You are on page 1of 2

a.

Partitioning the data into three equal depth bins means dividing the data into three groups
with roughly the same number of data points in each group. Since there are 27 data points,
each group should ideally contain 9 data points.

1. Partitioning the data:

• Bin 1: 13, 15, 16, 16, 19, 20, 20, 21, 22

• Bin 2: 22, 25, 25, 25, 25, 30, 33, 33, 35

• Bin 3: 35, 35, 35, 35, 36, 40, 45, 46, 52, 70

2. Smoothing by bin means:

• Calculate the mean value for each bin.

• Bin 1 mean:
13+15+16+16+19+20+20+21+229≈18.78913+15+16+16+19+20+20+21+22
≈18.78

• Bin 2 mean:
22+25+25+25+25+30+33+33+359≈28.33922+25+25+25+25+30+33+33+35
≈28.33

• Bin 3 mean:
35+35+35+35+36+40+45+46+52+7010≈44.901035+35+35+35+36+40+45+46
+52+70≈44.90

3. Replace each data point in the bin with the bin mean:

• Bin 1: 18.78, 18.78, 18.78, 18.78, 18.78, 18.78, 18.78, 18.78, 18.78

• Bin 2: 28.33, 28.33, 28.33, 28.33, 28.33, 28.33, 28.33, 28.33, 28.33

• Bin 3: 44.90, 44.90, 44.90, 44.90, 44.90, 44.90, 44.90, 44.90, 44.90, 44.90

This completes the smoothing by bin means.

b. How might you determine outliers in the data?

Outliers can be determined using various methods such as:

• Z-score method: Identify data points that fall more than a certain number of standard
deviations away from the mean.

• Interquartile range (IQR) method: Identify data points that fall below Q1−1.5×IQR or above
Q3+1.5×IQR, where Q1 and Q3 are the first and third quartiles, respectively, and IQR is the
interquartile range.

• Visualization methods such as boxplots or scatterplots.


c. What other methods are there for data smoothing?

Apart from smoothing by bin means, other methods for data smoothing include:

• Median smoothing: Replace each data point with the median of itself and its neighboring
points.

• Moving average: Replace each data point with the average of itself and its neighboring points
within a specified window size.

• Polynomial smoothing: Fit a polynomial curve to the data points to smooth out fluctuations.

• Exponential smoothing: Assign exponentially decreasing weights to past observations to


emphasize recent data.

You might also like