Parameter, sample statistic, and frequency distribution

CFA level I / Quantitative Methods: Basic Concepts / Statistical Concepts and Market Returns / Parameter, sample statistic, and frequency distribution

We have already defined the parameter and a sample statistic. Any measurement of a population is called a parameter whereas any measurement of a sample is called a sample statistic.

A frequency distribution is a tabular display of data summarized into a relatively small number of intervals.

For constructing a frequency distribution, the data is first sorted in ascending order. Then the range of the data is computed. Then the number of intervals in the frequency distribution is decided. Then the interval width is calculated which equals the range divided by the number of intervals. Then the intervals are formed starting from the minimum value, and we will keep on adding the interval width till we reach the maximum value of the data. The actual number of observation in a given interval is called the absolute frequency. The absolute frequency of each interval is calculated to get the frequency distribution.

Example 1: Constructing a frequency distribution

The returns earned by 15 mutual funds in the last year are 12 percent, 8 percent, -10 percent, 4 percent, 11 percent, -4 percent, 9 percent, 0 percent, -2 percent, -5 percent, 6 percent, 7 percent, 14 percent, 18 percent, and -12 percent. Construct a frequency distribution for this data.

Solution:

First arranging the returns in ascending order (all returns are in percentage): -12, -10, -5, -4, -2, 0, 4, 6, 7, 8, 9, 11, 12, 14, 18

Then calculating the range of data, Range = Maximum value - Minimum value = 18 - (-12) = 30.

Now, decide the total number of intervals in the frequency distribution. Let's choose it as 6.

So, the interval width will be equal to the range divided by the total number of intervals. Interval width = 30/6 = 5.

The intervals will be such so that it starts with the minimum value and then adding the interval width to each interval and finally ending with the maximum value.

Then we need to count the number of observations that fall in each interval, and that will be the frequency of that interval.

Interval

Observations

Frequency

-12≤x<-7

-12, -10

2

-7≤x<-2

-5, -4

2

-2≤x<3

-2, 0

2

3≤x<8

4, 6, 7

3

8≤x<13

8, 9, 11, 12

4

13≤x≤18

14, 18

2


Note that the intervals are defined in such a manner so that any observation doesn't fall in more than one interval.



Previous LOS: Descriptive statistics,Inferential statistics, and types of scales

Next LOS: Relative frequencies and cumulative relative frequencies

    CFA Institute does not endorse, promote or warrant the accuracy or quality of products and services offered by Konvexity. CFA® and Chartered Financial Analyst® are registered trademarks owned by CFA Institute.