PCA calculator — principal component analysis
Paste two or three series with equal observation counts. The calculator derives principal components from a correlation or covariance matrix.
Scree chart
Bars show the share of total variance explained by each component.
Components and loadings
| Component | Eigenvalue | Variance share | Loading A | Loading B | Loading C |
|---|---|---|---|---|---|
| Fill in the fields above — the result is computed on this page. | |||||
How to use this page
- Paste equal-length series.
- Choose scaling suitable for the data.
- Read the explained variance and loadings.
What this page does not do: The tool supports 2–3 variables and 3–5000 complete observations. It does not impute missing values or choose the final component count.
Further reading
PCA rotates the coordinate system so the first component captures as much variation as possible and each later component captures the greatest remaining variation while staying orthogonal. Standardisation is appropriate when variables use different units or scales.
A loading vector may be multiplied by −1 without changing the component. Focus on absolute loading sizes and explained variance.
Frequently asked questions
When should I standardise?
When variables use different units or have very different variances. Otherwise the largest scale may dominate.
Does a loading sign matter?
Eigenvector direction is arbitrary. Reversing every sign in a component leaves the model unchanged.
See also
A/B test calculator
Compare two proportions in an A/B test. Calculate conversion rates, difference, uplift, z score, p value and c
A/B test planning — sample size, MDE and duration
Plan a two-proportion experiment, estimate detectable effect and traffic duration.
ACF and PACF autocorrelation calculator
Calculate ACF and PACF across time-series lags. Review the chart, reference bounds and coefficient table.