week 11 statistics

Question 1

Test of association

Answer 1

Test of association are need when the variables of interest are categorical
association is relationship

Question 2

Correlations

Answer 2

used with scale variables
A correlation is a parametric statistic
comes with assumptions about distribution

Question 3

Chi-square

Answer 3

used categorical variables. Chi-square is non parametric . Does not make assumptions about a distribution

Question 4

Representing the data: contingency table

Answer 4

shows how the data are distributed across the variable
The number in the cells are known as observed frequencies

Question 5

Descriptive statistics are an important place to start

Answer 5

we have to look at descriptive statistics: we observe the frequencies looking at the descriptive statistics

Question 6

How Chi-square works

Answer 6

if there is no association then observed the values and frequency do not differ from what we would expect to happen merely by chance

But if the observed values are significantly different from the expected values then there is an association

Question 7

How do we know what the expected values are

Answer 7

Expected values: are the values you would expect to see in each cell if no association existed between the two variables
Row total x column total/ grand total

Question 8

Chi-square

Answer 8

The chi-square statistic measures the degree of difference between the observed and expected frequencies
1) square each O-E value
2) Divide each result by its expected values
3) add up all the results

Question 9

Interpreting Chi-squared

Answer 9

should always be either zero or a positive number. If it is not zero, then an association exists
But is it a statistically significant association
We also want to know how strong association it is

Question 10

Chi-square p-value

Answer 10

To get P-value we need to know the degrees of freedom
To calculate the degree of freedom for chi-square

Question 11

Critical value table

Answer 11

shows you critical value and tell you the value your statistic must be greater than to be significant

Question 12

Two effect size. Phi-coefficient and Cramer’s V

Answer 12

Both give a value between 0 and 1. Further from 0 the stronger the association between the two variable.
Takes both sample size into account

Question 13

Phi and Cohen’s V

Answer 13

the value should be equal too or greater than that given on the table to fall into that category.
As a percentage of their maximum possible variation