Marla G. answered 11/08/20
Masters Degree in Applied Statistics with 20+ Years of Work Experience
Sounds like your null needs to be H0 : all 5 category means are =, so the expected frequency for each mean is also =, and that is the same as the overall mean of the 'N' people(?) that are choosing a category:
1) Calculate that mean:(12+8+7+15+22)/5 =12.4.
2) This is the value for each of your expected frequencies.
3) Use the equation listed for the 4th column and calculate it for each row.
4) Add those five values is your Chi-squared test, and is also a Goodness-of-Fitness test for a two-way table.
5) Look up your value in a table for a Chi-Square distribution, to get the p-value and answer the question.
If the computed test statistic is large, then the observed and expected values are not close and the model is a poor fit to the data.