CODEWITHSUNDEEP
rstatisticschi-squaredgoodness-of-fit
AliCivil
AliCivil

Reputation: 2053

Chi-squared goodness of fit test in R

I have a vector of observed values and also a vector of values calculated with model: 

actual <- c(1411,439,214,100,62,38,29,64)
expected <- c(1425.3,399.5,201.6,116.9,72.2,46.3,30.4,64.8)

Now I'm using the Chi-squared goodness of fit test to see how well my model performs. I wrote the following: 

chisq.test(expected,actual)

but it doesn't work. Can you help me with this?

Upvotes: 13

Views: 22701

Answers (2)

rwinkel2000
rwinkel2000

Reputation: 136

chisq.test(actual, p=expected, rescale.p = TRUE) does get the correct values as calculated "by hand" in Excel.

Upvotes: 0

Roman Luštrik
Roman Luštrik

Reputation: 70653

X^2 = 10.2 at 7 degrees of freedom will give you a p ~ 0.18 .

> 1-pchisq(10.2, df = 7)
[1] 0.1775201

You should pass on the expected values under argument p. Make sure you scale your values to sum to 1.

> chisq.test(actual, p = expected/sum(expected))

    Chi-squared test for given probabilities

data:  actual 
X-squared = 10.2581, df = 7, p-value = 0.1744

This about what X^2 test is doing. You give the function a model (expected) and ask - how likely it is that my observed data came from a population that "generated" expected?

Upvotes: 15

Related Questions