Cumulative Frequency and Ogive

14 soru

Soru 1Soru

The table below shows the distribution of scores obtained by 6060 candidates in a competitive aptitude test:

Score Class IntervalFrequency (ff)
101910 - 1955
202920 - 291010
303930 - 391818
404940 - 491515
505950 - 591212

Using cumulative frequency estimation (or linear interpolation), what is the interquartile range of the distribution?

Cevabı ve açıklamayı göster

Cevap: 18.018.0

Cevap

The interquartile range of the distribution is 18.018.0.
The lower quartile (Q1Q_1) corresponds to the 15th15^{\text{th}} rank, which is exactly 29.529.5. The upper quartile (Q3Q_3) corresponds to the 45th45^{\text{th}} rank, which interpolates to 47.547.5. Subtracting Q1Q_1 from Q3Q_3 yields 47.529.5=18.047.5 - 29.5 = 18.0.

Adım Adım Çözüm

1
Construct the cumulative frequency distribution table with upper class boundaries.
Class intervals, upper class boundaries (UCBUCB), frequencies (ff), and cumulative frequencies (cfcf):
- 101910 - 19: UCB=19.5UCB = 19.5, f=5f = 5, cf=5cf = 5
- 202920 - 29: UCB=29.5UCB = 29.5, f=10f = 10, cf=15cf = 15
- 303930 - 39: UCB=39.5UCB = 39.5, f=18f = 18, cf=33cf = 33
- 404940 - 49: UCB=49.5UCB = 49.5, f=15f = 15, cf=48cf = 48
- 505950 - 59: UCB=59.5UCB = 59.5, f=12f = 12, cf=60cf = 60
Cumulative frequencies and upper class boundaries are necessary to determine quartile ranks and values.
2
Find the lower quartile (Q1Q_1).
The position of Q1Q_1 is 14N=14(60)=15th\frac{1}{4} N = \frac{1}{4}(60) = 15^{\text{th}} candidate score. Since the cumulative frequency reaching UCB=29.5UCB = 29.5 is exactly 1515, Q1=29.5Q_1 = 29.5.
The 15th value lies precisely at the upper class boundary of the 202920 - 29 class interval.
3
Find the upper quartile (Q3Q_3) using linear interpolation.
The position of Q3Q_3 is 34N=34(60)=45th\frac{3}{4} N = \frac{3}{4}(60) = 45^{\text{th}} score.
This falls in the 404940 - 49 class interval (UCB=49.5UCB = 49.5, lower boundary L=39.5L = 39.5, f=15f = 15, previous cf=33cf = 33).
Q3=L+(3N4cfprevf)×c=39.5+(453315)×10=39.5+8.0=47.5Q_3 = L + \left(\frac{\frac{3N}{4} - cf_{\text{prev}}}{f}\right) \times c = 39.5 + \left(\frac{45 - 33}{15}\right) \times 10 = 39.5 + 8.0 = 47.5.
Linear interpolation calculates the exact position within the target class interval.
4
Calculate the Interquartile Range (IQR).
IQR=Q3Q1=47.529.5=18.0\text{IQR} = Q_3 - Q_1 = 47.5 - 29.5 = 18.0.
The interquartile range is defined as the difference between the upper quartile and the lower quartile.

Anahtar Kavram

Interquartile Range estimation from Ogive / Cumulative Frequency Distribution
Tahmini Süre:1m 30s
Soru 2Soru

The table below shows the cumulative frequency distribution of the masses (in grams) of 100100 cocoa beans sampled from an agricultural yield:

Mass Class Interval (g)Cumulative Frequency
101910 - 191010
202920 - 293030
303930 - 396565
404940 - 499090
505950 - 59100100

Using linear interpolation from the cumulative frequency distribution, calculate the 75th percentile (Q3Q_3) mass of the cocoa beans in grams.

Cevabı ve açıklamayı göster

Cevap: 43.5

Cevap

The 75th percentile (Q3Q_3) mass of the cocoa beans is 43.5 g43.5\text{ g}.
To find the 75th percentile (Q3Q_3) from cumulative frequency data, calculate the rank 75100×100=75\frac{75}{100} \times 100 = 75. This falls into the 404940 - 49 class interval (boundaries 39.549.539.5 - 49.5). Applying Q3=L+(75Ff)cQ_3 = L + \left(\frac{75 - F}{f}\right)c yields 39.5+(756525)×10=43.5 g39.5 + \left(\frac{75 - 65}{25}\right) \times 10 = 43.5\text{ g}.

