Most commonly used research techniques are interviews and self administered questionnaires
Why are questionnaires important?
They’re used to gather information about particular subject.
Getting peoples opinions about a particular subject
Gathering customer satisfaction about a product
Collecting information to classify people and their circumstances
Collecting info to track baseline changes over time
What questions must you consider when you want to make a questionnaire?
What do we want to know according to the objectives, hypothesis and variables we have identified?
Are there previous studies that have been done with questionnaires that can be adapted?
Do we understand the topic sufficiently to develop a questionnaire for it? Or do we need loosely structured key informant interviews or focus group discussions to orient ourselves on the topic first?
What is the level of illiteracy among the informants
How large is the sample that will be interviewed?
Whom will we ask the questions and what techniques will we use ?
When shouldn’t you use questionnaires ?
Shouldn’t be used to explore complex issues in depth
Shouldn’t be used to explore new, difficult or potentially controversial issues(in this case, longer unstructured depth interviews would be more appropriate here)
Don’t use it as an easy option which will require little time or effort
Questionnaires are usually what type of questions ?
Closed and open ended questions.
Could be both.
They must be arranged in a way that the questions flow naturally
When will you want to use open ended questions?
To obtain information on facts the researcher isn’t well acquainted with or not familiar with.
To get info on the opinions, attitudes and suggestions of informants on sensitive issues
Advantages and disadvantages of open ended questions
Advantages ;
To explore issues not previously thought of when planning the study
Provides spontaneous valid answers
Information provided in the respondents own words may be a useful example of interest in the final report
It avoids creating biased answers
Disadvantages;
Needs a skilled interviewer
The analysis is time consuming
Respondents may not know how much to write or how long to respond to an answer
Got it! Here are just the three flashcard questions:
1. What type of questionnaire uses only close-ended questions with fixed response options?
2. Which type of questionnaire combines both open-ended and close-ended questions to allow for guided but flexible responses?
3. What kind of questionnaire is most suitable for exploring detailed personal experiences and has no fixed format?
Here are three flashcard-style questions based on the differences between structured, semi-structured, and unstructured questionnaires:
⸻
Flashcard 1
Q: What type of questionnaire uses only close-ended questions with fixed response options?
A: Structured questionnaire.
⸻
Flashcard 2
Q: Which type of questionnaire combines both open-ended and close-ended questions to allow for guided but flexible responses?
A: Semi-structured questionnaire.
⸻
Flashcard 3
Q: What kind of questionnaire is most suitable for exploring detailed personal experiences and has no fixed format?
A: Unstructured questionnaire.
⸻
Let me know if you want more or need them in a printable or app-import format!
Here’s a clear breakdown of structured, semi-structured, and unstructured questionnaires in a table format to help you compare and understand each one:
Type of Questionnaire Definition Characteristics Advantages Disadvantages Example Questions
Structured A questionnaire with pre-determined questions and fixed response options. - Close-ended questions- Fixed order- Easy to analyze- Standardized - Easy to administer and analyze- Suitable for large samples- Reduces interviewer bias - Limits depth of responses- Cannot explore new ideas “How often do you exercise?□ Daily □ Weekly □ Monthly □ Never”
Semi-Structured A questionnaire that includes a mix of close-ended and open-ended questions. - Combination of fixed and flexible parts- Allows probing- Guided but open to elaboration - Balances structure and flexibility- Can collect both qualitative and quantitative data - Requires trained interviewer- More time-consuming “How would you rate our service?□ Excellent □ Good □ Fair □ PoorWhy did you choose this rating?”
Unstructured A questionnaire with open-ended questions allowing free response. - Open-ended questions only- No fixed order- Exploratory- Interviewer-led - In-depth understanding- Encourages detailed responses - Hard to analyze statistically- Time-consuming- Potential bias “Can you describe your experience using our service?”
⸻
Summary:
• Use structured when you need quantitative, easily comparable data.
• Use semi-structured when you need both statistics and deeper insights.
• Use unstructured when you want to explore personal experiences or new topics in depth.
Let me know if you want this tailored to a research project you’re working on!
When will you want to use closed ended questions?
To offer a list of choices or options from which the respondent must choose from
Make sure the list of options are as few as possible. (If you find yourself having to add plenty options then closed ended questions won’t help you cuz it means you need in depth info)
Advantages and disadvantages of closed ended questions
Advantages
Easy recording and analyzing answers
Disadvantages:
Less suitable for one on one interviews with illiterates
Causes leading bias and loss of details
Respondents and interviewers may lose interest after a number of closed ended questions
Types of response scales
What type of questionnaires do response scales fall under
Pre-coded, single-choice
questions
Rank- ordering questions
Open-ended questions
Likert-type questions
Rating scales
Response scales fall under structured questionnaires.
Why?
