Skip global navigation
St. Cloud State University

St. Cloud State University

Cultural Audit: Final Report Nichols and Associates, Inc.
Washington, D.C.
October 2002

Survey Analysis

Keys to Interpretation. All questionnaire items were measured on a five- or seven-point Likert-type scales (i.e., "strongly agree," "agree," "uncertain," "disagree," and "strongly disagree"; "very satisfied," "satisfied," "uncertain," "dissatisfied," and "very dissatisfied"; "very characteristic," "characteristic," "moderately characteristic," "slightly characteristic," and "not characteristic"; "excellent" to "poor").

Demographic findings indicated majority staff respondents outnumbered minority staff respondents by a ratio of nearly four to one; males and females were equally represented. Therefore, the overall responses are significantly heavily weighed to the majority perspective.

Moreover, disparity in subgroup perceptions indicated potential for organizational conflict. Some comparisons were found to be statistically significant. Percentages may not total 100% due to rounding procedures. For the purposes of the analysis, calculated percentages of .5 or higher were rounded up to the next whole number.

Demographic and Level I analysis is driven by a frequency distribution (i.e., percentages, descriptive statistics) for each survey item across students and administrators, faculty and staff respondents2. Level II analysis includes t-tests and univariate analyses. Responses to the open-ended item will be included in section entitled Qualitative Analysis.

Due to incomplete surveys, missing value analysis was conducted using regression residuals for all scale items except those assessing demographic characteristics. Using SPSS, values for missing data were imputed.

Scale scores were calculated by adding all response item scores and resulted in a composite score. Survey items that were negatively worded were reversed scored. Thus, the lower the scale score, the better the score or the more favorable the perception. The total scale score and the range of responses were contingent on number of scale items and type of response scale (i.e., five- or seven-point Likert-type scales).

Qualitative data (i.e., focus group data and written comments) were collected and analyzed in an effort to enhance and validate survey findings and to understand SCSU members' perspectives and perceptions. It also increased the contextual perspective of the Nichols and Associates, Inc., team in reporting accurate findings and submitting appropriate recommendations. A thematic content analysis was conducted and used in the cultural assessment to:

  • Identify the intentions, focus or communication trends of individuals, groups or the organization (SCSU).
  • Determine attitudinal and behavioral responses to organizational communications, policies and procedures.
  • Determine psychological/emotional state and opinions of persons or groups. (See section entitled Qualitative Analysis).

Analyzing the data in this manner provides an additional perspective of SCSU issues and assists in developing an approach to resolve issues.

2 Note: The mean understates (overstates) the true value of the central tendency if there is a minimum (or maximum) value outlier. Despite this only flaw, the sample mean ( X or x-bar) has some particular properties that make it the most reliable/popular estimator for making inferences about the population mean
µ or central tendency. These properties include:
1. Unbiasedness - Its expected value is equal to the true value of the parameter µ (which is always unknown)
2. Relative Efficiency - Is variance is the smallest when compared with the variances of the competing summary measures (e.g., the median) of central tendency or µ
3. Consistency - Its value approaches the true value of µ (which is always unknown) as the sample size 'n' increases.
4. Sufficiency - It must use all of the information contained in a sample of data that is used in the computation of its value.

<< Previous Table of Contents Next >>