Adım Adım Çözüm

1
Calculate the percentile position rank
Rank position is 7575
The 75th percentile corresponds to 75%75\% of the total sample size N=100N = 100, giving 75100×100=75\frac{75}{100} \times 100 = 75.
2
Locate the 75th percentile class interval and its boundaries
Class interval is 404940 - 49, with lower boundary L=39.5L = 39.5 and upper boundary 49.549.5
Cumulative frequency before 404940 - 49 is 6565, and up to 404940 - 49 is 9090. Since 65<759065 < 75 \leq 90, the 75th item falls in this interval.
3
Identify class parameters for interpolation
L=39.5L = 39.5, F=65F = 65, f=25f = 25, c=10c = 10
Lower boundary L=39.5L = 39.5, previous cumulative frequency F=65F = 65, class frequency f=9065=25f = 90 - 65 = 25, class width c=49.539.5=10c = 49.5 - 39.5 = 10.
4
Compute Q3Q_3 using the linear interpolation formula
Q3=43.5 gQ_3 = 43.5\text{ g}
Q3=39.5+(756525)×10=39.5+4=43.5Q_3 = 39.5 + \left(\frac{75 - 65}{25}\right) \times 10 = 39.5 + 4 = 43.5.

Anahtar Kavram

Linear Interpolation of Percentiles from Cumulative Frequency Data
Soru 3Soru

The frequency distribution table below shows the daily rainfall (in mm) recorded across 8080 weather monitoring stations during a storm:

Daily Rainfall (mm)Frequency (ff)
101910 - 1988
202920 - 291414
303930 - 392626
404940 - 492020
505950 - 591212

Using linear interpolation from the cumulative frequency distribution (ogive), what is the 75th percentile (P75P_{75}) of the daily rainfall in mm?

Cevabı ve açıklamayı göster

Cevap: 45.5

Cevap

The 75th percentile of the daily rainfall distribution is 45.5 mm45.5\text{ mm}.
To find the 75th percentile (P75P_{75}), determine the 60th60^{\text{th}} cumulative frequency position (0.75×80=600.75 \times 80 = 60). The value lies within the 404940 - 49 class interval. Applying the lower class boundary L=39.5L = 39.5, preceding cumulative frequency cfb=48cf_b = 48, frequency f=20f = 20, and class width c=10c = 10, linear interpolation yields P75=39.5+604820×10=45.5 mmP_{75} = 39.5 + \frac{60 - 48}{20} \times 10 = 45.5\text{ mm}.

Adım Adım Çözüm

1
Calculate cumulative frequencies across all class intervals.
Cumulative frequencies are 88 for 101910-19, 2222 for 202920-29, 4848 for 303930-39, 6868 for 404940-49, and 8080 for 505950-59. Total frequency N=80N = 80.
Cumulative frequencies are necessary to locate percentile positions on an ogive.
2
Determine the position corresponding to the 75th percentile.
Position =0.75×80=60th= 0.75 \times 80 = 60^{\text{th}} cumulative frequency item.
The 75th percentile represents 75%75\% of the total sample size.
3
Identify the target class interval parameters containing the 60th observation.
The interval 404940 - 49 contains cumulative frequencies from 4949 to 6868. Parameters: L=39.5L = 39.5, c=10c = 10, f=20f = 20, cfb=48cf_b = 48.
Linear interpolation requires the exact boundaries and frequencies of the container class.
4
Apply the percentile interpolation formula P75=L+(60cfbf)×cP_{75} = L + \left(\frac{60 - cf_b}{f}\right) \times c.
P75=39.5+(604820)×10=39.5+6=45.5 mmP_{75} = 39.5 + \left(\frac{60 - 48}{20}\right) \times 10 = 39.5 + 6 = 45.5\text{ mm}.
Calculates the exact rainfall value corresponding to the 75th percentile.

Anahtar Kavram

Linear interpolation for percentiles using cumulative frequency distribution (ogive)
Tahmini Süre:1m 30s
Soru 4Soru

The cumulative frequency distribution table below shows the completion times (in minutes) for 120120 software engineers during a technical skill test:

Time Interval (min)Frequency (ff)Cumulative Frequency (cfcf)
101910 - 1912121212
202920 - 2928284040
303930 - 3940408080
404940 - 492424104104
505950 - 591616120120

Using linear interpolation from the cumulative frequency data, what is the 65th65^{\text{th}} percentile completion time?

