Results 1 to 4 of 4

Thread: [Biostatistics] Measures of Location

  1. #1

    Default [Biostatistics] Measures of Location

    With ordinal and metric data, we can provide a summary measure of location. This is a value around which most of the data seem to congregate or centre.

    In descriptive statistics, we use three main measures of location: the mode, the median, and the mean. The choice of the most appropriate measure depends crucially on the type of data involved.

    The Mode

    The mode, or modal value, is the value in the data with the highest frequency (i.e., occurs the most often). When the data are grouped, the group with the highest number (the highest frequency) is the modal category.

    However, as a descriptive measure, the mode has a few shortcomings:

    • There may be more than one mode.
    • It is not useful with metric continuous data, where no two values may be the same. It is much easier though, to find the modal category from grouped data.
    • The mode is not useful with discrete metric data, when the number of values is large.


    PS: Types of Data (nominal, ordinal, and metric) - http://www.tomhsiung.com/wordpress/2...types-of-data/
    Last edited by admin; Tue 15th March '16 at 9:02pm.
    Clinical Pharmacy Specialist - Infectious Diseases

  2. #2

    Default

    The Median

    If we arrange the data in ascending order of size, the median is the middle value. Thus, half of the values will be equal to or less than the median value and half equal to or greater than it. The median is therefore a measure of central-ness.

    Some properties of the median:

    • It discards a lot of information because it ignores most of the values, apart from those in the centre of the distribution.
    • It is not much affected by skewness in the distribution, or by outliers, and is therefore a stable measure.
    • It is not easy to determine (by hand) unless the sample has been ordered first.
    Clinical Pharmacy Specialist - Infectious Diseases

  3. #3

    Default

    The Mean

    The mean, or the arithmetic mean to give it its full name, is more commonly known as the average. So to determine the value of the mean, we add values together and divide this total by the number of values.

    A few things about the mean:

    • It uses all of the information in the data set - every value is included.
    • Because of this, it is affected by skewness in the distribution and by outliers.
    • As a consequence, the mean, on occasion, might be unrepresentative of the general mass of the data.
    • It cannot be used with ordinal data.
    Clinical Pharmacy Specialist - Infectious Diseases

  4. #4
    PharmD Year 1 TomHsiung's Avatar
    Join Date
    Jan 2013
    Location
    Chengdu, Sichuan, China
    Posts
    593

    Default The most appropriate measure of location

    • The mean cannot be used with ordinal data (because they are not real numbers)
    • The median can be used for both ordinal data and metric data (particularly when the latter is skewed).
    B.S. Pharm, West China School of Pharmacy, Class of 2007, Health System Pharmacist, RPh. Hematology, Infectious Disease.

Posting Permissions

  • You may not post new threads
  • You may not post replies
  • You may not post attachments
  • You may not edit your posts
  •