Staff Satisfaction Survey

No matter what kind of survey questionnaire you're working on, whether it's an employee satisfaction survey, product market research, a customer service questionnaire, a job performance review template or a customer satisfaction survey, having some basic knowledge of statistics and related terms is helpful.

If you're using survey analysis tools, chances are all the statistical calculations will be done for you, you only need to select the survey analysis methods. It's still important to know what the terms mean that are describing the data. Here's a quick "crash course" in basic statistics and what the terms mean:

Mean: Typically "mean" is used as a synonym for "average." While this is not exactly accurate, it's good enough for a high level understanding. To get the population mean, or the expected value of a random variable, take the sum of the results and divide it by the number of results.

Median: Separates the top half from the bottom half of the sample. The median is the exact middle number of your responses. To figure out the median, you order the finite list of responses from the lowest value to the highest value and select the middle value. If there is not a unique middle value, take the mean on either side of where the median would be (ie. in the list a < b < c < d the median would be the mean of b and c). The reason you would use the median over the mean is if there are outliers in the population that don't matter. Outliers will skew your mean in the direction of the outlier. However, using the median prevents the average from being skewed.

Mode: The mode is the response or variable in a data set that occurs most frequently (i.e. in the list a, a, b, a, b, c, c, d the mode would be a because it occurs the most). While the mean and median might be very similar for a data set, the mode may be very different depending on the data set's distribution.

Variance: Describes how spread out the distribution of a data set is.

Standard Deviation: Describes the probability of the data set's distribution. A low standard deviation means the the data points tend to be close to, or the same as, the mean. A high standard deviation indicates the data is spread out.