In: Statistics and Probability
As part of the study on ongoing fright symptoms due to exposure to horror movies at a young age, the following table was presented to describe the lasting impact these movies have had during bedtime and waking life:
| Waking symptoms  | 
||||
|---|---|---|---|---|
| Bedtime symptoms | Yes | No | ||
| Yes | 36 | 33 | ||
| No | 32 | 18 | ||
(a) What percent of the students have lasting waking-life
symptoms? (Round your answer to two decimal places.)
(b) What percent of the students have both waking-life and bedtime
symptoms? (Round your answer to two decimal places.)
  
(c) Test whether there is an association between waking-life and
bedtime symptoms. State the null and alternative hypotheses. (Use
α = 0.01.)
Null Hypothesis:
H0: There is no relationship between waking and bedtime symptoms.H0: Waking symptoms cause bedtime symptoms. H0: There is a relationship between waking and bedtime symptoms.H0: Bedtime symptoms cause waking symptoms.
Alternative Hypothesis:
Ha: Waking symptoms cause bedtime symptoms.Ha: Bedtime symptoms cause waking symptoms. Ha: There is no relationship between waking and bedtime symptoms.Ha: There is a relationship between waking and bedtime symptoms.
State the χ2 statistic and the
P-value. (Round your answers for χ2
and the P-value to three decimal places.)
| χ2 | = | |
| df | = | |
| P | = | 
Conclusion:
a. We do not have enough evidence to conclude that there is a relationship.
b. We have enough evidence to conclude that there is a relationship.
a) Required percentage = (36 + 32)/(36 + 33+ 32 + 18) =
57.14%
b) Required percentage = 36/(36 + 34 + 32 + 17) = 30.25%
c)
H0: There is no relationship between waking and bedtime symptoms.H0: Waking symptoms cause bedtime symptoms.
Ha: There is a relationship between waking and bedtime symptoms
| Chi-Square Test | |||||||
| Observed Frequencies | |||||||
| column | |||||||
| row | yes | no | Total | ||||
| Yes | 36 | 33 | 69 | ||||
| No | 32 | 18 | 50 | ||||
| Total | 68 | 51 | 119 | ||||
| Expected frequency of a cell = sum of row*sum of column / total sum | |||||||
| Expected Frequencies | |||||||
| yes | no | Total | |||||
| Yes | 39.4286 | 29.5714 | 69 | ||||
| No | 28.5714 | 21.4286 | 50 | ||||
| Total | 68 | 51 | 119 | ||||
| (fo-fe)^2/fe | |||||||
| Yes | 0.2981 | 0.3975 | |||||
| No | 0.4114 | 0.5486 | |||||
Chi-Square Test Statistic,χ² = Σ(fo-fe)^2/fe =  
1.656  
      
Level of Significance =   0.01  
Number of Rows =   2  
Number of Columns =   2  
Degrees of Freedom=(#row - 1)(#column -1) =  
1  
      
p-Value =   0.1982  
                            
[Excel function:   =CHISQ.DIST.RT(χ²,df) ]
Decision:    p value > α ,   do not reject
Ho  
a. We do not have enough evidence to conclude that there is a relationship.