developing a questionnaire Flashcards

1
Q

what are the different methods of finding out information?

A

Patient Notes/Records review

Survey of staff (paper/online)

Survey of patients (paper/online)

Telephone interview

Face to face interviews

Focus groups

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
2
Q

what factors should you consider when collecting info?

A

logistics

anonymity

consent

cost

data protection rules

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
3
Q

wha is considered research?

A

A study which is trying to generate new knowledge about patients or conditions or healthcare services that will be generally true across a wider population than it is actually studying.

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
4
Q

how should you choose what categories you will use for your research?

A

Stick to standardised categories e.g. from the Office of National Statistics

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
5
Q

what are the different types of questions you can ask?

A
  1. simple yes no
  2. multiple choice- e.g. picking ethnicity
  3. ordinal/interval- asking on a scale
How well did you know this?
1
Not at all
2
3
4
5
Perfectly
6
Q

what is the likert scale good for assessing?

A

Knowledge

Beliefs

Attitudes

Symptoms

Traits

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
7
Q

what are assumptions made by the likert scale?

A
  • bipolar scale only assess positive or negative response to statement
  • assumes distance between each response is equal
  • multiple statements related to each other are posed and scores are summarised across statements to form a scale- all the items on the scale have equal weighting
How well did you know this?
1
Not at all
2
3
4
5
Perfectly
8
Q

what does it it mean if a statement is loaded with social desirability?

A

Social desirability bias is when the respondent provides an answer which is more socially acceptable than his / her true attitude or behaviour - the respondent may resist answering truthfully to something that is socially stigmatised such as finance or mental health

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
9
Q

likert scales should avoid statements based on 2 premises- what are examples of these?

A

“The doctor prescribed antidepressants and they have really helped”

“Because I had a healthy baby, I felt I did not have the right to struggle”

“I did not go to the doctor as I thought they would not listen”

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
10
Q

how can you avoid creating skew in responses to likert scale?

A

-use a spread of questions to represent every aspect of the concept being measured -Can word some statements in opposite direction – avoid repeat ticking down one column

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
11
Q

how can you score yes no responses?

A

1/0

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
12
Q

how can you score multiple category responses like ethnicity?

A

1 / 2 / 3 / 4 / 5 / 6 etc (Could be then ‘dummy’ coded to compare binary categories e.g. White (1) versus non- White (2 to 6 re-coded as 0))

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
13
Q

how to score multiple possible responses? - e.g. which of these sports do you play?

A

One column in spreadsheet for each sport. Then 1 / 0 for yes/no like binary categorical (Could also re-code: dummy coding for each sport, a count for number of sports, multi- category coding e.g. separate categories for combinations of responses such as running + cycling, running + swimming)

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
14
Q

how to score open ended questions?

A

sually no score – qualitative analysis (Could also code qualitative data and turn it into numerical data if wanted e.g. number of benefits identified

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
15
Q

how would you analyse a simple description “How much of X is there in this population?”

A

this would depend on the type of response given

  1. Yes / No variables

– count these up- Report number of respondents answering Yes and %

  1. Categories
    - Report N (frequency) and % in each group
  2. Likert scales
    - Add up scores across similar questions to make a scale (total score) Report mean total score and standard deviation
How well did you know this?
1
Not at all
2
3
4
5
Perfectly
16
Q

which analysis should you use when comparing yes no answers?

A

ci square

17
Q

which analysis to use when comparing 2 group responses on likert scale- e.g. men vs women

A

t test

18
Q

how can you quality control data entry?

A

anual double entry of data is defined as the definitive gold standard for transferring data to an electronic format

19
Q

how can you keep data secure?

A

Password protect database

Anonymise data entry

giving participants identity numbers

Paper copies stored in a locked drawer

20
Q

what is the best way to store data for analysis?

A

1. Excel

  • is spreadsheet software,

1. SPSS

  • is statistical analysis software.

In Excel, you can perform some Statistical analysis but SPSS is more powerful