For some, statistical terminology can create angst and anxiety for those who are not statistics students but must translate research findings into something that others will understand. Frankly, no one really cares what the “mean” or “median” numbers are; what they care about is what the “mean” and “median” can tell us. For example, at UtilityPULSE, we learned a very long time ago that Customers don’t care that the number of outages they have is consistent with the mean (average) of the utility. What they care about is “there are too many outages that disrupt life.” This could tell us that the mean is too high. Here, we explain some key statistical terms and demonstrate how they can be used to identify trends and insights and ensure the overall quality of the research.

1. Mean (Average)

Definition: The mean is calculated by adding all the numbers in a dataset and dividing by the count of those numbers. It represents the central point of the data.

Use in Insights and Quality: The mean is useful for identifying the overall trend in data and provides a quick snapshot of where things stand on average. However, it can be influenced by extreme values (outliers), especially with a small number of respondents, which may skew perceptions if not considered carefully.

2. Median

Definition: The median is the middle value in a data set when organized in ascending order. If there is an even number of observations, the median is the average of the two middle numbers. For example, in a listing of numbers from 1 to 100, the median is 50.5, where ½ the numbers are above and ½ are below.

Use in Insights and Quality: The median is less affected by outliers and skewed data than the mean. This makes it more reliable in understanding the typical outcome when data is unevenly distributed, sometimes providing a clearer picture of the central tendency of the respondent group.

3. Standard Deviation (SD)

Definition: Standard deviation measures the amount of variation or dispersion in a set of values. A low standard deviation indicates that the values are close to the mean, while a high standard deviation indicates that the values are spread out over a wider range.

Use in Insights and Quality: Understanding standard deviation helps assess the spread of data, which can indicate the consistency of the responses. A small SD tells us there is small variability in Customer perceptions and behaviours. 

4. Top 2 Boxes and Bottom 2 Boxes

Definition: In survey research, “top 2 boxes” typically refers to the highest two ratings on a scale (e.g., “very satisfied” and “satisfied”) and “bottom 2 boxes” to the lowest two (e.g., “dissatisfied” and “very dissatisfied”).

Use in Insights and Quality: These metrics are often used to quickly gauge overall satisfaction or dissatisfaction levels, providing a snapshot of Customer sentiment. They simplify data analysis by focusing on the extremes of response scales.

5. Margin of Error (MOE)

Definition: The margin of error reflects the range within which the true value of the population is expected to fall. It is often expressed as a percentage and indicates confidence in the results.

Use in Insights and Quality: MOE is critical for understanding the precision of survey results. A small margin of error means higher confidence in the reliability of the data, which is essential when making decisions based on survey results.

6. Standard Error (SE)

Definition: Standard error measures the accuracy with which a sample represents a population. It is derived from the standard deviation and the sample size.

Use in Insights and Quality: SE helps determine how precise an estimate from the sample is likely to be in relation to the overall population. Lower standard error suggests a more accurate representation of the population.

7. Completion Rate

Definition: Completion rate is the percentage of respondents who completed the survey out of those who started it.

Use in Insights and Quality: High completion rates often indicate that the survey was engaging and well-designed, leading to reliable and comprehensive data collection. It also suggests that the results are representative of the target audience. It could also mean that the surveyed topic has emotional meaning to respondents.

8. Drop-offs

Definition: Drop-offs refer to respondents who start a survey but do not complete it.

Use in Insights and Quality: Monitoring drop-offs can provide insights into where respondents lose interest or encounter difficulties, which is crucial for improving survey design and ensuring data quality.

At UtilityPULSE, we’re committed to ensuring that survey or project questions are easy to understand with rating scales that make sense. We know that utility clients appreciate context with the numbers coupled with our experience in extracting information, insights, and feedback they can use to help their utility be more successful.

Research isn’t about the numbers, so to speak. It is about the story in the numbers AND the open dialogue that utility professionals have about the research findings.

Let’s Connect to discuss your research needs.