• Structured questionnaires use pre-defined questions with fixed response options, and response scales (like Likert scales, rating scales, frequency scales) are a type of these fixed options.
Examples of response scales:
• Likert scale:
“I am satisfied with the service.”
□ Strongly Agree □ Agree □ Neutral □ Disagree □ Strongly Disagree
• Frequency scale:
“How often do you exercise?”
□ Never □ Rarely □ Sometimes □ Often □ Always
These scales quantify attitudes, behaviors, or opinions and make it easier to analyze data statistically — a hallmark of structured questionnaires.
Let me know if you’d like a breakdown of different types of response scales!
Great question! Here’s the clarification:
⸻
Response scales can be used in both structured and semi-structured questionnaires, but their role is different depending on the context:
Questionnaire Type Use of Response Scales
Structured Response scales are central — all questions use standardized answer options (e.g., Likert, frequency scales). There’s little or no room for open answers.
Semi-Structured Response scales may be used for some questions, but are typically followed by open-ended questions to explain or expand on the answer. This mix allows both quantification and exploration.
⸻
Example in a Semi-Structured Questionnaire:
Q1: How satisfied are you with our service?
□ Very satisfied □ Satisfied □ Neutral □ Dissatisfied □ Very dissatisfied
Q2: Can you explain the reason for your rating? (Open-ended)
In this case, the response scale provides structure (quantitative), and the open-ended follow-up adds flexibility (qualitative), which is the essence of a semi-structured design.
⸻
Summary:
• Response scales = structured tool
• In semi-structured questionnaires, they’re used alongside open-ended questions to enrich the data.
Let me know if you want visual flashcards or a diagram to summarize this!
What are pre coded single choice response scales
Pre coded single choice questions ask respondents to indicate which one category applies
The answers are pre coded for easy entry
If not all options can be listed, include “Other” with a space to indicate what the “Other” category implies
“Please specify”.
⸻
If you love pineapple, and it’s not listed, you can tick:
• ✅ “Other”, and write “pineapple” in the blank space.
So, “Please specify” just means:
👉 Tell us exactly what you mean by ‘Other’.
Categories should be mutually exclusive (no categories should overlap with one another. These are also called as closed ended questions
TYPES OF SCALES
Dichotomous question: this is a question that will generally be a “yes/no” question, but may also be an “agree/disagree” question.
UNIV
It is the quickest and simplest question to analyze, but is not a highly sensitive
measure.
Multiple choice questions: these questions consist of three or more mutually-exclusive categories and ask for a single answer or several answers.
Multiple choice questions allow for easy analysis of results, but may not give the respondent the answer they want.
Example of pre coded single choice example
What toping do you like the
best on dessert?
nuts 1▫️
chocolate 2▫️
jelly 3▫️
sprinkles 4 ▫️
Others: ______(please specify)
Presence–absence questions are a type of pre-coded, single-choice question — typically binary (Yes/No) in nature. It’s a question designed to detect whether something is present or not, usually with fixed response options like:
• Yes / No
• Present / Absent
• True / False
⸻
🔧 Type:
• Structured questionnaire
• Pre-coded (responses are already defined)
• Single choice (respondent picks one)
⸻
🧾 Example:
Do you have a fever?
□ Yes
□ No
This is a presence–absence question because it checks if a condition exists (fever = present or not).
What are rank order scale questions
Does it address the issue of why the participant makes a certain ranking?
ank-order (or ordinal) scale
questions: this type of question asks your respondent to rank items or choose items in a particular order
from a set.
For example, it might ask your respondents to order five things from least to most important. These types of questions forces discrimination among alternatives, but does not address the issue of why the respondent made these discriminations.
Example of rank ordering scale questions
What are the disadvantages of these type of questions?
Rank-order scales
are comparative scales(cuz you’re comparing different things by asking people to pick which they would prefer more)
• Ask respondents to indicate an ordering of response items, usually from most preferred to least preferred
Rank-Ordering Questions: Example
1. Rank-order the three most important characteristics you want in the job you make your life’s work.
2. (Place a 1 beside the most important one; a 2 beside the second most important one; and a 3 beside the next most important one.) or most preferred to least preferred
> Disadvantages
• Must make the instructions explicit
• If alternative choice is missing, respondent’s answer could be misleading.
• Ordinal scale: will not have the “distance” between the ranks
• Does not offer information as to why the respondent choose the order he or she selected.
• These types of questions should be avoided or minimized because they take time
What are rating scales
State the types
LIKERT SCALE
Researchers disagree on whether the Likert Scale is an ordinal or interval scale.
Those who argue that likert scales is an ordinal scale say the intervals between the five-points of the scale are unknowable.
What does the above mean
Those that argue that is is an interval scale score Strongly disagree as
1, “Disagree” as a 2, “Neutral” as a
3, “Agree” as a 4, and “Strongly
Agree”
as a 5.
