Brainscape's Knowledge GenomeTM

Browse over 1 million classes created by top students, professors, publishers, and experts.


See full index

KNSS 209: Measurement and Evaluation > Correlation and Regression > Flashcards

Correlation and Regression Flashcards

1
Q

What is correlation?

A

used to determine the relationship between variables or factors

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

What is the correlation coefficient?

A

a measure of the degree of relationship between 2 variables or two sets of scores

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

If the points on a scatterplot graph almost form a straight line, this means ….

A

there is a correlation

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

If one variable increases as does the other variable, this means the correlation is _____.

A

positive

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

Trend line slanting up to the right means the correlation is _______.

A

positive

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

If one variable increases while the other variable decreases, this means the correlation is _______.

A

negative

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

Trend line slanting down to the right means the correlation is _______.

A

negative

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

Correlation is always a number between ______ and ______.

A

-1.00 and +1.00

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

+1.00 correlation indicates…

A
  • a perfect correlation
  • a perfect positive relationship or correspondence
  • all dots are co-linear
How well did you know this?
1
Not at all
2
3
4
5
Perfectly
10
Q

-1.00 correlation indicates …

A
  • a perfect negative correlation
  • inverse relationship between the two sets of scores
  • all dots are co-linear
How well did you know this?
1
Not at all
2
3
4
5
Perfectly
11
Q

-0.0 correlation indicates …

A
  • no correlation or relationship

- flat line with no slope

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

Correlations are shown by …

A
  • correlation coefficients

- p or r

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

Correlations can be but are not necessarily _____ and _____.

A

cause and effect

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

Give an example of when correlation is cause and effect.

A
  • Leg Strength and Sprint Speed

- they are related and one probably causes the other to be true.

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

Give an example of when correlation is not cause and effect.

A
  • Caffeine Consumption and Grades
  • they may be a high correlation, but drinking lots of coffee does not necessarily give you good grades
  • It may give you the ability to study long hours but the grades are not the direct result of the coffee
How well did you know this?
1
Not at all
2
3
4
5
Perfectly
16
Q

What are the words used to categorize correlation coefficient?

A
  • excellent
  • high
  • average
  • unacceptable
How well did you know this?
1
Not at all
2
3
4
5
Perfectly
17
Q

What is the range for excellent correlation coefficient?

A

±.90 to ±1.00

18
Q

What is the range for high correlation coefficient?

A

±.80 to ±.89

19
Q

What is the range for average correlation coefficient?

A

±.60 to ±.79

20
Q

What is the range for unacceptable correlation coefficient?

A

< ±.59

21
Q

Spearman rho rank order correlation coefficient is the one where we ….

A
  • re-create the table with all the columns

- write your own formula since excel does not have a function for this

22
Q

To determine the rank order correlation coefficient, the steps are:

A
  1. the scores fro each variables are listed and ranked
  2. the difference in ranks is determined
  3. the difference in ranks is squared
23
Q

If scores are identical when using the spearman rho correlation coefficient method, those tied scores are given ….

A

the mean value of the number of tied ranks

24
Q

Ex. what if 3 scores are tied in rank for 2, 3, and 4th place?

A
  • add up 2+3+4
  • 9/3
  • each one has a rank of 3
25
Q

Ex. what if 2 scores are tied in rank for 3rd and 4th place?

A
  • add up 3+4
  • 7/2
  • each one has a rank for 3.5
26
Q

Pearson correlation coefficient is the one where we…

A
  • create a table in excel with the raw scores only (x and y columns)
  • use the =CORRELATION formula in excel
27
Q

Which method of calculating correlation coefficients is more accurate?

A

Pearson correlation coefficient

28
Q

How do we check the “goodness” of a correlation coefficient?

A

coefficient of determination

29
Q

What does the coefficient of determination do?

A
  • theoretical approximation of the amount of similar quantities found in the two variables being compared
30
Q

How is the coefficient of determination calculated?

A
  • squaring the correlation coefficient

- p^2 or r^2

31
Q

If the coefficient of determination is 0.81, this means …

A

81% of whatever makes this person ____ is also responsible for making him _____

32
Q

The “whatever makes this person _____” of interpreting the coefficient of determination could be a composite of factors such as:

A
  • strength
  • explosive power
  • reaction time
  • desire to win
33
Q

What is regression?

A
  • used to show relationship

- predict or determine the performance of a variable from another variable

34
Q

Why is regression or prediction important in the development of many tests in physical education?

A

can predict a variable that is difficult to measure

35
Q

Give an example of how regression can be used in a test for physical education.

A
  • max VO2 testing requires expensive lab equipment and lots of time
  • regression equation for predicting VO2 from scores on a 12 minute run is used
36
Q

The stronger the correlation between the 2 variables…

A

the better the regression equation will be at predicting

37
Q

When the regression formula is graphed, it forms …

A

the line of best fit

38
Q

What is the regression equation?

A

y = mx + b

39
Q

What is y?

A

represents the variable we want to determine (predict)

40
Q

What is x?

A

represents the variable score used to predict y

41
Q

What is m?

A
  • represents the amount of change in y associated with each unit change in x
  • aka slope
  • indicates if the relationship is positive or negative
42
Q

What is b?

A
  • represents the constant adjustment that must be made in order to put x and y on the same scale
  • aka y-intercept of the line

KNSS 209: Measurement and Evaluation (9 decks)

Brainscape helps you reach your goals faster, through stronger study habits.
© 2024 Bold Learning Solutions. Terms and Conditions