SDA: Survey Analysis

Question 1

What are Causal Models?

Answer 1

Models highlighting bi-variate or multi-variate relationships

Table must show more than correlation because correlation does not imply causation!

Question 2

What is a bi-variate relationship/model?

Answer 2

‘x’ causes or has an effect on ‘y’ (two variables)

Question 3

What is a multi-variate relationship/model?

Answer 3

Independent causes of a response e.g. age, gender, social class and smoking all influence illness rates (more than one independent variable)

Question 4

What 3 conditions must be met for causality models?

Answer 4

1. Covariance
2. Temporal Precedence
3. Production

Question 5

What is Covariance?

Answer 5

If ‘x’ causes ‘y’, variations in ‘x’ should lead to variations in ‘y’

Question 6

What is Temporal Precedence?

Answer 6

If ‘x’ causes ‘y’, changes in ‘x’ should occur before corresponding changes in ‘y’

Question 7

What is Production?

Answer 7

Changes in ‘x’ should really produce changes in ‘y’

V. difficult to prove e.g. wet periods follow dry periods, but dry periods are not PRODUCED by wet periods

Question 8

Why do we undertake ‘control by analysis’/sub-group analysis?

Answer 8

It is very difficult to prove the third condition of causality models of Production in non-experimental research, therefore sub-group analysis allows looking to see if relationships hold for different subgroups of a population

Question 9

What do the following show in a Contingency Table:

1. Columns
2. Rows
3. Summing across the rows
4. Summing down the columns

Answer 9

1. Dependent variables (y)
2. Independent variables (x)
3. Row marginal
4. Column marginal

Question 10

What is the calculation for turning counts into row %s to allow for comparisons?

Answer 10

Row % = (cell count/row marginal) * 100

Question 11

What is a good graphical representation used for contingency tables?

Answer 11

Clustered bar charts

Question 12

What is a perfect positive relationship?

Answer 12

E.g. ALL people WITH bronchitis live in high pollution areas

Question 13

What is a perfect negative relationship?

Answer 13

E.g. ALL people WITHOUT bronchitis live in high pollution areas

Question 14

What does the Chi-squared test show?

Answer 14

Shows whether there is a relationship between recorded nominal data, but nothing else

Question 15

What does Cramer’s V test show?

Answer 15

The size of the relationship

Question 16

For the Chi-squared and Cramer’s V test, both +ve and -ve relationships give positive values, so how must the sign of the relationship be found?

Answer 16

Through inspection of contingency tables

Question 17

If the value of the chi-squared and cramer’s v test is 0, what does this say about the relationship?

Answer 17

There is no relationship

Question 18

What is the issue with the chi-squared test?

Answer 18

The value depends on the sample size, i.e. a big value means there was a big sample size, not that there is a very strong relationship

Question 19

What is confounding?

Answer 19

A type of bias arising when the relationship between two things is influenced by a third thing (a confounder)

Can be caused by selection bias when the individuals or groups under study are different

Leads to SPURIOUS relationships

Example: carrying a lighter and smoking 20 day are both related to lung cancer prevalence rates. But carrying a lighter is for the cigarettes, not a cause of lung cancer

Question 20

APPARENT relationships between two variables that are in fact spurious, is caused by what?

Answer 20

A ‘hidden’ extraneous confounding variable

Question 21

Why is checking for confounders important?

Answer 21

Because any variables that are deemed to be confounders should not be included in multi-variate analysis