Cevabı ve açıklamayı göster

Cevap: 39.0 minutes39.0\text{ minutes}

Cevap

39.0 minutes39.0\text{ minutes}
To find the 65th65^{\text{th}} percentile (P65P_{65}), we calculate 65100×120=78\frac{65}{100} \times 120 = 78. The cumulative frequency table shows that rank 7878 falls within the class interval 303930 - 39. The true lower boundary for this class is L=29.5L = 29.5, the cumulative frequency of the preceding class is F=40F = 40, the frequency of the percentile class is f=40f = 40, and the class width is c=10c = 10. Substituting into P65=L+(78Ff)cP_{65} = L + \left(\frac{78 - F}{f}\right)c yields 29.5+(3840)×10=39.0 minutes29.5 + \left(\frac{38}{40}\right) \times 10 = 39.0\text{ minutes}.

Adım Adım Çözüm

1
Determine the rank of the 65th65^{\text{th}} percentile (P65P_{65}).
Rank =65100×120=78= \frac{65}{100} \times 120 = 78.
The percentile rank identifies the position of the data point within the total frequency N=120N = 120.
2
Identify the percentile class and its boundaries.
Percentile class is 303930 - 39, with lower boundary L=29.5L = 29.5, upper boundary =39.5= 39.5, and class width c=10c = 10.
The cumulative frequency increases from 4040 to 8080 across this interval, containing rank 7878.
3
Apply the linear interpolation formula for percentiles on grouped data.
P65=L+(65N100Ff)×c=29.5+(784040)×10=29.5+9.5=39.0 minutesP_{65} = L + \left(\frac{\frac{65N}{100} - F}{f}\right) \times c = 29.5 + \left(\frac{78 - 40}{40}\right) \times 10 = 29.5 + 9.5 = 39.0\text{ minutes}.
Where F=40F = 40 is the cumulative frequency prior to the class and f=40f = 40 is the frequency of the class.

Anahtar Kavram

Linear Interpolation of Percentiles from Cumulative Frequency Distributions
Soru 5Soru

The frequency distribution table below shows the scores obtained by 5050 candidates in a competitive assessment:

Score IntervalFrequency
101910 - 1955
202920 - 291212
303930 - 391818
404940 - 491010
505950 - 5955

When constructing a cumulative frequency curve (ogive) for this distribution, which of the following ordered pairs (x,y)(x, y) represents the point plotted for the class interval 303930 - 39?

Cevabı ve açıklamayı göster

Cevap: (39.5,35)(39.5, 35)

Cevap

The point plotted on the ogive for the class interval 303930 - 39 is (39.5,35)(39.5, 35).
A cumulative frequency curve (ogive) is constructed by plotting the cumulative frequency of each class against its upper class boundary. For the interval 303930 - 39, the upper boundary is 39.539.5 and the cumulative frequency is 5+12+18=355 + 12 + 18 = 35, resulting in the point (39.5,35)(39.5, 35).

Adım Adım Çözüm

1
Determine the upper class boundary for the class interval 303930 - 39
Upper class boundary = 39+402=39.5\frac{39 + 40}{2} = 39.5
Cumulative frequencies in an ogive are plotted against the upper boundaries of each class interval.
2
Calculate the cumulative frequency up to the class interval 303930 - 39
Cumulative frequency = 5+12+18=355 + 12 + 18 = 35
The cumulative frequency is the running sum of frequencies up to and including the given interval.
3
Combine the upper class boundary (xx-axis) and cumulative frequency (yy-axis) into an ordered pair (x,y)(x, y)
Point = (39.5,35)(39.5, 35)
In an ogive, points are plotted as (Upper Class Boundary, Cumulative Frequency).

Anahtar Kavram

Plotting Points on a Cumulative Frequency Curve (Ogive)
Soru 6Soru

The frequency distribution table below shows the marks obtained by 4040 students in a mathematics quiz:

Mark IntervalFrequency (ff)
1101 - 1055
112011 - 2088
213021 - 301212
314031 - 401010
415041 - 5055

From a cumulative frequency curve (ogive) constructed for this data, what is the score corresponding to the 40th40^{\text{th}} percentile?

