Reliability achieved when responses to the same questions by two randomly

Reliability achieved when responses to the same

This preview shows page 9 - 11 out of 11 pages.

Reliability achieved when responses to the same questions by two randomly selected halvesof a sample are about the sameTest-retest reliability: A measurement showing that measure of a phenomenon at two points in time are highly correlated, if the phenomenon has not changed or has change only as much as the phenomenon itselfTriangulation: The use of multiple methods to study one research questionUnobtrusive measure: A measurement based on physical traces or other data that are collected without the knowledge or participation of the individuals or groups that generated the dataFour major classes of information:1.Attitudes: What people say they want2.Beliefs: What people think is true3.Behavior: What people do4.Attributes: What people areFour basic types of response structures:1.Open-ended2.Closed ended with ordered choices (fixed choices)3.Closed ended with unordered choices4.Partially close-ended
Background image
CHAPTER 8What is secondary analysis? Analysis of data collected by someone other than the researcher or the researcher’s assistantsWhy do researchers use secondary data analysis? There are a lot of high quality datasets available for use and it much less time consuming and expensive.What are some sources of data for secondary analysis? Inter-University consortium for political and Social Research at the University of Michigan, Individual researchers, the government, and other research organizations.What are the advantages of secondary research? More time can be spent on analysis, cheaper, less manpower isrequired.What is “data dredging”?it is mindlessly examining data with no purpose. What are the six major stages of data analysis?1.Coding2.Data Entry3.Descriptive Analysis4.Data Cleaning5.Cross-tab Analysis6.Testing relationshipsList and briefly describe these stages:What is coding? Coding is the process of assigning numerical codes to respondent’s qualitative responses. Codes should preserve the actual meaning of the respondent’s answers as closely as possible. Codes should reasonable preserve the variation in responses.What are the basic principles of code building? –Assigning numerical codes to data sets. –Preserve actual meaning of responses. –Preserve variation in responses.What are the difficulties in coding? No theory, tons of dataWhat is data entry? Process of taking all responses into an electronic database. Coded Responses> Word Processor-Spreadsheet-Data entry ProgramHow do we make sure that our data entry is accurate?What is a data file?How are data files typically organized? Coded responses; word processor, spreadsheet, data entry program. Collumns=Answers, Rows=ResponsesWhat is a codebook? An introduction, explains how to use the data. A map between questionnaire and data file.
Background image
Image of page 11

You've reached the end of your free preview.

Want to read all 11 pages?

  • Summer '19
  • researcher

  • Left Quote Icon

    Student Picture

  • Left Quote Icon

    Student Picture

  • Left Quote Icon

    Student Picture