W2: RQ for Associations (Page 1-22)

Question 1

What does a good research question contain:

Answer 1

1. ) A question
2. ) All constructs being investigated
3. ) The study population
4. ) A verb that indicates the type of relationship among constructs being proposed

Question 2

What are the 3 types of verbal forms of relationships

Answer 2

Difference; Association; Prediction

Question 3

What does DAP involve

Answer 3

Association = Correlation
Prediction = Linear Regression
Difference = Differences between groups

Question 4

What is a population

Answer 4

COMPLETE set of all individuals relevant to our research question

Question 5

What is a sample

Answer 5

SUBSET of individuals selected by some sampling scheme from the population, assumed to be representative of that population

Question 6

How many population and samples are relevant in our research question

Answer 6

1 population but there can be (theoretically) many possible samples drawn from that population

Question 7

What is a construct

Answer 7

Unobservable attributes to explain human behavior

Question 8

What is a measure. What are some conditions for a measure?

Answer 8

Method to measure people on a construct to obtain a construct score.

Measure must be valid and reliability

Question 9

What is a score

Answer 9

Numerical value of the construct measure

Question 10

What is a raw score and what are they generally indicated by

Answer 10

Values obtained directly from the construct measure.

They are generally indicated by a capital letter (X,Y), which is a variable containing a set of values

Question 11

What is a deviation score and what are they generally indicated by.

Hence

Answer 11

The mean is subtracted from the individual score.

They are generally indicated by lower case letter (x,y)

Hence, X - mean(x) = x

Question 12

What is a z score. What is the mean and sd of z scores

Answer 12

Particular kind of standardized score by dividing a deviation score by standard deviation

Mean = 0
SD = 1
(always)

Question 13

What is a standardized score (Generally speaking)

Answer 13

Raw scores that have been transformed such that they have a predefined mean and a predefined scaling for each unit standard deviation.

IQ: 100
Z: 15

Question 14

Why do we call something a random variable

Answer 14

Each value has an associated probability of ocurrene

Question 15

What is the difference between continuous and discrete random variables

Answer 15

Continuous: Any numerical value within a defined interval (e.g. 0 to 100)

Discrete: Finite number of distinct values (e.g. integers 1,2,3,4,5)

Question 16

If both measures are continuous, we use ___

Answer 16

Correlation

Question 17

If both measures are categorical, we use ____

Answer 17

Contingency Tables

Question 18

What is summary characteristics

Answer 18

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 (e.g. mean; standardd deviation)

Question 19

PPSS

Answer 19

Population - Parameter; Sample - Statistics

Question 20

What is population parameter and sample statistics

Answer 20

PP = Aggregated summary characteristic of individual scores derived from all members of a population

SS = Aggregated summary characteristic of individual scores calculated in a single sample drawn from a population (i.e. there can be many values for a sample statistic, one for each sample drawn from the same population)

Question 21

Do sample distributions vary. What does this imply about the sample mean.

Answer 21

Yes. Sample mean, etc… will randomly differ

Question 22

What is the benefit of scatter plot

Answer 22

Useful for indicating an association. Can be linear/non-linear

Question 23

What is a Pearson Correlation

Answer 23

Measure of LINEAR SYMMETRIC association between 2 CONTINUOUS variables

Question 24

How are associations between multiple variables often presented

Answer 24

Often a correlation matrix

Question 25

What do we use to identify patterns among multiple variables

Answer 25

Correlation plots are preferable for identifying patterns among multiple variables

Question 26

Is positive or negative in value important when discussing association strength

Answer 26

No. We ignore positive or negative

Question 27

What is the population correlation coefficient

Answer 27

p (rho). Correlation calculated on everybody in a population

Question 28

What is the sample correlation coefficient

Answer 28

r. estimated on a sample drawn from a population

Question 29

Do we often know p (rho)?

Answer 29

Almost certainly unknown.

We use the known sample value to estimate the unknown population value (point of research)

Question 30

What is a sampling distribution/distribution of values

Answer 30

A sample statistic obtained from a large number of repeated samples taken from a population

Question 31

What are the effects of having a larger sample size

Answer 31

Larger sample reduces variability of the sampling distribution (i.e. more narrow)

Question 32

What is the SD of the sampling distribution

Answer 32

Standard Error.

Question 33

What can each sample statistic value be regarded as

Answer 33

An estimate of the population parameter value

Question 34

What is a confidence interval. What does it have.

Answer 34

• Range of plausible values* of an unknown population parameter based on the (1) value of a single sample statistic and (2) its standard error.
• Lower bound and upper bound value. Typically set as 95%.

Question 35

What is a random sample. How is it typically done

Answer 35

A Simple Random Sample is one where each member of the population has an EQUAL probability of being selected.

It is typically done via. a uniform probability distribution (without replacement)

Question 36

When we transform a score into a standardized score, what actually changes

Answer 36

Only the scaling of the variable

Question 37

When we transform item scores as continuous, what we declare them in R

Answer 37

Declare them as numeric variables

Question 38

When we treat item scores as discrete, what we delcare them in R

Answer 38

Declare them as factor variable

Question 39

If we measure everyone in the population on a construct, then the set of scores form a …

Answer 39

Population distribution (There is only one)

Question 40

If we measure everyone in a single sample from a construct, then the set of scores form a …

Answer 40

Sample Distribution (There are many possible)

Question 41

Will the population distribution be larger/smaller than a sample distribution

Answer 41

Much Larger

Question 42

What does it mean by “symmetry” in a Pearson Correlation

Answer 42

Correlation of X and Y = Correlation of Y and X

Question 43

What is the correlation value always between

Answer 43

-1 to +1

Question 44

Will any kind of sample statistic have a corresponding sampling distribution. Elaborate

Answer 44

In Theory, yes.
- Anytime we have a distribution of values, we can calculate summary characteristics.

Under conditions, as Sampling increases,

1. ) Mean of sampling distribution will get closer to unknown population parameter value
2. ) SD can be calculated (known as Standard Error)

Question 45

How many types of scores are there

Answer 45

1. ) Raw Score
2. ) Deviation Score
3. ) Z-Score
4. ) Standardised Score

Deviation, Z and Standardized Scores are transformations of Raw Score

Question 46

What do the scores and the transformation actually change

Answer 46

Only the scaling of the variable are changed