No worries — let me explain it in plain, simple language.
⸻
What is a Likert scale?
It’s a type of question where you’re asked to rate how much you agree or disagree. For example:
How satisfied are you with your job?
1 = Strongly Disagree
2 = Disagree
3 = Neutral
4 = Agree
5 = Strongly Agree
⸻
What does “intervals are unknowable” mean?
It means:
👉 We don’t know if the “jump” between each point on the scale is equal.
Let’s break that down:
• The difference between 1 (Strongly Disagree) and 2 (Disagree) might feel small to one person…
• But the difference between 3 (Neutral) and 4 (Agree) might feel big to that same person.
So even though the numbers go up by 1, people may not feel the difference equally.
⸻
Why do people say that?
Because a Likert scale shows the order of feelings, not the exact size of the feeling.
It tells us that someone who picked “4” agrees more than someone who picked “3”…
But it doesn’t tell us how much more they agree.
⸻
Simple Example:
Imagine two people:
• Person A: Goes from 2 to 3 and feels only a little better.
• Person B: Goes from 3 to 4 and feels a lot better.
Even though both moved up by one number, the emotional difference is not the same.
That’s what we mean when we say the intervals (gaps) are unknowable.
⸻
Let me know if you’d like a simple visual or analogy (like a ladder or thermometer) to help even more!
Respondents who choose neutral in the likert scale, what interpretations can you give to them
Respondents who choose “neutral” may be those who:
• Are really neutral about the issue
• Do not know enough about the issue to form an opinion
• Those who do not want to reveal their true opinion.
Problems with adding a neutral scale to the likert scale
What is the difference between neutral and don’t know
Can give artificial results.
“Don’t know” vs. “neutral”
Respondent does not know enough about the issue to have an opinion about it
Neutral- Respondent knows about the issue, but does not have a positive or negative opinion about it
If you include “neutral” and not “don’t know” you may have an artificial number of “neutral” answers for people who really “don’t know”.
The “don’t know” option should be separate from the other options
Why should you mix favorable and unfavorable statements when constructing scales or rating scales or even likert scales
Great question — let’s unpack your notes clearly and simply, especially in the context of constructing a psychological scale like the Rosenberg Self-Esteem Scale.
⸻
🧠 What is the Rosenberg Self-Esteem Scale (RSES)?
It’s a 10-item scale designed to measure a person’s overall self-esteem — how they see and value themselves.
⸻
🧩 1. What are the attributes of self-esteem?
Self-esteem includes:
• Self-worth (feeling you have value)
• Self-respect
• Confidence in your abilities
• Feeling proud of yourself
• Positive or negative self-image
Each statement on the scale reflects one of these aspects.
⸻
🗨️ 2. Sample statements from the RSES:
• Favorable (positive) statements:
• “On the whole, I am satisfied with myself.”
• “I take a positive attitude toward myself.”
• “I feel that I’m a person of worth.”
• Unfavorable (negative) statements:
• “I feel I do not have much to be proud of.”
• “I certainly feel useless at times.”
• “I am inclined to feel that I am a failure.”
⸻
✅ 3. Why mix favorable and unfavorable statements?
Mixing positively and negatively worded items helps to:
• Check internal validity — making sure people aren’t just ticking “Agree” to everything mindlessly.
• It forces them to think carefully about each statement.
• It also balances the scale and reduces response bias (like always agreeing or disagreeing).
⸻
🧪 4. Internal validity — what does that mean here?
It means:
Is the scale measuring what it’s supposed to measure — consistently and accurately?
By including a mix of positive and negative statements, we can:
• Detect inconsistent answers (e.g., someone says “I feel useless” and also “I take a positive attitude toward myself” — that may need checking).
• Make sure the responses reflect true self-esteem, not just a pattern of clicking similar options.
⸻
🔁 Summary:
Concept Meaning
Attributes of self-esteem Self-worth, confidence, pride, respect
Favorable statements Show high self-esteem
Unfavorable statements Show low self-esteem
Why mix both? To check for consistency, reduce bias, and improve internal validity
What is response bias
✅ What is Response Bias?
Response bias refers to any systematic tendency for people to answer questions in a way that does not reflect their true feelings, thoughts, or behaviors — usually due to how the question is asked or how they think they should respond.
In simple terms:
It’s when people don’t answer honestly or accurately, often without realizing it.
⸻
🧠 Common Types of Response Bias:
Type What it Means Example
Social desirability bias Giving answers that make you look good or acceptable Saying “I never lie” even if it’s not fully true
Acquiescence bias Tendency to agree with statements regardless of content Agreeing with both “I feel confident” and “I feel worthless”
Extreme responding Always choosing the most extreme options Always picking “Strongly agree” or “Strongly disagree”
Central tendency bias Always choosing neutral or middle responses Picking “Neither agree nor disagree” for everything
Question order bias Earlier questions affect how you answer later ones Answering emotionally after a sad question
⸻
🧪 Why is response bias a problem?
