PSYCH 625 Correlation Worksheet PDF

Preview

Summary

WORKSHEET...

Description

PSYCH 625 Correlation Worksheet Complete the questions below in at least 90 words each. Be specific and provide examples when relevant. Cite any sources according to APA guidelines.

Positive Correlation

100000

Yearly Income

15 10 5 0

80000 60000 40000 20000 0

0

50000

100000 150000

0

Negative Correlation 120 100 80 60 40 20 0 0

1

2

3

4

5

Grade Point Average

Income

Weak Positive Correlation 10

Runs Atempted

 A strong positive correlation  A strong negative correlation  A weak positive correlation  A weak negative correlation

Weak Negative Correlation Years oF hIGHER eDUCATION

Draw a scatterplot of each of the following:

Answer

Test Grades

Question

2

4

6

8 10 12 14

Hours watching tv

8 6 4 2 0

0

5

10

15

Yards Gained

20

25

What is the meaning of the p value of a correlation coefficient?

The meaning of a p-value in a Pearson correlation coefficient is to determine whether the correlation between the chosen variables is significant by comparing the p-value to the significance level. Creswell (2018) states how a significance alpha level of 0.05 is what is usually used suggests that the possibility of concluding that a correlation exists, when in fact no correlation exists is 5%. The p-value tells us whether the correlation coefficient is significantly different from 0. Furthermore, a coefficient of 0 signifies that there is no linear relationship. The correlation is statistically significant if the p-value is less than or equal to the significance level (P-value ≤ 0.05), then you can conclude that the correlation is different from 0. Reject the null hypothesis. The correlation is not statistically significant if the p-value is greater than the significance level (P-value > 0.05), then you cannot conclude that the correlation is different from 0. Do not reject the null hypothesis.

Why is it important to know the amount of shared variance when interpreting both the significance and the meaningfulness of a correlation coefficient?

In order for one to understand the correlation coeffecint you would need to know the shared variance in order for it to have significance and meaning. If the variables are correlated then the researcher can predict what the specific degree would be from one to the next variable. One must also understand that there may be more then two variables and that even if there is a very strong relationship between just the two there could be a third that could come into play and that one could possibly have an influence on the other two variables.

If a researcher wanted to predict how well a student might do in college, what variables do you think he or she might examine?

If the researcher was to test the prediction of whether a student would do well in college, some variables that could be used or tested are the student’s class grades and test scores from standardized tests such as the ACT or SAT tests. Being that said, by identifying the causality and directionality, one can predict based on the data whether the student would progress in higher education. In addition, causality refers to the assumption that the correlation indicates a causal relationship between two variables, whereas directionality refers to the inference made with respect to the direction of a causal relationship between two variables (Jackson, 2017). Correlations between variables indicate that when one variable is present at a certain level,

What statistical procedure would he or she use?

the other also tends to be present at a certain level (p. 320). In this case, I think using the Pearson product-moment correlation coefficient (Pearson's r) would be the best procedure for finding the data to support or refute the hypothesis. The Pearson product-moment is the most commonly used correlation coefficient. It is used when both variables are measured on an interval or ratio scale.

How does determining a bestfitting line help us to predict from one variable to another?

When there are correlations that are predictive such as increased consumption of coffee and increased heart rate, the best -fitting line will help predict one variable to the other. On a scatter plot, we can predict how one variable will correlate based on the best-fitting line. According to Jackson, (2017), “The best-fitting line helps to determining[sic] where on the line an individual's[sic] score on one variable lies and then determining what the score would be on the other variable based on this” (p. 335). For example, the regression line in coffee and increased heart rate would be a right slanted upward slope indicating that there is a strong correlation in the independent variable of cups or milligrams (mg) of coffee to the dependent heart rate (hr), and this is predictive from one variable to another, although some confounding variables and sample outliers can play a role in predictiveness unless the sample parameters tighten. Variables can affect predictability such as preexisting cardiac conditions, potency, and manner of consumption, and individual’s tolerance and prior exposure or age. According to Ulanovsky, Haleluya, Blazer, Weissman, (2014), “Caffeine does not have detrimental effects on heart rate variability, heart rate or blood pressure in conventional doses given to premature newborns”(p.620). Ulanovsky’s research is a direct example of atypical correlations between caffeine and increased heart rate; there is difficulty in predicting the variables in this vulnerable population. The data regarding premature newborns and caffeine represented in plots, nonlinear dynamic methods, and tables (Ulanovsky, 2014)....