In: Statistics and Probability
Your worksite has instituted a new wellness program. As part of the plan for future evaluation of the effectiveness of the program, data are collected on a variety of health measures. These data are being collected every three months for the next two years. One of the measures collected by researchers was employee's cholesterol level. Initial data for 60 employees is listed below.
205 |
327 |
189 |
205 |
148 |
139 |
178 |
157 |
188 |
301 |
195 |
185 |
164 |
182 |
201 |
248 |
298 |
264 |
177 |
169 |
174 |
169 |
155 |
188 |
194 |
192 |
177 |
189 |
188 |
176 |
158 |
305 |
248 |
189 |
209 |
159 |
202 |
177 |
278 |
268 |
166 |
285 |
249 |
203 |
199 |
170 |
165 |
180 |
201 |
209 |
301 |
188 |
165 |
173 |
183 |
206 |
202 |
283 |
207 |
156 |
1. Find the highest and the lowest scores and place your data into an array, arranging values from highest to lowest
2. Evaluate your data. Do you see any clusters of scores, and are there any gaps in the data
3. What intervals should be used and why. Remember that your intervals must be equal and non-overlapping. Your intervals do NOT need to begin or end with your highest/lowest values.
4. Construct a frequency table for these data including intervals, frequency, relative frequency, and cumulative relative frequency and then create histograms and frequency polygons for these data.
Highest score =327
Lowest score =139
Range =188
Since sample size is 60,by rule of thumb we take 10 classes and the width is 188/10 approx.equal to 20
So we take class intervals from 130-149,150-169,...,310-329
The descending order array and the corresponding frequency table with relative and cumulative frequency are given below
by examining the frequency table , the clusters between 150 to 210 has more points in it
Histogram
The frequency polygon is obtained by joining the mid points of each bar in the histogram by line.