Developing Survey Items Bonnie L. Halpern-Felsher, Ph.D. Professor University of California, San Francisco.

Slides:



Advertisements
Similar presentations
Measuring Complex Achievement: Essay Questions
Advertisements

Standardized Scales.
Bridging Research, Information and Culture An Initiative of the Research and Planning Group for California Community Colleges Your Name Your Institution.
Survey Methodology Reliability and Validity EPID 626 Lecture 12.
The Research Consumer Evaluates Measurement Reliability and Validity
Data Mining Methodology 1. Why have a Methodology  Don’t want to learn things that aren’t true May not represent any underlying reality ○ Spurious correlation.
The W’s of Data. Data  Does have to be numbers?  It can be doesn’t have to be.  Without context, it’s useless!  Consider 17, 21, 44, and 76  Are.
Survey Methodology Survey Instruments (2) EPID 626 Lecture 8.
Item Writing Techniques KNR 279. TYPES OF QUESTIONS Closed ended  Checking yes/no, multiple choice, etc.  Puts answers in categories  Easy to score.
Surveys and Questionnaires. How Many People Should I Ask? Ask a lot of people many short questions: Yes/No Likert Scale Ask a smaller number.
COLLECTING DATA ON A SAMPLE OF RESPONDENTS Designing survey instruments.
Study examined associations between adolescent information management (disclosure & secrecy), parenting behaviors (solicitation & rules), and adolescent.
Questionnaire Design Sudman & Bradburn (1988).  Question wording is a crucial element in maximizing the validity of survey data obtained by a questionnaire.
  Data can be numbers, record names, or other labels.  Not all data represented by numbers are numerical data (e.g., 1 = male, 2 = female or zip codes.
Teen Health Perspective Results “Honestly, most issues are mental like anxiety, stress, worry, and over thinking. They do all not need to be treated with.
Program Evaluation Essentials: Developing High-Quality Questionnaires Mary E. Arnold, Ph.D. Associate Professor and 4-H Research and Program Evaluation.
Chapter 8 Developing Written Tests and Surveys Physical Fitness Knowledge.
Journal Club Alcohol, Other Drugs, and Health: Current Evidence July–August 2008.
Research Ethics Levels of Measurement. Ethical Issues Include: Anonymity – researcher does not know who participated or is not able to match the response.
Data Collection Methods In Transportation Planning Part 2.
Introduction to Qualitative Research
Questionnaire Issues -- Asking the Right Questions.
EXPERIMENTS AND OBSERVATIONAL STUDIES Chance Hofmann and Nick Quigley
1 3. Drafting Each Module. What we typically think of as “Designing a Survey Instrument” Going question by question to ensure it meets the research objective.
Methodologic Overview of Two National Data Sets Centers for Disease Control and Prevention National Center for Health Statistics Issues in Comparing Findings.
Notes for Social Sciences Constructing Survey Questions.
1 MTN-003 Training General Interviewing Techniques Some specific tips for administering the Screening interviewer-administered CRFs SSP Section 14.
Writing Good Survey Questions EDF 811 Topic 11 3-Apr-01.
Alcohol Use During Pregnancy Data from Maryland PRAMS, Diana Cheng, M.D. Medical Director, Women’s Health Maryland Department of Health and Mental.
Pengukuran Opini Publik. Survey Research Survey research is a technique that well designed for assessing the prevalence and distribution of attitudes,
Study Design Population Sampling Frame Interview Length
Copyright © 2010 Pearson Education, Inc. Chapter 2 Data.
Psychometric Properties of the Consumer Assessment of Healthcare Providers and Systems (CAHPS) Clinician and Group Adult Visit Survey September 11, 2012.
Source: Massachusetts BRFSS Prepared by: Health Survey Program Using the BRFSS to Track Healthy People 2010 Objectives Highlights from the 2004 Massachusetts.
Correlational versus Experimental. Study on Alcohol and Speech Researchers were quite interested in the effect of alcohol on speech. They obtained four.
Lifestyles in Malta 2007 A Survey Study Judith Rocchiccioloi, PhD., RN Karen Jagiello, RN, MSN James Madison Univesity.
C M Clarke-Hill1 Collecting Quantitative Data Samples Surveys Pitfalls etc... Research Methods.
A review and maybe even some new information!. I can identify the negative effects of alcohol on the mind and body. I understand the difference between.
Construction and Evaluation of Multi-item Scales Ron D. Hays, Ph.D. RCMAR/EXPORT September 15, 2008, 3-4pm
Copyright 2006 – Biz/ed Market Research.
Itinerary What is the purpose of your survey? Types of survey questions Evaluating your survey Writing your survey questions Homework.
Qualitative Methods vs. Quantitative Methods. Qualitative Methods? Quantitative Methods?
How To Conduct A… Narrative Interview. What’s a Narrative Interview? A Narrative Interview captures the voice of the person interviewed, considers a significant.
Survey Research I.Elite Interviewing – process of interviewing respondents in a non-standardized, individualized manner (face-to-face). A. Why? 1. May.
What Does “No Opinion” Mean in the HINTS? Michael P. Massagli, Ph.D. K. Vish Viswanath, Ph.D. Dana-Farber Cancer Institute.
Strategies for Improving Medication Adherence. Assess Patient Understanding and Behavior  What we need to know and understand is: How do patients feel.
Question Wording Pierre-Auguste Renoir: The Ball at the Moulin de la Galette (1876)
Copyright © 2007 Pearson Education, Inc. Publishing as Pearson Addison-Wesley Chapter 2 Data.
PAIN. Pain Questions Do you have frequent pain? Do you use medication for pain? If yes: In the past 3 months, how often did you have pain? Some days,
Principles of Instrument & Measurement Development Bonnie L. Halpern-Felsher, Ph.D. Professor University of California, San Francisco.
QUESTIONNAIRE DESIGN.
Introduction to Inference: Confidence Intervals and Hypothesis Testing Presentation 4 First Part.
Designing a Questionnaire. Major Function of a Questionnaire –Translating the research objectives into specific questions Iterative Process –A good.
Developing Questionnaires. What is a questionnaire? A group of printed questions that the respondent answers by him/herself A key assumption: the respondent.
Creating A Good Questionnaire
Interacting with and Observing Young Children
Review: Alternative Assessments Alternative/Authentic assessment Real-life setting Performance based Techniques: Observation Individual or Group Projects.
The effects of Peer Pressure, Living Standards and Gender on Underage Drinking Psychologist- Kanari zukoshi.
Surveillance and Population-based Prevention Department for Prevention of Noncommunicable Diseases Displaying data and interpreting results.
1. Is data always recorded as numbers? 2. What do you organize data into for it to be easily read? 3. What is a categorical variable? 4. What is a quantitative.
Creating A Good Questionnaire IB Geography. Advantages and Disadvantages of Questionnaires Advantages –Can assess a large group quickly –Easy to analyze.
© 2011 McGraw-Hill Higher Education. All rights reserved. Drug Use: An Overview Chapter 1.
Abstinence and Consequences of Sexual Activity Pg Pg. 554 – 558 Pg
COLLECTING DATA: SURVEYS AND ADMINISTRATIVE DATA PBAF 526 Rachel Garshick Kleit, PhD Class 8, Nov 21, 2011.
Statistics 2 Data. What Are Data? Data can be numbers, record names, or other labels. Not all data represented by numbers are numerical data (e.g., 1.
Statistical Concepts Basic Principles An Overview of Today’s Class What: Inductive inference on characterizing a population Why : How will doing this allow.
PROMOTING THE HEALTH OF MEN WHO HAVE SEX WITH MEN WORLDWIDE A training curriculum for providers.
Health & Happiness Survey Disability Data May 2016.
Ways of doing Needs Assessment
Survey Methodology Reliability and Validity
Presentation transcript:

