Chapter 6 Correlational Research

I. Correlations

a. Correlation: belief about associations between events in the world

b. Correlational research: used to describe the relationship between two or more naturally occurring variables; looks at how variables vary together or co-vary

c. Positive correlation: both variables go in the same direction: scores on one variable tend to increase as scores on the other variable increase

1. Example: height and weight

d. Negative correlation: scores on one variable tend to decrease as scores on the other variable increase, and vice-versa

1. Example: weather and amount of clothing worn

e. Correlational coefficient: statistic that indicates the degree to which two variables are related to one another

1. Ranges from -1.00 (perfect negative) to +1.00 (perfect positive)

2. 0.0 represents no correlation between the two variables

3. Tells us: direction (sign) and magnitude of relationship (how likely it is for both variables to occur)

4. Most common correlation coefficient: Pearson’s r (used when both variables are continuous)

II. Correlational Relationships

a. Scatterplot: provides a visual representation of the relationship between two variables

b. Correlations are measures of linear relationships

c. Pearson’s r won’t find a relationship that is not linear

d. Yerkes-Dodson effect: curvilinear relationship

1. Correlation coefficients only tell us about linear relationships

2. We need to examine a scatterplot to make sure that variables are not curvilinearly related

III. Coefficient of Determination

a. Coefficient of determination: R² : represents the proportion of variance in one of our variables that is accounted for by the other variable

1. Example: correlation is .4 à R²= .16 à 16% of the variance in variable A can be accounted for by variable B

IV. Statistical Significance

a. Statistical significance exists when a correlation coefficient calculated on a sample has a very low probability of being zero in the population

1. Probability of what we found is not due simply to chance

2. Affected by sample size, magnitude of correlation, and cut-off for significant

V. Correlation Does Not Equal Causation

a. Things needed for causality:

1. Variables correlate

2. One variable precedes the other in time

3. Extraneous factors are controlled for or eliminated

b. Third variable problem: another factor could cause both variables in a connection

c. Partial correlation: allows us to remove the influence of one or more variables (third variables)

d. Correlations are a useful beginning: causal relationship may exist, we just can’t make that conclusion



	PSY3213 PSY3213 TEST 2 Chapter 6 Correlational Research I. Correlations a. Correlation: belief about associations between events in the world b. Correlational research: used to describe the relationship between two or more naturally occurring variables; looks at how variables vary together or co-vary c. Positive correlation: both variables go in the same direction: scores on one variable tend to increase as scores on the other variable increase 1. Example: height and weight d. Negative correlation: scores on one variable tend to decrease as scores on the other variable increase, and vice-versa 1. Example: weather and amount of clothing worn e. Correlational coefficient: statistic that indicates the degree to which two variables are related to one another 1. Ranges from -1.00 (perfect negative) to +1.00 (perfect positive) 2. 0.0 represents no correlation between the two variables 3. Tells us: direction (sign) and magnitude of relationship (how likely it is for both variables to occur) 4. Most common correlation coefficient: Pearson’s r (used when both variables are continuous) II. Correlational Relationships a. Scatterplot: provides a visual representation of the relationship between two variables b. Correlations are measures of linear relationships c. Pearson’s r won’t find a relationship that is not linear d. Yerkes-Dodson effect: curvilinear relationship 1. Correlation coefficients only tell us about linear relationships 2. We need to examine a scatterplot to make sure that variables are not curvilinearly related III. Coefficient of Determination a. Coefficient of determination: R² : represents the proportion of variance in one of our variables that is accounted for by the other variable 1. Example: correlation is .4 à R²= .16 à 16% of the variance in variable A can be accounted for by variable B IV. Statistical Significance a. Statistical significance exists when a correlation coefficient calculated on a sample has a very low probability of being zero in the population 1. Probability of what we found is not due simply to chance 2. Affected by sample size, magnitude of correlation, and cut-off for significant V. Correlation Does Not Equal Causation a. Things needed for causality: 1. Variables correlate 2. One variable precedes the other in time 3. Extraneous factors are controlled for or eliminated b. Third variable problem: another factor could cause both variables in a connection c. Partial correlation: allows us to remove the influence of one or more variables (third variables) d. Correlations are a useful beginning: causal relationship may exist, we just can’t make that conclusion