Cevabı ve açıklamayı göster

Cevap: 23.023.0

Cevap

23.023.0
To find the 40th percentile score, calculate 40%40\% of the total 4040 students, which gives the 16th16^{\text{th}} cumulative student. The 16th16^{\text{th}} student falls in the 213021 - 30 mark interval, which has a lower class boundary of 20.520.5. Interpolating gives 20.5+(161312)×10=20.5+2.5=23.020.5 + \left(\frac{16 - 13}{12}\right) \times 10 = 20.5 + 2.5 = 23.0.

Adım Adım Çözüm

1
Construct the cumulative frequency distribution table.
Cumulative frequencies (CFCF): 11051-10 \rightarrow 5; 11201311-20 \rightarrow 13; 21302521-30 \rightarrow 25; 31403531-40 \rightarrow 35; 41504041-50 \rightarrow 40. Total frequency N=40N = 40.
Cumulative frequencies are needed to locate percentile positions on an ogive.
2
Determine the rank position for the 40th percentile (P40P_{40}).
Rank position =0.40×40=16th= 0.40 \times 40 = 16^{\text{th}} position.
The 40th percentile represents the value below which 40%40\% of the observations fall.
3
Identify the percentile class interval and its boundaries.
Since 13<162513 < 16 \leq 25, the 16th16^{\text{th}} position lies in the interval 213021 - 30. Lower class boundary L=20.5L = 20.5, cumulative frequency preceding the class CFb=13CF_b = 13, class frequency f=12f = 12, and class width c=10c = 10.
Interpolation on an ogive relies on the lower class boundary of the target interval.
4
Apply the linear interpolation formula for percentiles.
P40=L+(RankCFbf)×c=20.5+(161312)×10=20.5+2.5=23.0P_{40} = L + \left( \frac{\text{Rank} - CF_b}{f} \right) \times c = 20.5 + \left( \frac{16 - 13}{12} \right) \times 10 = 20.5 + 2.5 = 23.0.
This yields the exact mark corresponding to the 40th percentile reading from the ogive.

Anahtar Kavram

Calculating percentiles from a cumulative frequency distribution or ogive
Tahmini Süre:1m 30s
Soru 7Soru

The table below presents the cumulative frequency distribution of examination marks for 6060 candidates:

Mark BoundaryCumulative Frequency
<20.5< 20.555
<40.5< 40.51818
<60.5< 60.54242
<80.5< 80.55454
<100.5< 100.56060

How many candidates scored between 40.540.5 and 80.580.5 marks?

Cevabı ve açıklamayı göster

Cevap: 36

Cevap

36 candidates
To find the number of candidates with scores between 40.540.5 and 80.580.5, subtract the cumulative frequency of scores below 40.540.5 (1818) from the cumulative frequency of scores below 80.580.5 (5454). This gives 5418=3654 - 18 = 36.

Adım Adım Çözüm

1
Find the cumulative frequency up to the upper boundary of 80.580.5
Cumulative frequency (FupperF_{\text{upper}}) = 5454
This represents the total number of candidates scoring below 80.580.5 marks.
2
Find the cumulative frequency up to the lower boundary of 40.540.5
Cumulative frequency (FlowerF_{\text{lower}}) = 1818
This represents the total number of candidates scoring below 40.540.5 marks.
3
Calculate the number of candidates within the interval (40.5,80.5)(40.5, 80.5) by finding the difference
5418=3654 - 18 = 36
Subtracting the cumulative frequency at 40.540.5 from that at 80.580.5 isolates the count of candidates within this specific mark range.

Anahtar Kavram

Finding class frequency from cumulative frequency boundaries
Soru 8Soru

When constructing a standard cumulative frequency curve (ogive) for a grouped frequency distribution, against which statistical values on the horizontal axis are the cumulative frequencies plotted?

Cevabı ve açıklamayı göster

Cevap: Upper class boundaries

Cevap

Upper class boundaries
In statistics, an ogive is constructed by plotting cumulative frequency on the vertical axis against the upper class boundaries of each interval on the horizontal axis.

Adım Adım Çözüm

1
Identify the definition of a cumulative frequency curve (ogive).
An ogive displays running totals of data values up to a given upper limit.
By definition, the cumulative frequency at any point represents all observations up to and including the upper boundary of that class.
2
Determine the correct variable for the horizontal axis.
The horizontal axis must represent the upper class boundaries (xx-axis), while the vertical axis represents cumulative frequency (yy-axis).
This ensures the curve accurately reflects cumulative proportions at the end of each class interval.

