Associations and concepts Flashcards

1
Q

What are the four components of a research question

A
  1. a question mark
  2. CONSTRUCTS
  3. the study POPULATION
  4. Driving word
How well did you know this?
1
Not at all
2
3
4
5
Perfectly
2
Q

What are the three forms of relationship that we consider in this course?

A

Association
Prediction
Difference

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
3
Q

Z scores are nothing but standardised deviation scores, T/F

A

TRUE

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
4
Q

A confidence interval estimator that contains the true population parameter on average 95% of the time over the long run is described as…

A

unbiased

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
5
Q

A confidence interval estimator that gets increasingly accurate as the sample size gets bigger is described as…

A

consistent (ironically)

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
6
Q

The characteristic that is used to describe confidence interval estimators that are comparatively narrow (or wide) is …

A

efficiency

narrow = more efficient

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
7
Q

‘vary in a systematic way’ is linked to what type of research question

A

Association

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
8
Q

What is the difference between covariance and correlation

A

Correlation is standardised covariance (it is calculated on Z scores)

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
9
Q

In what type of thing will you find frequencies, frequency counts, or just counts

A

A contingency table

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
10
Q

What is the difference between observed and expected frequencies in a contingency table?

A
Observed = the actual counts
Expected = what you'd expect if there was no relationship between column and row variables (kinda like chance?)
How well did you know this?
1
Not at all
2
3
4
5
Perfectly
11
Q

The probability of an event occurring plus the probability of it not occurring must always equal…

A

1

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
12
Q

What is the range of possible values for an odds ratio?

A

0 to + infinity

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
13
Q

Can an odds ratio be negative?

A

Noooooo

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
14
Q

What is the reciprocal of an odds ratio value of 0.25?

A

Well that would be 4

Because:

1/0.25 = 4

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
15
Q

What is the reciprocal of an odds ratio of 5?

A

0.2

Because

1/5 = 0.2

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
16
Q

How may an association between two categorial variables be most easily identified in a mosaic plot?

A) By more than one row being present in the plot.

B) By different heights for the same coloured rectangle for each of the different categories displayed in the X axis of the plot.

C) By more than one column being present in the plot.

D) By different colours being present in the plot.

A

B

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
17
Q

Which of the following statements is most correct about an odds ratio?

A) The odds ratio compares the relative size of the odds of two different events occurring.

B) An odds ratio value of 0 means that there is no association between two variables.

C) The odds ratio must always be greater than or equal to 1.

D) The odds ratio value will always be between -1 and +1

A

A

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
18
Q

Which of the following statements is incorrect?

A) Chi-square values are in a squared metric, and therefore must be non-negative in value.

B) Chi-square values can range between minus and plus infinity.

C) For a particular chi-square value, the corresponding obtained probability value depends on the degrees of freedom.

D) Chi-square distributions have different amounts of skewness, depending on the degrees of freedom.

A

B

19
Q

Which of the following statements about the concept of odds is most correct?

A) Odds equal the frequency of one event occurring minus the frequency of a second event occurring.

B) Odds equal the probability of an event occurring relative to the probability of it not occurring.

C) Odds equal the ratio of one category to a second category.

D) Odds equal the ratio of one variable to a second variable.

A

B

20
Q

Which of the following is incorrect about a contingency table?

A) It can only be formed from variables each containing only 2 categories.

B) The column variable can contain 2 or more categories.

C) The row variable can contain 2 or more categories.

D) Each cell in the contingency table is defined by one category of the row variable and one category of the column variable.

A

A

21
Q

What is a construct?

A

An unobservable attribute of a person

22
Q

What is a measure

A

A method for measuring a construct

23
Q

How do you calculate a Z score?

A

Dividing the deviation score by the standard deviation

24
Q

The mean of Z scores always equals 1, T/F

A

FALSE

It always equals 0

25
Q

To take a score and transform it so that it has a predefined mean and uses predefined scaling is called…

A

standardising

26
Q

Means, standard deviation, variation, correlation are all examples of…

A

summary statistics

27
Q

Pearson’s r is a measure of what?

A

Correlation

28
Q

What guy/letter do we use for correlation?

A

Pearson’s r

29
Q

What do you find in a marginal cell within a contingency table?

A

The count of everything that falls within a single category

as opposed to joint cells, which contain the count of everything that is in two categories

30
Q

When do you use Cramer’s V?

A

To measure the strength of association in a contingency table

31
Q

What’s the guy/letter we use to measure strength of association in a contingency table?

A

Cramer’s V

32
Q

Cramer’s V measures both strength and direction, T/F

A

FALSE!

It measures strength but not direction

33
Q

Cramer’s V can range from what to what?

A

0 and 1

34
Q

Would a Cramer’s V of .27 be strong or weak?

A

WEAK

35
Q

A correlation is an example of an effect size, T/F

A

TRUE

And so is Cramer’s V

36
Q

What is the definition of VARIATION?

A

The total amount of variability from the mean in a distribution of scores

37
Q

How is VARIATION calculated?

A
  1. Measure all the deviations from the mean
  2. Square each one
  3. Sum all the squares

Hence it’s sometimes called ‘sum of squares’ or ‘sum of squared deviations’

38
Q

What is VARIANCE?

A

The average squared deviation (ie average variation)

39
Q

In what unit is VARIANCE expressed?

A

A squared metric

40
Q

How is VARIANCE calculated?

A
  1. Measure all the deviations from the mean
  2. Square each one
  3. Calculate the average of all squared deviations

(I’m pretty sure…)

41
Q

How do you calculate STANDARD DEVIATION?

A

The square root of the VARIANCE

42
Q

What is the St Dv of a Z score?

A

1

43
Q

Can a deviation score tell you how far you are from the mean?

A

No (but a Z score can!)