FreeStatisticalTools.com
Browse tools
Econometrics and time series

Granger Causality Test

Test whether the history of X helps predict Y beyond Y’s own history, and the reverse. F tests are reported for every lag length together with information criteria to choose the lag.

Free · No sign-upReplaces EViews · StataWorks with your data
Updated · By Bibin Xavier

Data 160 × 6

Paste from Excel, or drop a CSV, TSV or Excel file here.
Example data 160 rows, 6 variables. Data stays in this browser tab.
Quartertext · 160 levelsLog_GDPnumericLog_ConsumptionnumericInflationnumericInterest_RatenumericMoney_Growthnumeric
2000Q19.20618.65721.171.324.05
2000Q29.20058.66951.973.23.9
2000Q39.2168.67272.613.544.84
2000Q49.21158.69232.152.533.4
2001Q19.2248.69571.983.141.25
2001Q29.22868.68841.473.112.17
2001Q39.2328.70521.552.651.8
2001Q49.22078.69072.182.433.5

Variables and options

Results update automatically when you change an option.

Results

160 rows · example data
Table 1

Granger causality F tests

LagMoney_Growth → Inflation: FpInflation → Money_Growth: FpAICBIC
151.629< .0010.637.426262.9272.1
227.088< .0010.310.734262.6277.9
317.974< .0011.096.353261.2282.6
4 ★15.643< .0010.871.483256.8284.2

Note. H₀: the lags of the first series do not help predict the second. ★ lag chosen by AIC for the equation of Inflation. Use first differences if the series have unit roots.

Inflation and Money_Growth over time (standardized)

Interpretation

At 4 lags, Money_Growth Granger-causes Inflation (F = 15.64, p < .001), and Inflation does not Granger-cause Money_Growth (F = 0.87, p = .483). Granger causality means predictive precedence, not causation in the structural sense.

Money_Growth Granger-caused Inflation, F(4, 147) = 15.64, p < .001.

How to cite this tool

Using these results in a thesis, journal article, report or class assignment? Please cite this free tool so others can find it. It keeps the site free.

APA 7

Xavier, B. (2026). Granger Causality Test [Web application]. FreeStatisticalTools.com. https://freestatisticaltools.com/granger-causality-test/

BibTeX 

@software{xavier_grangercausalitytest_2026,
  author = {Xavier, Bibin},
  title = {Granger Causality Test},
  publisher = {FreeStatisticalTools.com},
  year = {2026},
  url = {https://freestatisticaltools.com/granger-causality-test/},
  note = {Web application}
}

Suggested sentence for your methods section: “The analysis was carried out with the free Granger Causality Test tool on FreeStatisticalTools.com (Xavier, 2026).”

What is the Granger causality test?

X Granger-causes Y if past values of X improve the prediction of Y beyond what Y’s own past already provides. The test compares a regression of Y on its own lags with one that also includes lags of X.

When to use the Granger causality test

Use it to test lead-lag relationships between stationary time series, for example whether money growth predicts inflation.

Assumptions

  • Both series are stationary (difference them if they are I(1) and not cointegrated).
  • Rows are in time order.

How to use this tool

  1. Enter your data. Paste columns from Excel, Google Sheets or SPSS with variable names in the first row, or upload a CSV or Excel file. The example data shows the expected layout.
  2. Choose the variables. Select the series 1 and series 2.
  3. Set the options. Fill in maximum lag and use first differences (for i(1) series).
  4. Read the results. Results update automatically. Read the plain-English interpretation, then use Copy table to paste APA-style tables into Word and Copy for the results sentence.

How to report the Granger causality test in APA style

Report the F statistic, degrees of freedom and p-value for each direction at the chosen lag length.

Frequently asked questions

Does Granger causality prove causation?

No. It shows predictive precedence; a third variable could drive both series.

How many lags should I use?

Choose the lag length by an information criterion such as AIC or BIC, and check that results are robust to nearby lag lengths.

Do the series need to be stationary?

Yes, for the standard F test. Difference I(1) series first, or use the Toda-Yamamoto approach.

Related tools

OLS with Robust Standard Errors and DiagnosticsRegression with HC0–HC3, clustered or Newey-West errors plus Breusch-Pagan, White, RESET, Durbin-Watson, Breusch-Godfrey and Jarque-Bera tests.Instrumental Variables (2SLS) RegressionTwo-stage least squares with first-stage F, partial R², Sargan over-identification and Wu-Hausman endogeneity tests.Probit and Logit with Average Marginal EffectsBinary choice models with average marginal effects, delta-method standard errors, odds ratios and fit statistics.Poisson and Negative Binomial RegressionCount-data regression with incidence rate ratios, overdispersion tests and a model comparison.Unit Root Tests: Augmented Dickey-Fuller and KPSSAugmented Dickey-Fuller and KPSS stationarity tests in levels and first differences, with ACF, PACF and Ljung-Box.Engle-Granger Cointegration TestEngle-Granger two-step cointegration test with MacKinnon critical values, the long-run equation and residual plot.

Browse all categories

Data cleaning and preparation · Describe and explore · Compare means · Nonparametric tests · Correlation and regression · Bayesian statistics · Categorical data · Reliability and agreement · Multivariate analysis · Structural equation modeling · Econometrics and time series · Panel data and causal inference · Marketing and decision research · Survival, clinical and meta-analysis · Study planning and calculators · PLS-SEM