Statistics made simple. Part 1. Mean, medians and modes.

Linda Shields PhD, FRCNA, Professor of Nursing, University of Limerick, Ireland This is one of a series of short papers on aspects of research by Alison Twycross and Linda Shields You’ve found a piece of research that you think may be relevant to your practice but it is full of statistics and you can make neither head nor tail of them. Why do researchers bother doing statistical tests? What on earth do these statistical tests mean? We constantly use statistics in everyday life. I may, for example, state that Oxford United Football Club will probably be promoted this season. At work I may say that it takes about 30 minutes to admit a child to the ward. However, neither of these examples are particularly precise. The use of statistics allows us to make precise statements. Statistical tests can be divided into two groups: descriptive statistics and inferential statistics. Descriptive statistics, as the name suggests, are used to describe numerical data. Inferential statistics are used to make inferences, that is draw conclusions, about the data collected. This paper will describe descriptive statistics commonly used in nursing research. Descriptive statistics are used to help explain the results of a piece of quantitative research. Descriptive statistics summarise certain aspects of the results and can be divided into measures of central tendency which relate to the most typical value, and measures that give a measure of dispersion that is the variability or spread of the results. Descriptive statistical tests are often used when data are collected using a questionnaire and provide a picture of the issue being studied (Hicks 1996). This paper will concentrate on statistical tests for measuring the central tendency of data. The most commonly used measures of central tendency are the mean, median and mode. The mean is what is most commonly referred to as the average. Three steps are required to calculate a mean score: 1 Count the total number of cases – in statistical terms this is referred to as ‘n’ 2 Add up all the scores 3 Divide this total by the number of cases. For example, you may have collected data relating to the peak flow readings of ten children and want to find out the mean peak flow for these children. Number of cases (n) = 9 Peak flow readings = 220, 250, 220, 260, 270, 220, 280, 320, 250 Total (adding all the above peak flow readings together) = 2290