6 Scales, Tests, & Indexes.

Slides:



Advertisements
Similar presentations
Allyn & Bacon 2003 Social Work Research Methods: Qualitative and Quantitative Approaches Topic 7: Basics of Measurement Examine Measurement.
Advertisements

Test Development.
Standardized Scales.
Scales and Indices Scales and Indices combine several categories in a question or several questions into a “composite measure” that represents a larger.
Developing a Questionnaire
MGT-491 QUANTITATIVE ANALYSIS AND RESEARCH FOR MANAGEMENT
Measurement the process by which we test hypotheses and theories. assesses traits and abilities by means other than testing obtains information by comparing.
MEASUREMENT. Measurement “If you can’t measure it, you can’t manage it.” Bob Donath, Consultant.
1 Measurement PROCESS AND PRODUCT. 2 MEASUREMENT The assignment of numerals to phenomena according to rules.
1 Measurement Measurement Rules. 2 Measurement Components CONCEPTUALIZATION CONCEPTUALIZATION NOMINAL DEFINITION NOMINAL DEFINITION OPERATIONAL DEFINITION.
Scaling and Attitude Measurement in Travel and Hospitality Research Research Methodologies CHAPTER 11.
Chapter 9 Flashcards. measurement method that uses uniform procedures to collect, score, interpret, and report numerical results; usually has norms and.
Social Science Research Design and Statistics, 2/e Alfred P. Rovai, Jason D. Baker, and Michael K. Ponton Internal Consistency Reliability Analysis PowerPoint.
Descriptive Statistics  Summarizing, Simplifying  Useful for comprehending data, and thus making meaningful interpretations, particularly in medium to.
Descriptive Statistics Used to describe the basic features of the data in any quantitative study. Both graphical displays and descriptive summary statistics.
Census A survey to collect data on the entire population.   Data The facts and figures collected, analyzed, and summarized for presentation and.
McMillan Educational Research: Fundamentals for the Consumer, 6e © 2012 Pearson Education, Inc. All rights reserved. Educational Research: Fundamentals.
Analyzing Reliability and Validity in Outcomes Assessment (Part 1) Robert W. Lingard and Deborah K. van Alphen California State University, Northridge.
Chapter 1: Research Methods
CHAPTER 6, INDEXES, SCALES, AND TYPOLOGIES
1.1 - Populations, Samples and Processes Pictorial and Tabular Methods in Descriptive Statistics Measures of Location Measures of Variability.
Introduction to Descriptive Statistics Objectives: 1.Explain the general role of statistics in assessment & evaluation 2.Explain three methods for describing.
Chapter 2 Describing Data.
Counseling Research: Quantitative, Qualitative, and Mixed Methods, 1e © 2010 Pearson Education, Inc. All rights reserved. Basic Statistical Concepts Sang.
Indexes, Scales & Scaling l Indexes Indexes l General Issues in Scaling General Issues in Scaling General Issues in Scaling l Thurstone Scaling Thurstone.
Appraisal and Its Application to Counseling COUN 550 Saint Joseph College For Class # 3 Copyright © 2005 by R. Halstead. All rights reserved.
Learning Objective Chapter 9 The Concept of Measurement and Attitude Scales Copyright © 2000 South-Western College Publishing Co. CHAPTER nine The Concept.
Selecting a Sample. Sampling Select participants for study Select participants for study Must represent a larger group Must represent a larger group Picked.
Learning Objectives Copyright © 2002 South-Western/Thomson Learning Using Measurement Scales to Build Marketing Effectiveness CHAPTER ten.
Measurement and Questionnaire Design. Operationalizing From concepts to constructs to variables to measurable variables A measurable variable has been.
Slide 10-1 © 1999 South-Western Publishing McDaniel Gates Contemporary Marketing Research, 4e Using Measurement Scales to Build Marketing Effectiveness.
The Practice of Social Research Chapter 6 – Indexes, Scales, and Typologies.
Measurement Theory in Marketing Research. Measurement What is measurement?  Assignment of numerals to objects to represent quantities of attributes Don’t.
CHAPTER Basic Definitions and Properties  P opulation Characteristics = “Parameters”  S ample Characteristics = “Statistics”  R andom Variables.
Chapter 6 Indexes, Scales, And Typologies Key Terms.
Methods of Data Collection Survey Methods Self-Administered Questionnaires Interviews Methods of Observation Non-Participant Observation Participant Observation.
Chapter 6 - Standardized Measurement and Assessment
Chapter 6 Indexes, Scales, And Typologies. Chapter Outline Indexes versus Scales Index Construction Scale Construction.
1 Collecting and Interpreting Quantitative Data Deborah K. van Alphen and Robert W. Lingard California State University, Northridge.
Educational Research Chapter 8. Tools of Research Scales and instruments – measure complex characteristics such as intelligence and achievement Scales.
ESTABLISHING RELIABILITY AND VALIDITY OF RESEARCH TOOLS Prof. HCL Rawat Principal UCON,BFUHS Faridkot.
Slide 1 Copyright © 2004 Pearson Education, Inc.  Descriptive Statistics summarize or describe the important characteristics of a known set of population.
7 th Grade Math Vocabulary Word, Definition, Model Emery Unit 4.
Selection of appropriate instruments/Validation of the Instrument It is important to ensure that instruments measures what they are designed to measure.
Chapter 2 Theoretical statement:
Indexes, Scales, and Typologies
CHAPTER 6, INDEXES, SCALES, AND TYPOLOGIES
Measurement and Observation
Understanding Results
Copyright ©2013 Pearson Education, Inc. publishing as Prentice Hall
(12) students were asked their SAT Math scores:
Introduction to Measurement
پرسشنامه کارگاه.
1 Chapter.
Measuring Social Life: How Many? How Much? What Type?
Chapter 3 Describing Data Using Numerical Measures
Chapter Eight: Quantitative Methods
Statistics and Research Desgin
Reliability, validity, and scaling
Analyzing Reliability and Validity in Outcomes Assessment Part 1
MEASURES OF CENTRAL TENDENCY
Test Development Test conceptualization Test construction Test tryout
Chapter 6 Indexes, Scales, And Typologies
M e a s u r e m e n t.
(-4)*(-7)= Agenda Bell Ringer Bell Ringer
Analyzing Reliability and Validity in Outcomes Assessment
Ticket in the Door GA Milestone Practice Test
Ticket in the Door GA Milestone Practice Test
Chapter 6 Indexes, Scales, and Typologies
Collecting and Interpreting Quantitative Data
Presentation transcript:

