Career assessment glossary
Questionnaires generally include a number of dimensions, for example extraversion or conscientiousness. Each one of the questions/items chosen can be attributed to one of these dimensions. Questions/items with related content are grouped under the same dimension.
In some of the questionnaires, the dimensions are sub-divided into further categories. For example, in the HEXACO-PI-R personality inventory, the extraversion dimension contains the sub-categories: social self-esteem, social boldness, sociability and liveliness.
Your score / mean score based on your answers
Your score is based on the mean score of your answers attributed to a specific dimension. However, questionnaires are invariably subject to measurement errors. These can, for example, result from the "misunderstanding" of a question. The confidence interval is designed to compensate for the resulting inaccuracy of the score (see below).
All scores presented on the Laufbahndiagnostik platform (dimensions, facets/sub-categories) are average (arithmetic mean) scores.
Mean scores are calculated by adding up the answers to the individual questions/items. First, a number is assigned to each possible answer (e.g. 0 for Yes and 1 for No), and then these numbers are added up. The total value is then divided by the respective number of questions/items. The mean score therefore shows the average «yes» strength of an individual’s answers to the questions/items.
The confidence interval shows that the questionnaire in use is subject to measurement errors (e.g. because a question is “misunderstood”). The confidence interval is indicated individually for each dimension or facet/sub-category. It indicates the range in which an individual’s mean score may vary. When calculating the confidence interval, the following parameters are included:
- Mean score and standard deviation in dimension or facet/sub-category. The scores are determined based on a sample collected on the Laufbahndiagnostik platform (see below).
- Measurement accuracy (reliability) of a dimension or facet/sub-category. The scores are calculated based on the sample collected on the Laufbahndiagnostik platform.
- Confidence level: All confidence intervals on the Laufbahndiagnostik platform have a confidence level of 95%. This means that the score obtained would lie within the indicated interval in 95 of 100 cases. Wide intervals suggest that the dimension or facet/sub-category is likely to be measured imprecisely. Narrow confidence intervals indicate that the dimension or facet/sub-category is measured precisely.
Mean score and standard deviation in dimension or facet/sub-category
Consultants who have an account with us (fee-based) are able to display mean scores and standard deviations of the total number of samples on the Laufbahndiagnostik platform. The total number of samples includes all those who have already filled in the corresponding questionnaire on the platform.
The mean score of a dimension or facet/sub-category is determined based on the sample collected on the Laufbahndiagnostik platform.
The mean score is the sum of the scores of all participants in a sample divided by the number of participants in the sample. The mean score shows the participants' average score.
The standard deviation of a dimension or facet/sub-category is determined based on the sample collected on the Laufbahndiagnostik platform. It is calculated by adding up every participant's squared difference from the mean score. The sum is divided by the number of participants in the sample and then the square root is extracted from the resulting figure. The standard deviation indicates the extent to which an individual participant's answers are scattered around the mean score.
The Laufbahndiagnostik platform provides all data necessary for the calculation of standard values. Standard values (of a so-called norm-referenced assessment) are used to compare a participant's scores with those of other participants.
Here you can find information related to normalisation in German: Laufbahndiagnostik platform - Statistical principles.
Here You can find a sample calculation of a normalisation in German.