Interpreting Data Distributions and Outliers - Statistics and Probability

1. Identify the effect of a single very large outlier on the mean (increase, decrease, or no change).

   Increase. Large values pull mean upward in calculation.

2. Which word best compares spreads when one IQR is larger: higher or more variable?

   More variable. Describes greater dispersion in the data.

3. Which word best compares centers when one median is larger: higher or wider?

   Higher. Compares typical values between distributions.

4. Which summary is most appropriate for an approximately symmetric distribution with no outliers: mean and standard deviation, or median and $IQR$?

   Mean and standard deviation. Non-resistant measures work well for clean data.

5. What does the spread of a distribution describe, and name two common measures?

   Variability; IQR and standard deviation measure spread. Spread shows how dispersed the data is.

6. Which measure of spread is more resistant to outliers: IQR or standard deviation?

   IQR. IQR uses middle 50%, unaffected by extremes.

7. Given fences $-2$ and $30$, is $x=31$ an outlier by the $1.5IQR$ rule (yes or no)?

   Yes, because $31>30$. Value exceeds upper fence of $30$.

8. What is the $IQR$ formula in terms of quartiles $Q_1$ and $Q_3$?

   $IQR=Q_3-Q_1$. Difference between third and first quartiles.

9. In a boxplot, which part represents the $IQR$: the box, the whiskers, or the median line?

   The box. Box spans from $Q_1$ to $Q_3$.

10. Two boxplots have equal medians, but Plot A has larger $IQR$ than Plot B; which has greater spread?

    Plot A has greater spread. Larger $IQR$ means more variability in data.

11. What does the spread of a distribution describe, and which two statistics are most common for spread?

    Variability; most common are $IQR$ and standard deviation. Spread measures how far data extends from center.

12. What is the $1.5\times\text{IQR}$ rule for identifying outliers using quartiles?

    Outliers are $<Q_1-1.5\text{IQR}$ or $>Q_3+1.5\text{IQR}$. Values beyond these bounds are unusually extreme.

13. Identify the best center measure for a strongly skewed distribution with outliers: mean or median.

    Median. Median resists outlier influence in skewed data.

14. Given $Q_1=10$, $Q_3=18$, what is $IQR$?

    $8$. Apply formula: $IQR = 18 - 10 = 8$.

15. Which option best describes a right-skewed distribution: mean $>$ median or mean $<$ median?

    Mean $>$ median. Right tail pulls mean above median.

16. What does the shape of a distribution describe (for example, symmetric, skewed, unimodal)?

    Overall pattern: symmetry/skewness, modality, and tail behavior. Shape reveals how data clusters and extends from center.

17. A data set gains one extreme high value. Which statistic changes more: mean or median?

    Mean changes more. Mean includes all values; median only uses middle.

18. Which data set has the larger spread if $\text{IQR}_A=12$ and $\text{IQR}_B=8$?

    Data set $A$. $12>8$, so $A$ has more variability.

19. Which data set has the larger center if $\text{median}_A=52$ and $\text{median}_B=47$?

    Data set $A$. $52>47$, so $A$ has higher typical value.

20. If a distribution is left-skewed, what is the typical relationship between mean and median?

    Mean $<$ median. Left tail pulls mean lower than median.

21. Which option best describes a left-skewed distribution: mean $>$ median or mean $<$ median?

    Mean $<$ median. Left tail pulls mean below median.

22. Which summary is most appropriate for a skewed distribution with outliers: mean and standard deviation, or median and $IQR$?

    Median and $IQR$. Resistant measures handle outliers better.

23. What is the center of a distribution, and which two statistics are most common for center?

    Typical value; most common are mean and median. Center represents where most data values cluster.

24. What is the rule for identifying outliers using fences based on $Q_1$, $Q_3$, and $IQR$?

    Outliers: $x<Q_1-1.5IQR$ or $x>Q_3+1.5IQR$. Values beyond $1.5$ times $IQR$ from quartiles are outliers.

25. Find the outlier cutoffs if $Q_1=10$ and $Q_3=18$ using the $1.5\times\text{IQR}$ rule.

    Lower $=-2$, upper $=30$. $\text{IQR}=8$, so bounds are $10-12=-2$ and $18+12=30$.

26. A data set gains one extreme high value. Which statistic changes more: standard deviation or IQR?

    Standard deviation changes more. SD uses all values; IQR only uses quartiles.

27. Which option best describes a symmetric distribution: mean and median are about equal, or mean far from median?

    Mean and median are about equal. Balanced tails keep mean and median aligned.

28. Which measure of center is more resistant to outliers: mean or median?

    Median. Median uses middle value, unaffected by extreme values.

29. Identify the effect of a single very large outlier on the median (large change or small change).

    Small change (median is resistant). Median position barely shifts with one extreme value.

30. Which measure of spread is more resistant to outliers: standard deviation or $IQR$?

    $IQR$. Based on quartiles, ignores extreme values.

31. What is the center of a distribution, and which two statistics commonly represent it?

    Typical value; mean and median represent center. Center shows where most data clusters.

32. Identify the effect of a single very large outlier on standard deviation (increase, decrease, or no change).

    Increase. Outliers increase squared deviations from mean.

33. What does the shape of a distribution describe (in words) when comparing data sets?

    Symmetry or skewness and the number of peaks (modality). Shape includes distribution pattern and peak count.

34. Given $Q_1=10$, $Q_3=18$, what are the outlier fences using $1.5IQR$?

    Lower $=-2$, upper $=30$. Lower: $10-1.5(8)=-2$; Upper: $18+1.5(8)=30$.

35. Identify the best spread measure for skewed data with outliers: standard deviation or IQR.

    IQR. IQR resists outlier influence better than SD.

36. Identify the distribution shape described by "two distinct peaks separated by a dip."

    Bimodal. Two modes indicate two data concentrations.

37. Which option indicates greater spread in a boxplot: longer box (larger IQR) or higher median line?

    Longer box (larger IQR). Box length shows IQR, which measures spread.

38. If a distribution is right-skewed, what is the typical relationship between mean and median?

    Mean $>$ median. Right tail pulls mean higher than median.

Study these flashcards