This question asks about the effect of removing an outlier on correlation strength. The scatterplot shows a general negative trend (as ads increase, click rate decreases), but one point deviates significantly from this pattern. When an outlier doesn't follow the trend of the other points, removing it typically strengthens the correlation because the remaining points follow a clearer, more consistent pattern. The correlation would remain negative (not switch to positive) but become stronger as the data becomes more linear. Remember that outliers that deviate from the overall pattern tend to weaken correlation, so their removal strengthens it.

This question asks about interpreting the slope of the line of best fit in context. The slope represents the rate of change in battery percentage (y) per hour of usage (x). Since the line slopes downward from left to right, the slope is negative, indicating battery percentage decreases as usage time increases. Looking at the line, for each additional hour of use, the battery percentage drops by approximately 8 percentage points - this is what the slope of -8 means in this context. A common error is confusing the units or direction of change, or interpreting slope as the starting value rather than the rate of change. Remember that slope always represents change in y per unit change in x.

This question requires calculating both predicted and actual values, then finding their difference. Using the equation y = 2.5x + 5, when x = 20 pages, the predicted time is y = 2.5(20) + 5 = 50 + 5 = 55 minutes. The actual time spent was 62 minutes. The difference is 62 - 55 = 7 minutes, so the actual time was 7 minutes greater than predicted. This type of residual calculation helps us understand how well the model fits individual data points. Students often make arithmetic errors or confuse which value to subtract from which. Always calculate predicted minus actual (or actual minus predicted) consistently to avoid sign errors.

This question asks about the meaning of the slope in the equation y = -1.5x + 120. The slope is -1.5, which means for each 1-unit increase in x (temperature), y (reaction time) decreases by 1.5 units. Since temperature is measured in °C and reaction time in seconds, this translates to: for each 1°C increase in temperature, reaction time decreases by 1.5 seconds. The negative slope indicates an inverse relationship - as temperature goes up, reaction time goes down. Students often confuse the sign of the slope or misinterpret what the variables represent. Remember that slope represents the rate of change: how much y changes for each unit change in x.

This question asks about the slope of the line of best fit in the context of packages delivered versus driving time. The slope represents the additional minutes of driving time per additional package. Looking at the line, we can estimate the slope by finding two points on the line and calculating rise over run. The line appears to increase by about 20 minutes for every 10 packages, giving a slope of 20/10 = 2 minutes per package. This means each additional package is associated with about 2 more minutes of driving time. When interpreting slope in context, always include the appropriate units.

This question asks about the correlation between sugary drinks consumed and health score. The scatterplot shows that as sugary drinks increase (moving right), health scores decrease (moving down), indicating a negative correlation. The points follow a relatively clear downward trend with little scatter, making this a strong negative correlation. Choice D is incorrect because correlation never proves causation, regardless of how strong the correlation is. When describing correlation, use terms like "strong" or "weak" to indicate how closely points follow the trend, and "positive" or "negative" to indicate the direction.

This question asks about the meaning of slope in the context of mass versus volume. In a scatterplot with mass on the x-axis and volume on the y-axis, the slope represents the change in y per unit change in x, which is the change in volume per unit change in mass. Specifically, the slope tells us how many milliliters the volume increases for each 1-gram increase in mass. Choice D is incorrect because slope represents an absolute change, not a percent change. Understanding slope in context means translating "rise over run" into the specific units and variables of the problem.

This question asks which statement is supported by the scatterplot of class size versus average project score. The scatterplot shows a negative trend - as class size increases, average scores tend to decrease. However, correlation does not imply causation; the scatterplot shows an association but cannot prove that class size causes the score differences. Choice A correctly states this relationship while acknowledging the limitation. Choices B and C misrepresent the pattern, and choice D makes an unsupported causal claim with a specific numerical prediction. When interpreting scatterplots, distinguish between describing patterns (what we observe) and making causal claims (what causes what).

This question asks about the association between time a candle burned and length burned. The scatterplot shows that as time increases (moving right), length burned increases (moving up), indicating a positive association. The points follow a very clear linear pattern with little scatter, making this a strong positive association. This relationship makes physical sense - the longer a candle burns, the more of its length is consumed. When describing association strength, consider how closely the points follow a linear pattern; tightly clustered points indicate strong association.

This question asks for a reasonable interpretation of the relationship between stretching time and injuries. The scatterplot shows a negative association - more stretching is associated with fewer injuries. However, this observational data cannot prove that stretching prevents injuries; there could be other factors involved (athletes who stretch more might also be more careful in general). Choice A correctly describes the association while acknowledging the limitation that correlation doesn't prove causation. This is a key principle in data analysis: scatterplots can show relationships but cannot establish cause and effect.