Measures of Central Tendency
The measures are applied in cases where the researcher wants to indicate the centralized positioning of a range of values. The tools used in measuring the central tendency are basically summarized statistics that tend to point out to the central location of the values. The different measures that can be used to indicate the centralized value are mean, median and mode. Important to note is that the different measures are appropriate for different kinds of measures and scales.
Mode refers to the most frequent or popular score in a data set. A researcher in using mode would be focused on identifying the most common score within the data collected. For instance, when the researcher is conducting a research on the preference of work schedule, respondents may choose different times and mode would easily be used to identify the most common work schedule. Mode is most appropriate use on a nominal scale.
Mean is the most popular of the measures of central tendencies. It is basically an average of the values. In applying the mean in conducting research, the researcher will need to be clear whether they are trying to find mean of the population or the sample. This is due to the implication that comes from use of one and not the other. In measuring the population mean, the formula is denoted as; while for the mean of the sample, the formula can be denoted as; x̄ = . Mean can be used in quantitative data analysis when the scale is either interval or ratio. A weakness in the use of mean for summary statistics is that it is affected when the data points are either skewed or contain an outlier.
Median refers to the middle value in a data set that is arranged in an ascending order. A researcher would choose to use median when the data is skewed or has an outlier as median is able to handle such a data set well. When analyzing data that is on an ordinal scale, median as a summary statistics is most appropriate.
Haron Tinega is an Lead Consultant at SD-Cubed Analytics. Haron specializes in data analytics, machine learning, and advanced technologies. He excels in dismantling data barriers to uncover hidden business opportunities and risks, ultimately enabling smart, competitive decision-making.
