Unit 3 Flashcards

Correlation and Prediction (62 cards)

1
Q

what is correlation

A

describes the relationship between two variables

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

what is a scatterplot or scatter diagram

A

shows the pattern of correlation between two variables
a graph that shows hte degree of direciton of relationship between two variables

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

what are the two variables in a scatter plot and what axis are they located on

A

predictor/causing variable - x axis
criterion variable - y axis

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

what are the three patterns of correlation for a scatter diagram

A

positive
negative
no correlation

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

in a positive correlation what happens with the variables

A

both increase together

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

what happens with the two variables in a negative correlation

A

the criterion variable decreases as the predictor variable increases

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

what can be said about the variables in a no correlation scatterplot

A

that they are independent of one another

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

what are the two shapes for the trend line or line of best fit

A

linear or curvilinear

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

what is the indpendent variable

A

the variable that is presumed to cause change in the dependent variable
difference between the control and experimental group
changed to test a hypotheis

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

what is the dependent variable

A

the thing being measured

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
11
Q

what axis do the independent and dependent variable go on

A

indpendent -x
dependent - y

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

what is the formula for a regression line

A

Y = mx + b

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

what do the values in Y=mx+b represent

A

y is the depdendent variable
m is the slope of the line
b is where the line intersects the x axis where y is 0

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

what is the name of the value that tells us the strength and direction of a linear correlation

A

pearson correlation coefficient (r)

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

what does the Pearson correlation coefficient tell us

A

the strength and direction of a linear correlation

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

if data points are far away from the regression line what does this mean

A

it is a weak correlation

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

if data points are close to the regression line what does this mean

A

that it is a strong correlation

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

what type of statistic is the pearson correlation coefficient

A

descriptive statistic

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
19
Q

what is the range of values for the correlation coefficient r

A

-1.00 and +1.00

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
20
Q

what is the cross product of z scores from your two data sets

A

correlation coefficient (r)

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
21
Q

what r values indicate a weak correlation

A

0-0.29

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
22
Q

what values for the correlation coefficient indicate a moderate correlation

A

0.3-0.5

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
23
Q

what r values indicate a strong correlation

A

> 0.5

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
24
Q

what are the 5 steps in calculating the Pearson correlation coefficient (r)

A
  1. calculate the mean and standard deviation for each variable
  2. change all raw scores to Z scores
  3. caclulate the cross product of the Z scores for each person
  4. sum the cross products of Z scores
    divide by the number of people in the study
How well did you know this?
1
Not at all
2
3
4
5
Perfectly
25
what value tells us the amount of variation accounted for by the indpendent variable
coefficient of determination
26
what is the difference between r and r²
r = how strong and in what direction the relationship is. r² = how much of the variation in one variable is explained by the other.
27
explain the issues of causality when interpreting a correlation coefficient
correlation does not prove causation x could cause y y could cause x another third factor could be causing both x and y
28
how would you predict the Z score of the dependent or critierion variable
Predicted Zy = (β)(Zx)
29
what is β
The standardized regression coefficient
30
what is another name for the dependent variable
criterion variable
31
what is another name for the independent variable
predictor variable
32
what does the coefficient of determination r^2 tell us?
the amount of variation accounted for by the independent variable
33
why do we need both r and r^2
r tells us the strength and direction r^2 indicates the amount of variation accounted for by X
34
is r or R^2 used for ANOVA testing
R^2 - used for multiple correlations or multiple regressions
35
what r value would indicate a perfect correlation
-1.00 or + 1.00
36
what is the correlation coefficient
represented by r a statistical index of the relationship between two things -1 to +1
37
what is a true experiment
the only research strategy that can determine that something causes something else
38
what is the direction of causality
path of casual effect; if X is thought to cause Y then the direciton of causality is from X to Y
39
what is a longitudinal study
research in which the same people are restuided and retested over a long period
40
What does the standardized regression coefficient β represent
regression coefficient in a prediction model using Z scores
41
what is a correlation matrix
common way of reporting correlation coefficients amonth several variables in a research article
42
what is multiple correlation
a correlation between one variable and a combined set of predictor variables
42
what is multiple regression
procedure for predicting scores on a criterion variable from scores on two or more predictor variabels
43
What do the asterisks mean in a correlation matrix
statistical significance - associated p values are at the bottom of the matrix
44
what is multiple correlation
association between criterion variable and two or more predictor variables
45
what is a multiple regression
procedure for predicting scores on a criterion variable from scores on two or more predictor variables
46
a correlation descibes the relationship between two ________________
equal-interval numeric variables
47
what are two ways researchers can rule out alternative directions of causality
longitudinal study conduct a true experiment
48
the corrrelation coefficient is also called the
proportion of variance accounted for
49
what is the association of a criterion variable with two or more predictor variables
multiple correlation
50
if the correlation coefficient is .6 what is the proportion of variance accounted for?
.36
51
does a correlation coefficient of 0 necessarily mean that two variables are not correlated?
not necessarily - it doesn't mean there is no relationship. only that there is no linear relationship
52
What are 5 ways in which the correlation coefficient improves our understanding of a relationship beyond what is shown in the scatter diagram
1. quantifies strength of the relationship 2. measures the direction 3. gives a standardized measure 4. detects linear relationships 5. allows for statistical testing
53
Why are Z scores used to calculate a linear regression btw two variables (3)
1. standardize the variables 2. simplify regression math 3. make the slope equal to the correlation
54
what do r² and R² tell us
r²: (only one predictor) the proportion of variance in Y that is explained by X R²- (two or more predictors) the proportion of variance in Y explained by all predictors combined
55
what would you say about an r=0.87
statistically significant and that there is low likelihood that the findings occurred by chance
56
What would you say about r=0.15
not statistically significant and that you cannot conclude that there is a relationship between the variables
57
When would you caclulate r²
when there is a strong correlation between variables which tells us the proportion of varaiation in the criterion variable that can be explained by the predictor variable
58
what type of data is hte mean the best? median? mode?
mean - symmetrical distributions median - skewed distirbutions mode - nominal data
59
define variance
average squared deviation from the mean
60
difference between measures of central tendency and representative values
central tendency - statistics that affect the center of a distribution, mean, median and mode CENTER OF DATA representative values - any statistic that represents the data set as a whole mean, median, mode, standard deviation, variance and range center + spread + standardized values
61