6 Scales, Tests, & Indexes

6.1 Foundations of Scales, Tests, and Indexes Three approaches for measuring a construct: Scales Measure abstract concepts, like attitudes Tests Measure some ability or knowledge Indexes Combines several measures to estimate a more complex construct

6.2 Scales and Scaling Scaling Unidimensional scaling types Involves the construction of an instrument that associates qualitative constructs with quantitative metric units Unidimensional scaling types Thurstone or Equal-Appearing Interval Scaling Likert or Summative Scaling Guttman or Cumulative Scaling

6.2a General Issues in Scaling Figure 6.2 Scaling as the assignment of numbers according to a rule

6.2a Types of Scales Response scale Dichotomous response A sequential-numerical response format, such as a 1-to-5 rating format Dichotomous response Has two possible options (e.g., true/false or yes/no) Interval response scale Measured on an interval level, where the size of the interval is meaningful

6.2a Differences Between Scaling and Response Scales Table 6.1 Differences between scaling and response scales. Ask the class to identify an example of a construct being measured for each scale and response scale.

6.2b Purposes of Scaling To test a hypothesis To discover if a construct is unidimensional or multidimensional As part of exploratory research To represent a construct as a single score

6.2c Dimensionality Unidimensional Scales Two Dimensional Scales Figure 6.3 Unidimensional scales: For each construct in the figure (height, thirst, and self-esteem) the measurement is on a single dimension. Figure 6.4 A two dimensional scale: Here, a single construct is being measured in two dimensions (quantitative and verbal). Unidimensional Scales Two Dimensional Scales

6.2c Dimensionality Figure 6.5 A three dimensional scale. Semantic differential: A scaling method in which an object is assessed by the respondent on a set of bipolar adjective pairs.

6.2d Unidimensional or Multidimensional? Unidimensional scales are easier to use and understand Used when: What you are measuring is unidimensional in reality If the concept is not unidimensional, this scale will not measure the concept well, and you need to choose a multidimensional approach

6.2d Unidimensional or Multidimensional? Unidimensional types Thurstone scaling Likert scaling Guttman scaling Thurstone Scaling: A class of scaling methods (the method of equal appearing intervals, the method of successive intervals, and the method of paired comparisons) that were designed to yield unidimensional, intervallevel, multi-item scales. Likert or summative scaling: A method of scaling in which the items are assigned interval level scale values and the responses are gathered using an interval-level response format. Guttman or cumulative scaling: A method of scaling in which the items are assigned scale values that allow them to be placed in a cumulative ordering with respect to the construct being scaled.