Anahtar Kavram

Plotting Cumulative Frequency Curves (Ogives)
Tahmini Süre:45s
Soru 9Soru

The table below details the cumulative frequency distribution of the masses, in kg\text{kg}, of 8080 agricultural packages recorded during an export inspection:

Mass Boundary (kg\text{kg})Cumulative Frequency
19.5\leq 19.588
29.5\leq 29.52424
39.5\leq 39.55252
49.5\leq 49.57272
59.5\leq 59.58080

Using linear interpolation on the cumulative frequency data, determine the interquartile range of the package masses in kg\text{kg}.

Cevabı ve açıklamayı göster

Cevap: 16.5

Cevap

The interquartile range of the package masses is 16.5 kg16.5\text{ kg}.
The interquartile range measures the spread of the middle 50%50\% of the data and is computed as Q3Q1=43.527.0=16.5 kgQ_3 - Q_1 = 43.5 - 27.0 = 16.5\text{ kg}.

Adım Adım Çözüm

1
Find the lower quartile (Q1Q_1)
Q1=27.0 kgQ_1 = 27.0\text{ kg}
The rank for Q1Q_1 is 14×80=20\frac{1}{4} \times 80 = 20, which lies in the 19.529.519.5 - 29.5 boundary interval with cumulative frequency increasing from 88 to 2424.
2
Find the upper quartile (Q3Q_3)
Q3=43.5 kgQ_3 = 43.5\text{ kg}
The rank for Q3Q_3 is 34×80=60\frac{3}{4} \times 80 = 60, which lies in the 39.549.539.5 - 49.5 boundary interval with cumulative frequency increasing from 5252 to 7272.
3
Calculate the Interquartile Range
IQR=16.5 kg\text{IQR} = 16.5\text{ kg}
Interquartile Range is the difference between the upper quartile (Q3Q_3) and lower quartile (Q1Q_1).

Anahtar Kavram

Interquartile Range from Cumulative Frequency Distribution
Soru 10Soru

The cumulative frequency distribution of the operational lifespans (in hours) for a batch of 100100 precision LED modules tested in a laboratory is summarized below:

Lifespan Interval (hours)Class BoundariesCumulative Frequency
100119100 - 11999.5119.599.5 - 119.51010
120139120 - 139119.5139.5119.5 - 139.52525
140159140 - 159139.5159.5139.5 - 159.56060
160179160 - 179159.5179.5159.5 - 179.58585
180199180 - 199179.5199.5179.5 - 199.5100100

Using linear interpolation for cumulative frequency distributions, calculate the 75th percentile (P75P_{75}) of the lifespan of these modules in hours.

Cevabı ve açıklamayı göster

Cevap: 171.5

Cevap

The 75th percentile of operational lifespan is 171.5 hours.
The 75th percentile rank position is 0.75×100=750.75 \times 100 = 75. The percentile falls within the class boundary 159.5179.5159.5 - 179.5. Substituting lower class boundary L=159.5L = 159.5, preceding cumulative frequency c.f.=60c.f. = 60, class frequency f=25f = 25, and class width c=20c = 20 into P75=L+(75c.f.f)×cP_{75} = L + \left(\frac{75 - c.f.}{f}\right) \times c gives 159.5+(1525)×20=171.5159.5 + \left(\frac{15}{25}\right) \times 20 = 171.5 hours.

Adım Adım Çözüm

1
Determine the rank position of the 75th percentile.
Rank position = 75th value out of 100.
The 75th percentile corresponds to 75% of the total frequency N = 100.
2
Identify the percentile class interval and extract relevant parameters.
Class interval is 159.5 - 179.5, with L = 159.5, c.f. = 60, f = 25, and c = 20.
The cumulative frequency increases from 60 to 85 across the boundary 159.5 to 179.5, which contains the 75th value.
3
Compute the percentile value using ogive linear interpolation.
P_75 = 159.5 + [(75 - 60) / 25] * 20 = 171.5 hours.
Applying the cumulative frequency interpolation formula yields the exact value.

Anahtar Kavram

Calculating Percentiles from Cumulative Frequency / Ogives
Soru 11Soru

The table below presents the cumulative frequency distribution of delay times (in minutes) for 5050 regional flights recorded at an airport:

Delay Time (minutes)Cumulative Frequency
101910 - 1988
202920 - 292020
303930 - 394040
404940 - 495050

What is the 70th70\text{th} percentile of the delay times?

