Spectrum Health Value StudyTM Methodology

Beginning in January 2009, every three months approximately 1,000 respondents are surveyed for the Spectrum Health Value Study. Respondents are matched to the U.S. population by age, gender, region and ethnicity. The sample is provided by E-Rewards, a recognized leader in the online sample industry with 2.9 million panel members. Data collection is conducted by Russell Research, Inc. of New York, NY, a well-known leader in consumer research.

To ensure that the study sample is representative regardless of Internet access, in the fall of 2009 a telephone sample will be added to the study.

To measure how respondents value different aspects of health care is accomplished by using the Max-Diff method. The Max-Diff methodology was chosen over other possible techniques because it:

  • is easy to administer to respondents,
  • is easy to implement and to analyze, and
  • provides extremely discriminating data.

  • Max-Diff can be thought of as a more sophisticated extension of the Method of Paired Comparisons. Consider a set of four benefits or attributes which a respondent evaluates (i.e., A, B, C, and D). If the respondent says that B is the "most important" and A is the "least important" we know that:
    B > A; B > C; B > D; C > A; and D > A

  • Through two simple responses we obtain five implied paired comparisons

Statistical Notation for the Spectrum Health Value Study

The statistical significance of a result in this survey is the probability that the observed relationship (e.g., between variables) or a difference (e.g., between means) in a sample occurred by pure chance, and that in the population from which the sample was drawn, no such relationship or differences exist.

Using less technical terms, one could say that the statistical significance of a result tells us something about the degree to which the result is "true." More technically, the p-value represents a decreasing index of the reliability of a result. The higher the p-value, the less we can believe that the observed relation between variables in the sample is a reliable indicator of the relation between the respective variables in the population. Specifically, the p-value represents the probability of error that is involved in accepting our observed result as valid, that is, as "representative of the population." For example, a p-value of .05 (i.e.,1/20) indicates that there is a 5% probability that the relation between the variables found in our sample is a "fluke."

The following statistical notations are used throughout the study results:

= Indicates figure is significantly higher than the other sub-group at a 95% confidence level (i.e. p-value of .05 or less).

A letter indicates which group the number is significantly higher than, as follows:

  • M = Males; F = Females

  • S = Sufferers; NS = Non-Sufferers

  • C = Caregivers; NC = Non-Caregivers

  • Ca = Caucasian; A = African-American; H = Hispanic

If you have additional questions about methodology used in the Spectrum Health Value Study, please contact us.