Syntax
CHISQ.INV(probability, deg_freedom)
| Parameter | Description |
|---|---|
| probability | Parameter of the CHISQ.INV function. |
| deg_freedom | Parameter of the CHISQ.INV function. |
Examples
Upper bound for variance CI
Formula
=CHISQ.INV(0.025, 19)
Returns ~8.907. Used as the denominator divisor for the upper bound of a 95% confidence interval for variance with a sample of n=20.
95th percentile of chi-squared
Formula
=CHISQ.INV(0.95, 10)
Returns ~18.307. 95% of a chi-squared distribution with 10 df falls below this value.
Median chi-squared value
Formula
=CHISQ.INV(0.5, 5)
Returns ~4.352. The median of a chi-squared distribution with 5 df is about 4.35, slightly less than the mean of 5.
Common Errors
#NUM!
Probability must be between 0 and 1 (inclusive of 0, exclusive of 1). Degrees of freedom must be at least 1.
#VALUE!
Occurs when arguments are non-numeric.
Tips
Left-tailed inverse
CHISQ.INV gives the left-tail inverse. For the right-tail inverse used in most hypothesis testing, use CHISQ.INV.RT instead.
Variance confidence interval
To construct a CI for population variance: lower = (n-1)*s^2 / CHISQ.INV(1-alpha/2, n-1), upper = (n-1)*s^2 / CHISQ.INV(alpha/2, n-1).
Not symmetric
Unlike the t and normal distributions, the chi-squared distribution is not symmetric, so CHISQ.INV(0.025, df) is not simply the negative of CHISQ.INV(0.975, df).
Try CHISQ.INV in Viztab
Import your data and use CHISQ.INV with 370+ other formulas. No signup required.
Open Viztab