relationship) to +1 (perfectly in sync). A value above 0.7 or below −0.7 is considered strong.
r² (r-squared)
The percentage of one variable's variation that is explained by the other. If r = 0.8, then r² = 64% — meaning 64% of the change in one column can be accounted for by the other. The remaining 36% is down to other factors.
p-value
The probability that you'd see this correlation by pure chance if there were actually no real relationship. A p-value below 0.05 is the conventional threshold for "statistically significant" — it means there's less than a 5% chance the pattern is just noise. Note: significance doesn't prove causation.
Mean
The average — all values added together and divided by how many there are. Useful as a central reference point, but can be skewed by extreme outliers.
Median
The middle value when all numbers are sorted in order. Half the values are above it, half below. More resistant to outliers than the mean — if the mean and median are very different, your data likely has skewed extremes.
Std Dev (Standard Deviation)
Measures how spread out the values are around the mean. A low std dev means most values cluster tightly around the average. A high std dev means values are widely scattered. As a rule of thumb: ~68% of values fall within 1 std dev of the mean, ~95% within 2.
Min / Max
The lowest and highest values in the column. Large gaps between min/max relative to the std dev can indicate outliers worth investigating before drawing conclusions from the correlations.
Strength labels
Strong: |r| ≥ 0.7 — a clear, reliable relationship. Moderate: 0.4–0.7 — a meaningful trend worth noting. Weak: 0.2–0.4 — a slight tendency, treat with caution. Negligible: below 0.2 — effectively no linear relationship.
Correlation measures linear relationships only. Two variables can have a strong non-linear relationship and still show r ≈ 0. Always sanity-check findings against your knowledge of the subject matter.
Correlation matrix
Pearson r — ranges from −1 (perfect negative) to +1 (perfect positive). * = p < 0.05 (statistically significant).
Descriptive statistics
Data preview