NTN Data Analytics 2 — Questions and Answers
Question 1: A fire department recorded 450 emergency calls in January, 380 in February, and 520 in March. What is the average number of monthly calls for this quarter?
- 400
- 450 (Correct answer)
- 520
- 383
Correct answer: 450
The average is calculated by adding all values and dividing by the number of months: (450 + 380 + 520) / 3 = 1350 / 3 = 450.
To find the average (mean) of a data set, sum all values and divide by the count of values. Here: 450 + 380 + 520 = 1,350 total calls. Dividing 1,350 by 3 months gives 450 calls per month on average. This type of calculation is commonly used in public safety agencies to identify staffing needs and resource allocation across different time periods.
Question 2: A dispatcher notices that response times have increased by 15% over the past six months. If the original average response time was 8 minutes, what is the current average?
- 9.2 minutes (Correct answer)
- 9.0 minutes
- 8.5 minutes
- 10.2 minutes
Correct answer: 9.2 minutes
A 15% increase on 8 minutes equals 8 × 0.15 = 1.2 minutes. Adding this to the original: 8 + 1.2 = 9.2 minutes.
Percentage increase calculations are fundamental in data analytics for public safety. To find a 15% increase: multiply the original value by 0.15 to get the increase amount (8 × 0.15 = 1.2), then add it to the original (8 + 1.2 = 9.2). Alternatively, multiply by 1.15 directly (8 × 1.15 = 9.2). Tracking response time trends helps agencies identify operational issues and implement corrective measures.
Question 3: Which type of chart would be most appropriate for showing the distribution of crime types across different city districts?
- Line graph
- Stacked bar chart (Correct answer)
- Scatter plot
- Histogram
Correct answer: Stacked bar chart
A stacked bar chart effectively shows the composition of different categories (crime types) across multiple groups (districts), allowing comparison both within and between districts.
Stacked bar charts are ideal when you need to compare the composition of categories across different groups. Each bar represents a district, and the segments within each bar represent different crime types. This allows viewers to see both the total volume per district and the relative proportion of each crime type. Line graphs are better for trends over time, scatter plots for correlations between two variables, and histograms for frequency distributions of a single variable.
Question 4: A law enforcement agency collected data showing that 60% of traffic accidents occur at intersections, 25% on highways, and the remainder on residential streets. If 840 accidents occurred last year, how many happened on residential streets?
- 126 (Correct answer)
- 210
- 504
- 84
Correct answer: 126
Residential streets account for 100% - 60% - 25% = 15% of accidents. 15% of 840 = 840 × 0.15 = 126 accidents.
This problem requires understanding complementary percentages. The three categories must total 100%: intersections (60%) + highways (25%) + residential (15%) = 100%. To find the count for residential streets: 840 × 0.15 = 126 accidents. Data analytics in law enforcement frequently involves breaking down incident data by location type to prioritize safety improvements and allocate patrol resources effectively.
Question 5: When analyzing a data set of officer performance metrics, the median score is 78 and the mean score is 72. What does this suggest about the distribution of scores?
- The distribution is perfectly symmetrical
- The distribution is skewed to the right (positively skewed)
- The distribution is skewed to the left (negatively skewed) (Correct answer)
- There is no relationship between mean and median
Correct answer: The distribution is skewed to the left (negatively skewed)
When the mean is lower than the median, the distribution is left-skewed (negatively skewed), indicating some unusually low scores are pulling the mean downward.
The relationship between mean and median reveals distribution shape. When mean < median, the distribution is left-skewed (negatively skewed) — a few very low scores drag the mean below the median. When mean > median, the distribution is right-skewed. When they are equal, the distribution is approximately symmetric. In this scenario, some officers may have significantly lower performance scores, pulling the average down while the middle value remains higher at 78.
Question 6: A fire department wants to determine if there is a correlation between building age and fire incident frequency. Which statistical measure would be most appropriate?
- Standard deviation
- Pearson correlation coefficient (Correct answer)
- Mode
- Range
Correct answer: Pearson correlation coefficient
The Pearson correlation coefficient measures the strength and direction of the linear relationship between two continuous variables, making it ideal for examining the relationship between building age and fire frequency.
The Pearson correlation coefficient (r) ranges from -1 to +1 and measures the strength and direction of a linear relationship between two continuous variables. An r close to +1 indicates a strong positive correlation (as building age increases, fires increase), while r close to -1 indicates a strong negative correlation. Standard deviation measures spread within a single variable, mode identifies the most frequent value, and range shows the difference between maximum and minimum values — none of these measure relationships between two variables.
NTN Data Analytics 2
A fire department recorded 450 emergency calls in January, 380 in February, and 520 in March.
What is the average number of monthly calls for this quarter?