Developing Survey Items Bonnie L. Halpern-Felsher, Ph.D. Professor University of California, San Francisco

From Last Week Find existing measures of interest Create/continue creating/find an instrument with: –At least 2: factual questions frequency and quantity questions “feelings” subjective questions Evaluative questions Scales

Respondents are Able to Respond Items are specific, not ambiguous. Respondents know and remember information. Minimize burden of recall. If recall is needed, help respondent: –Place events or behavior in time –Use memory aids

Respondents are Able to Respond Examples: –Factual Data: SES, Parent Education, Income, Medical Data. Can ask the source (e.g., parents, teachers, chart reviews –Event-Specific Data: Since high school graduation… Since we last surveyed you… Provide calendars…

Respondents are Willing to Respond Items should be written such that respondent does not feel the need to respond inaccurately. Assure confidentiality.

Respondents are Willing to Respond Handling “Don’t Know” and “Not Sure” Responses: –Can provide a screening question –Can provide an option for N/A, None, Don’t Know –Don’t assume or judge

Ambiguous Measurement Items, measures and response sets should be specific enough so as to inform participants regarding the kinds of responses that are acceptable. Do not leave it open to interpretation. Only assess one concept per question.

Ambiguous Measurement Leads to: –Unreliable and invalid information. –Inability to discern age or developmental differences. –Inability to interpret data.

Ambiguous Measurement Can occur with respect to: –Behavior –Time –Events

Ambiguous Measurement Examples: Time In the past week, on how many days did you do homework?

Ambiguous Measurement Examples: Time In the past week, on how many days did you do homework? Better: In the past 7 days, on how many days did you do homework?

Ambiguous Measurement Examples: Behavior Have you ever smoked? Have you ever had sex? What is the chance you will get an STD if have sex?

Ambiguous Measurement Examples: Behavior Have you ever smoked? (amount) Have you ever had sex? (type of sex) What is the chance you will get an STD if have sex? (type of sex, context, partner type)

Factual Questions

Objective: Measure Age

Factual Questions Objective: Measure Age –Depends on how precise you need to be: Exact to the day? General year enough? –Depends on how much participants knows/remembers.