Because it can:
• Skew the results
• Reduce the accuracy of your survey or study
• Lead to false conclusions
⸻
🛡️ How to reduce it:
• Mix positive and negative statements
• Assure anonymity/confidentiality
• Use clear and neutral wording
• Randomize question order when possible
⸻
Let me know if you’d like to see how response bias affects real-life questionnaires like self-esteem or health surveys!
Constructing scales
• Use matrix type questions when they all have the same answer choices (perfect for likert items)
What does this mean
Great — you’re diving into the practical aspects of constructing Likert-scale items within a matrix format. Let’s break it down simply:
⸻
✅ What the notes mean:
🗂️ 1. “Use matrix-type questions when they all have the same answer choices”
This means:
If you’re asking multiple questions (statements) that all use the same response options, it’s more efficient and clean to arrange them in a table or grid format.
👉 Perfect for Likert scale items where responses like:
Strongly Agree (SA), Agree (A), Undecided (U), Disagree (D), Strongly Disagree (SD)
apply to all the statements.
⸻
📋 2. Sample format (Matrix Question):
Statement SA A U D SD
a. The police should be disarmed in America. ○ ○ ○ ○ ○
b. Looters should be shot on sight during riots. ○ ○ ○ ○ ○
c. I trust the government to maintain public safety. ○ ○ ○ ○ ○
So instead of writing full Likert options every time under each question, you put them once as column headers — this is a matrix format.
⸻
🤔 3. “Note the ‘Undecided’ option instead of ‘Neutral’”
• Usually, Likert scales have a middle point (e.g. “Neutral”)
• Here, they’re calling it “Undecided” instead
• Why it matters:
• “Neutral” implies a balanced or indifferent opinion
• “Undecided” implies the person hasn’t formed an opinion yet
That subtle difference can affect how people respond.
⸻
🔁 4. “Note where it is positioned”
Typically, the neutral/middle option is placed in the center of the scale.
In your note, it seems like “Undecided” is not in the center, which is unusual.
👉 If the order is, say:
Strongly Agree – Agree – Disagree – Strongly Disagree – Undecided
That can confuse the respondent and bias responses.
⸻
✅ Best practice:
Place Undecided or Neutral in the middle of the scale to:
• Maintain balance
• Reflect that it’s the “in-between” choice
Like this:
SD – D – U – A – SA
or
Strongly Disagree – Disagree – Undecided – Agree – Strongly Agree
⸻
Let me know if you’d like help designing your own Likert matrix properly formatted for print or online surveys!
Emotional vs cognitive response styles
Ah, thank you for that clarification — now it makes perfect sense! 🙌
Your notes are pointing out a subtle but important psychological distinction in how people express agreement on a Likert scale:
⸻
✅ Interpretation of Your Note:
“Strongly agree/disagree” = Emotional
“Completely or generally agree/disagree” = Cognitive
This means:
• When someone chooses “strongly agree” or “strongly disagree,”
👉 they’re likely responding with emotion — passion, frustration, conviction, etc.
• When someone chooses “completely agree” or “generally agree,”
👉 they’re likely expressing a more thought-based (cognitive) evaluation — reasoning, logic, or mild belief.
⸻
🧠 Why this matters:
• When you’re constructing or analyzing a scale, recognizing whether people are reacting emotionally or rationally can help you:
• Understand the depth of their attitudes
• See whether their support is emotionally driven or based on reason
• Tailor communication or interventions accordingly (e.g., policy vs. marketing)
⸻
🔍 Example:
Statement: “I support stricter environmental laws.”
Response Option Interpretation Type
Strongly agree “I feel very passionately about this.” Emotional
Completely agree “I logically think this is the right move.” Cognitive
Generally agree “I think it’s mostly a good idea.” Cognitive
Strongly disagree “This idea really upsets me.” Emotional
⸻
✅ Summary:
Response Style Reflects
Strongly agree / Strongly disagree Emotional intensity
Completely / Generally agree/disagree Cognitive judgment
⸻
Let me know if you’d like help designing a question set where you deliberately separate emotional and cognitive responses — it’s great for attitude surveys!
-
Intro19
-
Social Pathology22
-
Guide to community entry & Strategies in relating with communities45
-
Traditional Healthcare Practices And Pimary Health Care25
-
THE HOSPITAL AS A SOCIAL SYSTEM AND BUREAUCRACY IN HEALTH CARE24
-
Society And Culture32
-
GEM 2010
-
Gem 2010
-
Gem 20139
-
Health And Economic Development27
-
Questionnaire Development43