Cevabı ve açıklamayı göster

Cevap: 37.037.0 minutes

Cevap

The 70th70\text{th} percentile of the delay times is 37.037.0 minutes.
The 70th70\text{th} percentile position is found by taking 70%70\% of 5050, which yields 3535. Looking at the cumulative frequency table, the 35th item falls in the 303930 - 39 interval (class boundaries 29.539.529.5 - 39.5). Applying the percentile interpolation formula: P70=29.5+(352020)×10=29.5+7.5=37.0 minutesP_{70} = 29.5 + \left(\frac{35 - 20}{20}\right) \times 10 = 29.5 + 7.5 = 37.0\text{ minutes}.

Adım Adım Çözüm

1
Determine the position of the 70th percentile rank.
Position rank =70100×50=35th value= \frac{70}{100} \times 50 = 35\text{th value}.
The 70th percentile corresponds to 70% of the total frequency N=50N = 50.
2
Identify the 70th percentile class interval and its parameters.
Interval: 303930 - 39; Lower class boundary L=29.5L = 29.5, cumulative frequency preceding class F=20F = 20, frequency of percentile class f=20f = 20, class width c=10c = 10.
The cumulative frequency reaches 20 at 29.529.5 and 40 at 39.539.5, so the 35th value lies in the 303930 - 39 class interval.
3
Apply the percentile interpolation formula P70=L+(70N100Ff)×cP_{70} = L + \left(\frac{\frac{70N}{100} - F}{f}\right) \times c.
P70=29.5+(352020)×10=29.5+(1520)×10=29.5+7.5=37.0 minutesP_{70} = 29.5 + \left(\frac{35 - 20}{20}\right) \times 10 = 29.5 + \left(\frac{15}{20}\right) \times 10 = 29.5 + 7.5 = 37.0\text{ minutes}.
Linear interpolation distributes the cumulative frequencies evenly across the class interval.

Anahtar Kavram

Calculating percentiles from grouped cumulative frequency data using class boundaries and linear interpolation.
Soru 12Soru

The cumulative frequency distribution below shows the monthly electricity consumption (in kWh) recorded for 5050 households in a residential estate:

Electricity Usage (kWh)Cumulative Frequency
50\leq 505
100\leq 10015
150\leq 15035
200\leq 20045
250\leq 25050

Using linear interpolation, calculate the 60th percentile (P60P_{60}) of electricity consumption in kWh.

Cevabı ve açıklamayı göster

Cevap: 137.5

Cevap

137.5 kWh
The 60th percentile corresponds to the 30th observation out of 50 (0.60×50=300.60 \times 50 = 30). From the cumulative frequency table, the 30th value falls in the class interval between 100100 and 150150. Using the lower boundary of 100100, previous cumulative frequency of 1515, interval frequency of 2020, and interval width of 5050, linear interpolation gives 100+301520×50=137.5100 + \frac{30 - 15}{20} \times 50 = 137.5 kWh.

Adım Adım Çözüm

1
Determine the rank for the 60th percentile
Rank position = 30th household
The 60th percentile rank corresponds to 60%60\% of the total sample size (N=50N = 50), which is 0.60×50=300.60 \times 50 = 30.
2
Identify the parameters of the percentile class interval
Lower boundary L=100L = 100, CFprev=15CF_{\text{prev}} = 15, class frequency f=20f = 20, width w=50w = 50
The cumulative frequency rises from 15 to 35 in the class interval (100,150](100, 150], so the 30th value lies within this interval.
3
Calculate the value using linear interpolation
137.5 kWh
Substitute values into P60=100+(301520)×50=100+37.5=137.5P_{60} = 100 + \left(\frac{30 - 15}{20}\right) \times 50 = 100 + 37.5 = 137.5 kWh.

Anahtar Kavram

Linear interpolation for percentiles from a cumulative frequency distribution
Soru 13Soru

The cumulative frequency distribution table below shows the mass of cocoa beans (in kg) harvested by 4040 smallholder farmers in a agricultural cooperative:

Mass (kg)Cumulative Frequency
20\leq 2044
30\leq 301212
40\leq 402828
50\leq 503636
60\leq 604040

Using linear interpolation from the cumulative frequency table, what is the median mass (in kg) of cocoa beans harvested by the farmers?