Factual Questions Objective: Measure Age –How old were you on your last birthday? –On what date were you born? –How old are you today?

Factual Questions Objective: Soft drink consumption

Factual Questions Objective: Soft drink consumption –Depends on how precise you need to be: Simply describe general consumption? Assess number of drinks consumed by sample in general? Examine trends over time?

Factual Questions Objective: Soft drink consumption –How many soft drinks did you drink yesterday? –How many soft drinks did you drink in the last 7 days? Should define “soft drink”

Factual Questions Objective: Use of Medical Care

Factual Questions Objective: Use of Medical Care –How are you defining medical care? –Are you counting events? Characterizing individuals?

Factual Questions Objective: Use of medical care –How many times have you seen or talked to a doctor about your health in the past 2 weeks? –How many times have you received any kind of medial care in the last 2 weeks? –How many times have you received any kind of medical care in the last 12 months?

Factual Questions Objective: Measure hospitalizations

Factual Questions Objective: Measure hospitalizations –Depends on how precise you need to be: Exact to the day? General year enough? –How is hospitalizations being defined?

Factual Questions Objective: Measure Age –How many times have you been hospitalized in the past year? Problems?

Factual Questions Objective: Measure Age –How many times have you been hospitalized in the past year? Better: –In the past 12 months, since (DATE) a year ago, how many different times have you been admitted to a hospital as a patient overnight or longer?

Factual Questions Objective: Alcohol consumption

Factual Questions Objective: Alcohol consumption –How many drinks did you have altogether yesterday? Problems?

Factual Questions Objective: Alcohol consumption –How many drinks did you have altogether yesterday? Better: –On days when you have anything alcoholic to drink, how many drinks do you usually have?

Factual Questions Objective: Alcohol consumption –If a teen, or for all people… Likely need to define drink – –E.g., How many times have you had a glass of wine, bottle of beer, or shot of whiskey?

Subjective Questions

Subjective States How would you rate your health?

Subjective States Do you consider crime to be a problem in your neighborhood?

Subjective States Think of an important adult in your life…

Subjective States What is the chance you will get into trouble if you tell a lie?

Ambiguous Measurement Examples: Multiple Concepts I love to play ball sometimes. (True/False)

Ambiguous Measurement Examples: Multiple Concepts I love to play ball sometimes. (True/False) –Is subject responding to “sometimes” or “playing ball?”

Ambiguous Measurement: Some Solutions Provide as much detail as is necessary…without burdening respondent. If construct being measured is too complex for one item, use multiple items. Provide definitions, either before the measure or embedded within the measure.

Ambiguous Measurement: Some Solutions Definition Before Measure: –For the next 10 questions, when we ask about sex, we are talking about consensual intercourse (going all the way…) Within the item: –Have you ever had at least one drink of alcohol (that is, one beer, glass of wine, shot of hard liquor or wine cooler?)

Ambiguous Measurement: Some Solutions Scenario: –Imagine you have been DATING TANYA FOR 3 MONTHS. You both have had sex with two other people but not with each other. Tonight, you and Tanya have sex one time. You DO NOT USE A CONDOM or other safer sex method (e.g., other birth control, withdrawal).

Answering the Questions: Scale Development

General Principles Response set must fit the item/question. Response set should be consistent across types of questions and throughout survey. Balance between detail and accuracy. Responses should fit analytic plan. Consider number and type of response categories.

Response Set Must Fit Items How likely are you to drink alcohol in the next 6 months? –Definitely will to Definitely will not Vs. –Very likely to Very Unlikely

Consistent Response Do not switch order of responses. Do not switch number or type of responses. –Examples: Yes/No  No/Yes Agree/Disagree  Disagree/Agree

Detail vs. Accuracy In general, more detail is best as you can always recode or reduce data, especially with subjective states. But, can reduce accuracy, especially when assessing factual information.

Fits With Analytic Plan How will you analyze the data?

Number of Response Categories In general, between 5 and 7 responses is best to provide meaningful data. Little new, valid data is obtained after 10. If phone survey, best is 3-4 response choices. Odd vs. even number?

Type of Response Sets Do not use both numbers and adjectives (e.g., 1-5 and likely scale). Best: Adjectives, as numbers do not always engender meaning in the same way. –E.g., the mid-point on a 10-point scale is not always the same to people.

Type of Response Sets Disagree/agree Rank order Narrative or open-ended Magnitude estimation techniques

Type of Response Sets Depends on research aims, answers sought, and how will analyze data!

Type of Response Sets For example: –Overall, how would you rate your physical health? Excellent  Poor –On a scale from 0 to 10, where 10=best and 0=worst, how would you rate your physical health? –Overall, would you say you are in good physical health? GOOD/NOT GOOD

Type of Response Sets Likely scales: –Very likely –Likely –Unlikely –Very unlikely