SPSS Statistics: Data Analysis Education

SPSS Statistics: Data Analysis Education The average number (mean) of years that participants attended school was 13.0, with data ranging from 0 years to 20 years. The median was 12 years and the mode (most frequent response) was also 12. Looking at the histogram for the education variable we can see that the distribution is relatively normal, but in this case it may still be more accurate to use the median as the representation of central tendency.

Outliers do not impact the median, and in a variable like education there can be quite a few outliers. Also, given that the median and the mode are the same, these numbers may be a better representation of the entire sample. Having said this, there is not an overwhelming difference between the mean, median and mode in this sample, given the relatively normal distribution. Hours Worked Last Week On average, participants in this sample worked 41.76 hours in the past week, with responses ranging from 2 hours to 89 hours.

The standard deviation was also quite high, 14.63, and thus there was quite a bit of variability in the responses provided on this variable. The media and mode were both the same, indicating that the majority of respondents worked 40 hours in the past week. Once again, because all three measures of central tendency are similar, any one would provide a relatively accurate representation of the sample.

It may still be best to represent this variable using the mode, given that the vast majority of the sample reported working 40 hours, with smaller numbers of participants endorsing all other responses. Over 250 respondents reported working 40 hours, with the next highest frequency being under 100. Number of Siblings The histogram for the number of siblings shows a negatively skewed data set, with more participants reporting fewer siblings. However, the range in this variable was quite high, ranging from 0 to 22 siblings.

The mean response was 3.71 siblings, the median response was 3 siblings and the mode of the sample was 2, indicating that the most frequent response was 2 siblings. In this case the mode would likely be a good representation of this sample, as it represents the majority. The mean could also be used as a way of representing the number of participants who did have more than 2 participants, but outliers, such as the individuals.