Cevabı ve açıklamayı göster

Cevap: 35

Cevap

The median mass of cocoa beans harvested by the farmers is 35.0 kg35.0\text{ kg}.
The total number of farmers is N=40N = 40. The median corresponds to the 402=20th\frac{40}{2} = 20^{\text{th}} position. From the cumulative frequency table, the 20th20^{\text{th}} item lies within the 3040 kg30 - 40\text{ kg} class interval. Using the grouped median formula Median=L+(N2c.f.f)×w\text{Median} = L + \left(\frac{\frac{N}{2} - c.f.}{f}\right) \times w, where L=30L = 30, c.f.=12c.f. = 12, f=2812=16f = 28 - 12 = 16, and w=10w = 10, we obtain Median=30+(201216)×10=35.0 kg\text{Median} = 30 + \left(\frac{20 - 12}{16}\right) \times 10 = 35.0\text{ kg}.

Adım Adım Çözüm

1
Find the median position in the cumulative frequency distribution
Median position =N2=402=20th= \frac{N}{2} = \frac{40}{2} = 20^{\text{th}} item
The median corresponds to the 50th percentile, which is half of the total cumulative frequency N=40N = 40.
2
Locate the median class interval and extract its statistical parameters
Median class interval is 3040 kg30 - 40\text{ kg}, with lower limit L=30 kgL = 30\text{ kg}, preceding cumulative frequency c.f.=12c.f. = 12, class frequency f=2812=16f = 28 - 12 = 16, and width w=10 kgw = 10\text{ kg}
The cumulative frequency just below 2020 is 1212 (at upper boundary 3030), and at upper boundary 4040 it rises to 2828.
3
Substitute values into the grouped data median formula
\text{Median} = 30 + \left(\frac{20 - 12}{16}\right) \times 10 = 30 + 5 = 35.0\text{ kg}
Linear interpolation estimates the exact position of the median within the median class interval.

Anahtar Kavram

Calculation of Median from Cumulative Frequency Data
Soru 14Soru

The table below shows the distribution of examination scores of 5050 candidates in a selection test:

Score ClassFrequency (ff)
101910 - 1955
202920 - 2999
303930 - 391616
404940 - 491414
505950 - 5966

Using the cumulative frequency distribution (ogive), what is the estimated 70th70^{\text{th}} percentile score?

Cevabı ve açıklamayı göster

Cevap: 43.143.1

Cevap

The estimated 70th70^{\text{th}} percentile score is 43.143.1.
The 70th70^{\text{th}} percentile corresponds to the score at the 35th35^{\text{th}} candidate (70%70\% of 5050). This falls within the 404940 - 49 score class, which has a lower boundary of 39.539.5, a frequency of 1414, and a class width of 1010. Interpolating linearly gives 39.5+(353014)×10=43.0743.139.5 + \left(\frac{35 - 30}{14}\right) \times 10 = 43.07 \approx 43.1.

Adım Adım Çözüm

1
Construct the cumulative frequency table to find class boundaries and cumulative frequencies.
Cumulative frequencies: 101910-19 (CF=5CF = 5), 202920-29 (CF=14CF = 14), 303930-39 (CF=30CF = 30), 404940-49 (CF=44CF = 44), 505950-59 (CF=50CF = 50).
Cumulative frequencies are required to locate the position of the desired percentile.
2
Determine the rank position of the 70th70^{\text{th}} percentile (P70P_{70}).
Rank position = 70100×50=35th\frac{70}{100} \times 50 = 35^{\text{th}} position.
The 70th70^{\text{th}} percentile corresponds to the score below which 70%70\% of the total candidates fall.
3
Identify the class interval containing the 35th35^{\text{th}} cumulative frequency and state its parameters.
The target class is 404940 - 49. Parameters: Lower class boundary L=39.5L = 39.5, preceding cumulative frequency CFprev=30CF_{\text{prev}} = 30, class frequency f=14f = 14, class width c=10c = 10.
Since 30<354430 < 35 \le 44, the 35th35^{\text{th}} entry falls within the 404940 - 49 class.
4
Apply the linear interpolation formula for percentiles from an ogive.
P70=L+(70N100CFprevf)×c=39.5+(353014)×10=39.5+501443.0743.1P_{70} = L + \left(\frac{\frac{70N}{100} - CF_{\text{prev}}}{f}\right) \times c = 39.5 + \left(\frac{35 - 30}{14}\right) \times 10 = 39.5 + \frac{50}{14} \approx 43.07 \approx 43.1.
This calculates the exact score estimate on the cumulative frequency curve.

Anahtar Kavram

Estimating Percentiles from Grouped Data and Ogives