In: Statistics and Probability
   Group Meetings   Face-to-Face Meetings
with Individuals   E-mails   Other
Generation Y   180   240  
50   30
Generation X   230   165  
50   55
Boomer   220   185   60  
35
Mature   205   150   70  
75
A newspaper reported on preferred types of office communication by different age groups. Suppose the results were based on a survey of 500 respondents in each age group. The results are cross-classified in the table found below. At the 0.10 level of significance, is there evidence of a relationship between age group and type of communication preferred? Calculate the test statistic
Null hypothesis : Ho : There is no relationship between age group and type of communication preferred(Age group and type of communication are independent)
Alternate Hypothesis : Ha: There is relationship between age group and type of communication preferred(Age group and type of communication are not independent)
Test Statistic

O : Observed Frequency
E: Expected Frequency

| Observed Counts/Frequency | Group Meetings | Face-to-Face Meetings with Individuals | E-mails | Other | Row Total | 
| Generation Y | 180 | 240 | 50 | 30 | 500 | 
| Generation X | 230 | 165 | 50 | 55 | 500 | 
| Boomer | 220 | 185 | 60 | 35 | 500 | 
| Mature | 205 | 150 | 70 | 75 | 500 | 
| Column Total | 835 | 740 | 230 | 195 | 2000 | 
| E: Expected Count/Frequency | Group Meetings | Face-to-Face Meetings with Individuals | E-mails | Other | 
| Generation Y | (500*835) / 2000 | (500*740) / 2000 | (500*230) / 2000 | (500*195) / 2000 | 
| Generation X | (500*835) / 2000 | (500*740) / 2000 | (500*230) / 2000 | (500*195) / 2000 | 
| Boomer | (500*835) / 2000 | (500*740) / 2000 | (500*230) / 2000 | (500*195) / 2000 | 
| E: Expected Count/Frequency | (500*835) / 2000 | (500*740) / 2000 | (500*230) / 2000 | (500*195) / 2000 | 
| E: Expected Count/Frequency | Group Meetings | Face-to-Face Meetings with Individuals | E-mails | Other | 
| Generation Y | 208.75 | 185 | 57.5 | 48.7500 | 
| Generation X | 208.75 | 185 | 57.5 | 48.7500 | 
| Boomer | 208.7500 | 185 | 57.5000 | 48.7500 | 
| Mature | 208.7500 | 185 | 57.5000 | 48.7500 | 
| O | E | O-E | (O-E)2 | (O-E)2/E | 
| 180 | 208.75 | -28.75 | 826.5625 | 3.9596 | 
| 240 | 185 | 55 | 3025 | 16.3514 | 
| 50 | 57.5 | -7.5 | 56.25 | 0.9783 | 
| 30 | 48.75 | -18.75 | 351.5625 | 7.2115 | 
| 230 | 208.75 | 21.25 | 451.5625 | 2.1632 | 
| 165 | 185 | -20 | 400 | 2.1622 | 
| 50 | 57.5 | -7.5 | 56.25 | 0.9783 | 
| 55 | 48.75 | 6.25 | 39.0625 | 0.8013 | 
| 220 | 208.75 | 11.25 | 126.5625 | 0.6063 | 
| 185 | 185 | 0 | 0 | 0.0000 | 
| 60 | 57.5 | 2.5 | 6.25 | 0.1087 | 
| 35 | 48.75 | -13.75 | 189.0625 | 3.8782 | 
| 205 | 208.75 | -3.75 | 14.0625 | 0.0674 | 
| 150 | 185 | -35 | 1225 | 6.6216 | 
| 70 | 57.5 | 12.5 | 156.25 | 2.7174 | 
| 75 | 48.75 | 26.25 | 689.0625 | 14.1346 | 
| Total | 62.7398 | 

Value of the test statistic = 62.7398
Degrees of freedom = (Number of rows -1)x(Number of columns -1)=(4-1)x(4-1)=9

For 9 degrees of freedom,

p-value = 0.0000
As p-value < 0.10:level of significance ; Reject the null hypothesis.
There is sufficient evidence to conclude that There is relationship between age group and type of communication preferred(Age group and type of communication are not independent)