Thurstone Scaling: The Method of Equal Appearing Intervals Develop the focus of the scaling project Generate potential scale items (statements); 80-100 separate items Rate the scale items Compute scale score values for each item Median, interquartile range Selecting the final scale items Administering the scale Median: The score found at the exact middle or 50th percentile of the set of values. One way to compute the median is to list all scores in numerical order and then locate the score in the center of the sample. interquartile range: The difference between the 75th (upper quartile) and 25th (lower quartile) percentile scores on the distribution of a variable. The interquartile range is an estimate of the spread or variability of the measure.

Displaying the Median and Interquartile Ranges of the Attitude Data Figure 6.7 Histogram displaying the median and interquartile ranges of the attitude data.

Likert Scaling Define the focus Generate the items on a 1-5 or 1-7 agree/disagree response scale Have a group of judges rate the items Select the items by computing the intercorrelations between all pairs of items Administer the scale Forced Choice Response Scale; Reversal Items Forced-choice response scale: A response scale that does not allow for a neutral or undecided value. By definition, a forced-choice response scale has an even number of response options. Reversal items: Items on a multi-item scale whose wording is in the opposite direction of the construct of interest. Reversal items must have their scores reversed prior to computing total scale scores.

The Employment Self-Esteem Likert Scale Table 6.2: The Rosenberg scale.

Guttman Scaling (Scalogram Analysis) Define the focus Develop the items (80-100) Have a group of judges rate the items Develop the cumulative scale Administer the scale Scalogram analysis: A method of analysis of a set of scale items used when constructing a Guttman or cumulative scale. In scalogram analysis, one attempts to determine the degree to which responses to the set of items allows the items to be ordered cumulatively in one dimension with respect to the construct of interest.

Developing a Cumulative Scale with Guttman Scaling Figure 6.9 Developing a cumulative scale with Guttman scaling.

6.3 Tests A test is a measure designed to measure a respondent’s knowledge, skill, or performance The history of testing goes back to 2200 BCE The key for a good test is reliability and validity

Example: A Driving Simulator Figure 6.9 This driving simulator was used as part of a driver-training study for adolescents with attention deficit problems (Fabiano et al., 2011). Courtesy of Kevin F. Hulme Tests: A measure designed to measure a respondent’s knowledge, skill, or performance.

6.3a Validity, Reliability, and Test Construction Factor analysis Consequential validity Test-retest reliability Item analysis Figure 6.10 What validity issue do you see here? Factor analysis: A multivariate statistical analysis that uses observed correlations (variability) as input and identifies a fewer number of unobservedvariables, known as factors, that describe the original data more efficiently. Consequential validity: The approximate truth or falsity of assertions regarding the intended or unintended consequences of test interpretation and use. Test-retest reliability: A method of estimating the reliability or consistency of a test or measure by assessing the degree of correlation between two successive administrations. Item Analysis: The correlation of a particular item with the total subtest or test score.

6.3b Standardized Tests A method of test construction that uses statistics and a large sample of previously taken tests to “standardize” the measurement Includes statistics such as: Mean, median, and mode Percentiles Variance and standard deviation Correlations with other, related tests

6.3c Test Fairness Many factors affect standardized test performance Consequential validity Many decision makers (e.g., universities) have begun to either do away with standardized test scores or to combine single test scores with other measures of ability Does your SAT score fairly reflect your intelligence?

6.3d How to Find A Good Test Test publishers Primary research literature Test reviews in academic journals Buros Center for Testing at the University of Iowa APA

6.4 Indexes Index A quantitative score that measures a construct of interest by applying a formula or a set of rules that combines relevant data

6.4a Some Common Indexes Consumer Price Index (CPI) Socioeconomic Status (SES) Duncan Socioeconomic Index (SEI)

6.4b Constructing an Index Conceptualize the index Operationalize and measure the components Develop the rules for calculating the index score Weighted Index Weighted Index: A quantitative score that measures a construct of interest by applying a formula or a set of rules that combines relevant data where the data components are weighted differently.

Discuss and Debate I Consider standardized tests Are they fair? What are some factors that may affect a person’s performance?

Discuss and Debate II Have you ever answered questions on a scale in a way that would make you look good? Some measurements may not be accurate when respondents do not answer truthfully – what can be done? In research, this is called the social-desirability bias. Allow the class to discuss the ways in which that bias can skew the results of a study.