i.e. EF = RxC / ss
The above table contains the expected frequency of each cell
Step3: test the two assumptions.
All the frequencies are greater than 1 and none of them is less than 5.
Step4: select the significance level a. we usually take a at 5%
Step5: calculate the critical value 2a with df. Critical value is the area of right skewed
curve that is to be rejected. df=(R-1) x (C-1). Here df =(3-1) x (3-1)= 4.
As a is 0.05 and df =4, we calculated the critical value from the right skewed table. The
value from the table is 14.86
Step6: calculate the value of the test statistic i.e. 2 = (OF-EF) 2 / EF
In this case 2 turns out be 1.07
Step 7: compare the value of 2 that of 2a.
Since 2 does falls in the critical value (rejected area), will not reject null hypothesis.
Step 8: write the conclusion
At the significance level of 5%, it is proved from the data given the table that there is no association between Non-American students and the disciplines.
B. Define "causation" in statistical analysis. Describe at least two factors that influence relationships between two variables and can lead to misinterpretation of data analysis.
Causation tells the relationship between two variables. The occurrence of one variable (event) results the occurrence of the other variable (event), this phenomena is causation.
This means that the second variable is dependent on first variable. This means that if
second event has occurred, then the first event would have already occurred. But it is not
necessary that occurrence of first event must always leads to the occurrence of second event. For example, to...
For example, the number of people having hot coffee and the number of people taking sauna bath in gym may not be caused by each other. However, coldness may be reasons for both events. However, it is not necessary that one or the other may cause two variables, which are changing simultaneously, can be cause of any one. For example, the speed of wind and the number of cars on the road are not associated to each other. It is important to note that the symptoms must not be considered as cause. For example, B is caused by A and C is caused by B. Actually that not the case. C is also caused by A. B is just the symptom of A, which cannot be considered as cause.
The statistician should be aware of averages when computing for extreme values i.e. have outliers. Averages cannot be applied in this case, however if you remove the extreme values, which are in outliers, only then you can you averages.