Name: ______Date: ______Period: ___

Honors Biology, Pietrangelo

Zodiac Chi-Squared Activity

Using what you have learned about chi-squared of best-fit statistical analysis methods, and collected data complete the following exercises. You will be asking what zodiac signs individuals have and compare those numbers to what you would expect them to be.

Baby Zodiac by Tania Howells



Table 1: Class Data for Zodiac Chi-squared Analysis

Observed # / Expected #
Zodiac Sign / O / E / (O – E) / (O - E)2 / (O - E)2/E
Aquarius
Pisces
Aries
Taurus
Gemini
Cancer
Leo
Virgo
Libra
Scorpio
Sagittarius
Capricorn
Sum

Table 2: Collected Data for Zodiac Chi-squared Analysis (at least 100 people)

Observed # / Expected #
Zodiac Sign / O / E / (O – E) / (O - E)2 / (O - E)2/E
Aquarius
Pisces
Aries
Taurus
Gemini
Cancer
Leo
Virgo
Libra
Scorpio
Sagittarius
Capricorn
Sum

Post Lab Questions:

Answer the following questions for the zodiac data analysis and for each assigned analysis in this exercise.

  1. Write the specific steps of the scientific method that were used in this exercise.
  2. What hypothesis was tested in this exercise (be sure you write it in the correct format)?
  3. What observations were made?
  4. Did the observations support the hypothesis? Explain.
  5. What variable was studied?
  6. What conclusion was made from the analysis?
  7. Identify, apart from the situations mentioned in this exercise, three other possible investigations wherein the chi-square goodness of fit test might be used.
  8. In a chi-square goodness of fit analysis there were 200 observations among four classes (A, B, C, and D) and the expected numbers in the classes were in a 9:3:3:1 ratio for the classes A, B, C and D, respectively. What would be the expected numbers?
  9. Under what circumstances might it be more desirable or appropriate to use a 1% level of significance rather than a 5% level of significance?
  10. Does the chi-squared goodness of fit test provide an absolute test of the null hypothesis involved?
  11. How would increasing sample size (total number of observations) affect the confidence one has in the conclusion from an analysis?