Lecture 2-3: Research Questions for Associations

Question 1

*What do good research questions contain?

Answer 1

• A question mark at the end
• All constructs being investigated
• The study population
• A verb that indicates the type of relationship among constructs being proposed

Question 2

*What are the different types of relationships?

Answer 2

• Associate
• Predict
• Different

Question 3

*What is a population?

Answer 3

The complete set of all individuals relevant to our research question and to whom some psychological theory applies.

Question 4

*What is a sample?

Answer 4

A subset of individuals who are selected by some sampling scheme from the population and assumed to be representatives of that population.

Question 5

*What is a construct?

Answer 5

An unobservable attribute of people that we use in both theories and research to explain human behaviour, cognition, and affect.

Question 6

*What is a measure?

Answer 6

Any method for measuring people on a construct that is used to obtain a score, for which there is evidence for its reliability and validity.

Question 7

*What is a score?

Answer 7

A numerical value on a construct measure assigned to an individual by the method of measurement.

Question 8

*What are the four types of scores?

Answer 8

• Raw/observed = Values obtained directly from the construct measure, indicated by a capital letter
• Deviation = Value obtained by subtracting the mean score from each individual score
• Z-score = A standardised score obtained by dividing the deviation score by the SD

Question 9

What is a summary characteristic?

Answer 9

Some kind of aggregation undertaken on the individual values in one or more variables to produce a single quantity that is informative about the values.

Question 10

*What is a population parameter?

Answer 10

An aggregated summary characteristic of individual scores derived from all members of a population.

Question 11

*What is a sample statistic?

Answer 11

An aggregated summary characteristic of individual scores calculated in a single sample drawn from a population.

Question 12

*What forms a population distribution?

Answer 12

The set of scores obtained by measuring everyone in the population on a construct.

Question 13

*What forms a sample distribution?

Answer 13

The set of scores obtained by measuring individuals in a single sample drawn from the population.

Question 14

What do scatterplots tell us?

Answer 14

The strength of a correlation (linear or non-linear).

Question 15

What is a Pearson correlation?

Answer 15

A measure of the linear symmetric association between two continuous variables.

Question 16

What range of values can a correlation be in?

Answer 16

-1 to 1

Question 17

What is a correlation matrix?

Answer 17

The association between multiple variables.`

Question 18

What are correlation plots used for?

Answer 18

They are used to identify patterns among multiple variables.

Question 19

*What effect does a larger sample size have on the sampling distribution?

Answer 19

Reduces variability.

Question 20

*What is a standard error?

Answer 20

The SD of a sampling distribution.

Question 21

*What is a confidence interval?

Answer 21

A range of plausible values of an unknown population parameter based on the value of a single sample statistic and its standard error. It is typically set at 95%.

Question 22

*What are margins of error?

Answer 22

The lengths from the sample estimate to the lower bound and to the upper bound.

Question 23

What does a contingency table contain?

Answer 23

The frequency counts of people in each category of one variable and each category of a second variable.

Question 24

What are mossaic plots?

Answer 24

A two-way table that shows associations.

Question 25

How is the strength of an association measured?

Answer 25

Using Cramer’s V (only strength, not direction), in which the values are between 0 and 1. It can be both a sample statistic or a population parameter.

Question 26

Does Cramer’s V provide a p-value?

Answer 26

No.

Question 27

What are estimators?

Answer 27

Mathematical functions applied to sample scores to obtain an estimated population parameter (or, a formula to obtain a summary characteristic).

Question 28

*What are the two types of estimators?

Answer 28

• Point estimator (if it calculates a sample statistic value)
• Interval estimator (if it calculates a confidence interval)

Question 29

*What are the properties of good interval estimators?

Answer 29

• Unbiased (captures the true population, does not depend on sample size)
• Consistent (the larger the sample size, the closer it is to capturing the true population parameter value 95% of the time, related to sample size)
• Efficient (produces a more narrow CI)

Question 30

*What are effect sizes?

Answer 30

A quantitive measure of the strength of a relationship between construct measures, estimated by sample statistics which can be applied to population parameters. It is more useful when it has a CI.

Question 31

What are examples of effect sizes?

Answer 31

• Regression coefficients
• Means
• Mean differences
• Standardised mean differences
• R-squared

Question 32

What is an odds ratio?

Answer 32

A measure of the strength of an association between two variables that each contain two categories. It is the ratio of two sets of odds formed by considering odds of one category in a variable within each category of the other variable.

Question 33

What are odds?

Answer 33

The probability of one event accusing relative to it not occurring.

Question 34

What do you do if an odds ratio value is less than 1?

Answer 34

• Reverse the ordering of the two categories in one of the variables in the contingency table, and
• Recalculate the odds ratio in the revised table and interpret the estimates that are now greater than 1