StatFas emblem: a philosopher beside a rising bar chart StatFas.comAn Easy Way to Do Statistics

Partial Autocorrelation (PACF) Plot Maker

Use this tool when you want to choose the autoregressive order of a time series model, for example before fitting an ARIMA model. Paste or upload your series below, set the number of lags, read which lags are significant, edit colours and labels, and download the figure as a picture or as an APA 7 Word file.

About the PACF plot

The partial autocorrelation function (PACF) measures the correlation between a time series and its own lagged values after removing the effect of the shorter lags in between. A PACF plot draws this value for each lag as a bar, with a confidence band around zero.

For an autoregressive process of order p, the PACF cuts off after lag p, which is why analysts read it together with the ACF plot to choose the order of an AR or ARIMA model.

When to use it

Use a PACF plot when you model a stationary time series and need to decide how many autoregressive terms to include. Check stationarity first and difference the series if there is a trend. Bars outside the confidence band suggest lags that carry direct information.

What this tool offers

Assumptions to check

How to report it in APA7

State the series, its length and any differencing, report the number of lags and the lags outside the 95% confidence band, and cite the figure as Figure 1 with a note that the band is approximately ±1.96/√n. The generator writes the text, caption and note for you.

Frequently asked questions

Is the PACF plot generator free?

Yes. You can create and edit the plot without an account. Create a free account or log in only when you want to download it.

How do I read a PACF plot?

Look for bars that extend beyond the blue confidence band. If the PACF cuts off after lag p and the ACF tails off, an AR(p) model is a good candidate.

What is the difference between ACF and PACF?

The ACF shows the total correlation between the series and its lags. The PACF shows only the direct correlation at each lag after removing the effect of the lags in between.

Is my data uploaded to a server?

The plot is built in your browser. Your data stays on your device while you work.

Related tools