|
Program and Project Evaluation
Introduction to Evaluation
Planning the Evaluation
Collecting Information
Analyzing and Interpreting
Reporting |
Home >>
Program and Project Evaluation •Analyzing and Interpreting
Data analysis and interpretation is the process of assigning
meaning to the collected information and determining the conclusions, significance, and
implications of the findings. The steps involved in data analysis are a function of the type
of information collected, however, returning to the purpose of the evaluation and the
evaluation questions will provide a structure for the organization of the data and a focus
for the analysis.
The analysis of Numerical (Quantitative) Data
is represented in mathematical terms. The most common statistical terms include:
- Mean – The mean score represents a numerical average for a set of
responses.
- Standard deviation – The standard deviation represents the distribution
of the responses around the mean. It indicates the degree of consistency among the responses. The
standard deviation, in conjunction with the mean, provides a better understanding of the data. For
example, if the mean is 3.3 with a standard deviation (StD) of 0.4, then two-thirds of the
responses lie between 2.9 (3.3 – 0.4) and 3.7 (3.3 + 0.4).
- Frequency distribution – Frequency distribution indicates the frequency
of each response. For example, if respondents answer a question using an agree/disagree scale, the
percentage of respondents who selected each response on the scale would be indicated. The
frequency distribution provides additional information beyond the mean, since it allows for
examining the level of consensus among the data.
Higher levels of statistical analysis (e.g., t-test, factor analysis,
regression, ANOVA) can be conducted on the data, but these are not used in most program evaluations.
The analysis of Narrative (Qualitative) Data
is conducted by organizing the data into common themes or categories. It is often more difficult to
interpret narrative data because it lacks the built-in structure found in numerical data. Initially,
the narrative data appears to be a collection of random, unconnected statements. The evaluation
purpose and questions can help direct the focus of the data organization. The following strategies
may also be helpful when analyzing narrative data:
Focus Groups and Interviews:
- Read and organize the data from each question separately. This approach
permits focusing on one question at a time (e.g., experiences with tutoring services,
characteristics of tutor, student responsibility in the tutoring process).
- Group the comments by themes, topics, or categories. This approach
allows for focusing on one area at a time (e.g., characteristics of tutor – level of preparation,
knowledge of content area, availability).
Documents
- Code content and characteristics of documents into various categories
(e.g., training manual – policies and procedures, communication, responsibilities).
Observations
- Code patterns from the focus of the observation (e.g., behavioral
patterns – amount of time engaged/not engaged in activity, type of engagement, communication,
interpersonal skills).
The analysis of the data via statistical measures and/or narrative themes
should provide answers to the evaluation questions. Interpreting the analyzed data from the
appropriate perspective allows for determination of the significance and implications of the
evaluation.
|
.GIF)
