|
MEASURES OF LOCATION
In a set of data:
MODE = THE MOST FREQUENTLY OBSERVED VALUE
A set of data can have more than one mode. The mode does not necessarily give much indication of a data set’s centre. However, it is often close to the mean and median, and will be so if the data has a normal or near normal distribution.
NOMINAL OR DISCRETE VARIABLES
For nominal or discrete variables, the mode is simply the most observed value. To work out the mode, observations do not have to be placed in order, although for ease of calculation it is advisable to do so.
EXAMPLE
1. | From Tony Modra’s goal kicking figures: 7, 5, 0, 7, 8, 5, 5, 4, 5, and 1 goals in 10 matches, find the mode. The mode is 5, because this value occurred the most often (4 times). This can be interpreted to mean that if one match was selected at random, a good guess would be that Tony would kick 5 goals. |
2. | In 12 matches a netball player scored 14, 14, 15, 16, 14, 16, 16, 18, 14, 16, 16, and 14 goals. What is the mode? In this case there are two modes, 14 and 16, because both of them occur the most often (5 times). |
3. | In the following data set represents the number of home runs scored by softball player in 14 matches. Find and compare the mean, median and mode. |
| In order:
0, 0, 1, 0, 0, 2, 3, 1, 0, 1, 2, 3, 1, 0
0, 0, 0, 0, 0, 0, 1, 1, 1, 1, 2, 2, 3, 3 |
The mode is 0, as this value occurs most often. If one match was selected at random, the mode tells us that a good guess would be that the player would not score a home run.
Therefore, it can be said that on average (mean), the player will score one home run per match; even though the mode indicates he or she doesn’t score a home run in a lot of matches. So, in this case, the mode does not provide a useful measure of the data’s centre.
GROUPED VARIABLES (CONTINUOUS OR DISCRETE)
When continuous or discrete variables are grouped in tables, the mode is defined as the class interval where most observations lie. This is called themodal-class interval.
In the example of heights of 50 Year 10 girls, the modal-class interval would be 160-<165cm, as this interval has the most observations in it.
NOTE:
For numeric variables the mode is not often used as a measure of central tendency. However, for nominal variables the mode is useful as the mean and median do not make sense
EXERCISES
1. | | For the following sets of data find the: |
| i) | Mean |
| ii) | Median |
| iii) | Mode |
| | a) 0, 0, 0, 0, 1, 0, 0, 0, 0, 0, 0 (to 1 decimal place) |
| | b) 2, 1, 2, 3, 1, 3, 0, 2, 4, 2, 2 |
| | c) 2.4, 3.9, 1.8, 1.7, 4.0, 2.1, 3.9, 1.5, 3.9, 2.6 |
| | d) 153.8, 154.7, 156.9, 154.3, 152.3, 156.1, 152.3 |
| | |
2. | | For the following sets of data find the: |
| i) | Mean |
| i) | Median |
| iii) | Mode |
| iv) | Describe briefly the relative positions of the mean, median and mode of each data set. |
3. | | For each of the following stem and leaf tables find the: |
| i) | Mean |
| ii) | Modal-class interval |
4. | The population increase in Queensland during 1986 to 1995 is given in the table below: |
| Year | Increase | |
|
| |
| 1986 | 53,377 | |
| 1987 | 52,170 | |
| 1988 | 67,000 | |
| 1989 | 90,332 | |
| 1990 | 72,681 | |
| 1991 | 65,226 | |
| 1992 | 76,777 | |
| 1993 | 83,657 | |
| 1994 | 77,753 | |
| 1995 | 82,892 | |
| a) | Calculate the mean population increase for the years 1986-95. |
| b) | Calculate the median population increase for the years 1986-95. |
| c) | Do you think the difference in these two measures is significant? Give reasons for your answer, and explain which result gives a better indication of the data’s centre. |
| d) | For what purposes would the Queensland Government use measures such as these? |
| | |
5. | | The marks out of 10 for forty students who attempted a maths test were recorded as follows: |
| | 9, 10, 7, 8, 9, 6, 5, 9, 4, 7, 1, 7, 2, 7, 8, 5, 4, 3, 10, 7, 3, 7, 8, 6, 9, 7, 4, 2, 3, 9, 4, 3, 7, 5, 5, 2, 7, 9, 7, 1 |
| a) | Prepare a frequency table of the scores. |
| b) | Using the table, calculate the mean, median and mode. |
| c) | How would you interpret these results? |
| | |
6. | | The number of people unemployed at the time of the 1996 Census in Tasmania is given in the table below |
| Age group | Number unemployed | |
|
| |
| 15-19 | 3,688 | |
