In a Chi-Squared Goodness-Of-Fit Test, If the Expected Frequencies $e _ { i }$

Multiple Choice

In a chi-squared goodness-of-fit test, if the expected frequencies $e _ { i }$ and the observed frequencies $f _ { i }$ were quite different, which of the following is the best conclusion?

A) Null hypothesis is false, and reject Ho.
B) Null hypothesis is true, and retain Ho.
C) Alternative hypothesis is false, reject H_A.
D) Chi-squared distribution is invalid, use t-distribution instead.