Exploring Two–Variable Data
In a scatterplot, data points lie perfectly on a downward-sloping straight line; what value would you expect for the sample correlation coefficient?
-1
Exactly zero
Greater than zero
One
In a study examining the relationship between hours studied (X) and exam scores (Y), what significance does finding a correlation coefficient close to -1 imply about these variables?
The exam scores tend to stay constant regardless of how many hours are studied since they are perfectly uncorrelated.
The number of hours studied causes lower exam scores with near certainty due to causation implied by high correlation.
There exists no significant relationship between hours studied and exam scores because correlations near -1 indicate lack of association.
There exists a strong negative linear relationship between hours studied and exam scores.
What does a correlation coefficient of 0 indicate about two variables?
No linear relationship.
A perfect negative linear relationship.
The data points all fall perfectly on a line.
A perfect positive linear relationship.
If a study finds that there is a correlation of between the number of hours studied and exam scores, which of the following best explains why we cannot conclude causation from this correlation?
There might be an outlier influencing the high correlation coefficient observed.
The value of may change if more data points are added, altering the conclusion.
The presence of confounding variables may affect both the hours studied and exam scores.
The sample size for the study could be too small to establish a strong correlation.
What is the term for a numerical measurement describing some type of association between two variables?
Standard deviation
P-value
Correlation coefficient
Z-score
When considering bivariate data where one variable is categorical and one is quantitative, which statistical method should be used to examine if there is an association between the two variables?
Simple linear regression analysis
Two-sample t-test
Point-biserial correlation coefficient
Chi-square test for independence
In an experiment designed to measure how study time correlates with test scores, if an extreme outlier is included in the data set, how might it affect Pearson's r and what should be done?
Outliers have no effect on Pearson's r since it measures only linear association without considering individual data points' magnitude.
It could significantly inflate or deflate Pearson's r, and it may need to be investigated further and possibly removed if it is influential.
The correlation coefficient automatically adjusts its calculation for outliers by assigning them less weight in determining linearity strength.
An outlier will correct for skewness in the distribution and provide a more accurate value of Pearson's r reflecting all aspects of data variability.

How are we doing?
Give us your feedback and let us know how we can improve
Given that variable X has a strong positive association with Y for lower values but a weak or no association for higher values, how might this heteroscedasticity impact the calculation and interpretation of their Pearson's r?
It may lead to an underestimate of r for low values and overestimate at high values.
Heteroscedasticity does not affect Pearson's r calculations or interpretations.
It will cause an underestimation in r only at higher value ranges.
It will result in a consistently overestimated r across all ranges.
Which symbol is commonly used to represent the sample correlation coefficient?
μ
β
r
σ
When the correlation coefficient is 0, it implies?
No linear relationship between the variables.
A weak positive relationship.
A perfect positive relationship.
A strong positive relationship.