§411.301. Definitions Used in Subpart D  


Latest version.
  • Absolute value – A nonnegative number equal in numerical value to a given real number.

     

    Attempt – Using a phone, electronic mail or U.S. mail to contact residential or nonresidential customers.

     

    Categorical questions – Questions with response options limited to prescribed categories.

     

    Confidence interval – A range believed to contain the actual response of the entire population, based on a sample result.

     

    Confidence level – The probability that a result, based on a sample, is likely to contain the actual response of the entire population.

     

    Contact information − A residential or nonresidential customer's name, street address, phone number and/or email address.

     

    Contingency table – A depiction of observed and expected frequencies in the sample data.

     

    Correlation coefficient – An indicator of both the strength and the direction of a relationship between responses. The coefficient has two components:  a value and a sign.  Coefficient values range from 0 to 1 or 0 to -1 and indicate the strength of the relationship between two variables. As the value of the coefficient approaches 1, the relationship becomes stronger, with a value of 1 indicating a one-to-one correlation. As the value of the coefficient approaches 0, the relationship becomes weaker, with a value of 0 indicating no relationship. The coefficient can be either positive or negative.

     

    Cross-tabulations – A widely used method for studying the relationship or association among and between variables. In cross-tabulation, the sample is divided into subgroups in order to examine how a variable of interest varies from subgroup to subgroup.

     

    Descriptive statistics – Statistics that organize and summarize information without interpreting meaning. Descriptive statistics include, but are not limited to, the range of responses, the median response, the mean response, and the modal response.

     

    Firmographics – The statistical data of a business.

     

    Mean response – The sum of the numeric value of each response divided by the number of responses.

     

    Median response – The numeric value of the response with 50% of responses above and 50% below it.

     

    Modal response – The response that occurs most frequently.

     

    Non-responses – The number of individuals in the sample who are not reached or refuse to respond to the entire survey or to a specific question.

     

    Pearson Product Moment Correlation – The maximum likelihood estimator of population correlation, under normal conditions. If underlying requirements are met, it is most likely to detect co-variation or relationship between variables in the population.

     

    Population – The total number, in each category, of residential and non-residential customers for the jurisdictional entity.

     

    Range of responses – The distance between the highest score and the lowest score.

     

    Rating questions – Questions with response options expressed as a numeric value on a scale of zero to ten.

     

    Respondents – The number of residential or nonresidential customers who are reached and complete the survey.

     

    Response rate – This is calculated by dividing the number of respondents by the number of prospective respondents contacted.

     

    Sample size – The total number of randomly selected customers, including those who responded and those who did not.

     

    Sampling frame – The size of the accessible population from which a sample is drawn.  For example, where jurisdictional entities draw the sample from their customer databases, the sampling frame is identical to the population.  Where jurisdictional entities use random digit dial, the sampling frame shall be valid customer telephone numbers.

     

    Standard chi-square test – A statistical test used to determine if a relationship between variables exists by comparing expected and observed cell frequencies.  Specifically, a chi-square test examines the observed frequencies in a category and compares them to what would be expected by chance or would be expected if there were no relationship between variables.

     

    Statistically significant – Differences at the .05 probability level and/or relationships with a statistically significant correlation of .5 or higher.

     

    Yes/no questions – Questions with yes or no response options.

     

(Source:  Amended at 46 Ill. Reg. 5653, effective March 22, 2022)