In: Statistics and Probability
A makeup company wants to know if all the shades of their foundation are sold at equal rates. Below is the gathered data.
Shade #1 | Shade #2 | Shade #3 | Shade #4 | Shade #5 | Shade #6 | Shade #7 |
218 | 191 | 239 | 189 | 178 | 168 | 149 |
Pearson's Chi-square test | ||||||
X-squared = 28.88 | df = 6 | p_value = ? |
Based on the information above, determine if you should accept or reject the null hypothesis that there is no relationship between shade number and number of units sold when alpha = 0.05?
Test statistic, X-squared = 28.88
Degrees of freedom = 7 - 1 = 6
P-value = 0.000064
Since, the P-value is less than the significance level of 0.05, we should reject the null hypothesis that there is no relationship between shade number and number of units sold.
Edit:
P-value for Chi-square distribution can be calculated from Chi-square distribution table. But from table you can calculate the p-value (by linear interpolation) if the p-value can be bounded within 0.001 and 0.05. You cannot calculate it if the p-value is less than 0.001 (in this case p-value is 0.000064). In this case, you have to use a statistical calculator or a statistical software (eg R-Studio, Python etc) or some online calculator. Here is a link of an online p-value calculator:
https://www.danielsoper.com/statcalc/calculator.aspx?id=11