| 20-24 | 4,031 |
|
| 25-34 | 5,432 | |
| 35-44 | 4,360 | |
| 45-54 | 3,162 | |
| 55-64 | 1,702 | |
| a) | Copy the table and by first finding the mid-point of each interval, calculate the average age of an unemployed person in Tasmania. |
| b) | What is the modal-class interval? |
| c) | In what age group does the median lie? |
| d) | Briefly discuss the comparison between these three results. |
| e) | Why do you think the number of unemployed decreases after the age group 25-34? |
| f) | How might social welfare organisations use these figures? |
| | |
7. | | A random analysis of 100 married men gave the following distribution of hours spent per week doing unpaid household work. |
| Hours | Number of men | |
|
| |
| 0 - <5 | 1 | |
| 5 - <10 | 18 |
|
| 0 - <15 | 24 | |
| 15 - <20 | 25 | |
| 20 - <25 | 18 | |
| 25 - <30 | 12 | |
| 30 - <35 | 1 | |
| 35 - <40 | 1 | |
| | a) Copy the table and include columns to find the end-point of each interval, calculate cumulative frequency and cumulative percentages. |
| | b) Draw the ogive with cumulative frequency as the y-axis. |
| | c) From the curve, find an approximate median value. What does this value indicate? |
| | d) What is the modal-class interval? |
| | e) Calculate the mean. What does this value indicate? |
| | f) Briefly describe the comparison between mean, median and mode values. |
| | g) How might you find out whether women spent more hours per week than men doing unpaid household work? |
| | |
8. | | The 1996 Census table below shows annual income of people aged 15 years or more in Western Australia. |
| Income ($) | Persons | |
|
| |
| 0 - 2,079 | 114,195 |
|
| 2,080 - 4,159 | 44,817 | |
| 4,160 - 6,239 | 45,862 | |
| 6,240 - 8,319 | 139,611 | |
| 8,320 - 10,399 | 114,192 |
|
| 10,400 - 15,599 | 148,276 | |
| 15,600 - 20,799 | 123,638 | |
| 20,800 - 25,999 | 121,623 |
|
| 26,000 - 31,199 | 103,402 | |
| 31,200 - 36,399 | 73,463 | |
| 36,400 - 41,599 | 59,126 | |
| 41,600 - 51,999 | 68,747 | |
| 52,000 - 77,999 | 56,710 | |
| | a) What is the modal-class interval? |
| | b) Copy the table into your books and include columns to find the upper end-point of each interval, calculate cumulative frequencies and cumulative percentages. |
| | c) Draw the ogive. |
| | d) From the curve, give an approximate value for the median annual individual income. |
| | e) Calculate the mean annual income. (Hint: in the above table, the interval 2,080 - 4,159 actually represents 2,080 - <4,160, so the mid-point is 3,120.) |
| | f) Describe the comparison of mean, median and mode values. |
| | g) Which measure gives the most accurate picture of the data’s centre? |
| | h) What type of organisation would use information such as this? |
Click here for answers
CLASS ACTIVITIES
1. | Measure the height of each student in your class to the nearest centimetre. Are there any outliers? Use an appropriate method to find the mean, median and mode. Compare all three measures. Which value gives the best measure of central location and why? Which organisations or companies would find such statistics useful? |
2. | Find out what your school’s student population or your year level’s population has been for the last 10 years. Are there any outliers? Use an appropriate method to find the mean, median and mode. Compare all three measures. Which value gives the best measure of central location and why? How would your school or the Education Department use such statistics? |
3. | Find from your school’s records the final scores of your favourite school sport. Collect the scores, both for and against, for the last ten years. (If the data is not available, use data for your favourite sporting team.) |
| What was the mean final score, both for and against, for the last ten years? |
| What was the median final score, both for and against, for the last ten years? |
| Are any of the mean final scores similar to the corresponding median final score? |
| What can be said about the distributions given these values? |
| What are some of the problems you might come across in trying to use statistics to compare school or other sports teams of the past with those of today? |
For ordinal data, can you think of occasions where the mode would be of more use than the median or mean? Discuss as a class.
|
|