DHSC9035 Data Collection for Applied Research
Project
Study Descriptiona
Study purpose: To examine whether preventive care has an effect on developing Type II
diabetes.
Participants: 30 adults (18 – 65 years) who visit an urban medical clinic routinely
Study Design: Quantitative descriptive
Inclusion criteria:
Adults ages 18-65
HgA1c levels tested within the past 12 months
Exclusion criteria:
Children < 18 years and adults > 65 years of age
Individuals who have not had their HgA1c levels tested within the past 12 months
Methods: Participants were consecutively sampled who visited an urban medical clinic. The
admitting nurse reviewed the patient charts to determine whether the patients had their HgA1c
levels tested within the past year. Those meeting the inclusion criteria were asked if they would
be willing to participate in a brief survey. Upon agreement, they were asked to sign an informed
consent which was reviewed by the nurse.
Data collection: Upon signing the Informed Consent, participants completed the demographic
section and the 5-point Likert scale questions on the Preventive Care Survey.* Upon completion
of the brief survey, the admitting nurse completed the bottom portion of the survey instrument,
recording the participants' most recent height, weight, BP, and HgA1c levels, measured within
the past 12 months.
a
Mock study and survey created by Dr. Helen Salisbury, PhD
Preventive Care Surveya
Demographics
1) What is your age?
2) What is your sex?
3) Please indicate your income range:
< $20,000
$20,000-29,999
$30,000-39,999
$40,000-49,999
$50,000-59,999
$60,000-69,999
$70,000-79,999
$80,000-89,999
$90,000-99,999
> $100,000
Prefer not to answer
4) Please select your highest educational level attained:
High School
Community College Bachelor's
Master's
Doctorate
5) Race (select all that apply)
White/Caucasian
Black/African American
American Indian or Alaska Native
Asian
Native Hawaiian or Other Pacific Islander
Other (please specify)
Prefer not to answer
6) Have you accessed preventive services that are available through your provider?
Yes
No
7) If "no", please rank order the following reasons you have not taken advantage of the
preventive services available (if N/A, leave blank).
No insurance
Not covered by my insurance
Don't feel it's necessary
Takes too much time
Can't get out of work for appointments
Physician doesn't emphasize this/think it's necessary
a
Mock study and survey created by Dr. Helen Salisbury, PhD
Preventive Care
Please select the degree to which you agree or disagree with the following statements.
My healthcare provider:
Strongly
disagree
Disagree
Neither
agree nor
disagree
Somewhat
Agree
Strongly
Agree
8) recommends
annual preventive
visits
9) recommends
biometric lab tests
annually (e.g., lipid
profile, HbA1c)
10) recommends
imaging screenings
at appropriate
intervals
11) encourages me
to exercise for 30
minutes 2-3 times
per week
12) recommends I
drink alcohol
moderately
13) recommends I
stop smoking or don't
start
14) recommends I
wear protective
equipment when
engaging in sports
15) recommends I
follow a specific diet
(e.g., Atkins, Weight
Watchers,
Mediterranean)
16) recommends I
eat less red meat
17) recommends I
consume more fresh
fruit and vegetables
Thank you for completing this survey! Please do not write below the line.
______________________________________________________________________
a
Mock study and survey created by Dr. Helen Salisbury, PhD
To be completed by medical staff only:
HbA1c (latest test result within the past 12 months): ______%
Height (in inches): ______
Weight (in pounds): ______
SBP: ______
DBP: ______
a
Mock study and survey created by Dr. Helen Salisbury, PhD
Preventive Care & HbA1c Variable View Worksheet (A1)
Complete this SPSS® Variable View worksheet, ensuring every cell contains the appropriate alphanumeric response setting(s). Like a
puzzle, some information is provided for you already. You must fill in the remainder. The recommendation is that you complete this
worksheet prior to populating the Variable View tab in the assignment SPSS® dataset (PrevCare_HbA1c.sav).
Here are the SPSS® Variable View column headings, with brief definitions/explanations:
Name (variable name). These have been provided for you and should not be changed.
Type (e.g., numeric, date, string)
Width* (The default is 8. Adjust as appropriate.)
Decimals (The default is 2. Decimals are only needed if the collected data points should logically be carried out to decimals.)
Label (Keep labels brief but informative. Labels assist with interpreting your output.)
Values (Used with nominal and ordinal variables. Nominal variables will have numbers assigned to the categories and ordinal
variables will have numbers assigned to the rankings.)
Missing (Defines the numeric values that should be considered missing [e.g., -99] or out of range [e.g., -98])
Columns* (The default is 8. Adjust as appropriate.)
Align (Right is the default. You can adjust to your preferences, although consistency is advised.)
Measure (Scale is for interval/ratio variables; Ordinal for ordinal; Nominal for nominal. String variables ("text") are
automatically defined as nominal.)
Role (The default is Input. You can retain this setting for all of your variables.)
* Width vs. Columns: "Width" refers to the size of the variable. This should be set based on the largest size data point you are likely to
obtain for a given variable. If your responses can range from "1" to "150", for example, your width would be "3". If your responses
can range from "1.25" to "150.99", then you width would be "6". Decimals count as characters.
Columns are not the same as Width, although they can be equal. Columns will determine how much of the variable name and
accompanying data will be visible on the screen. For ease in "reading" your dataset, always be sure the full name of the variable is
visible in Data View. Avoid presenting your dataset in a "squashed" manner as this is difficult to read. Consistency is recommended
across your variables, though.
Name
Type
Width
Decimals
Label
Values
Missing
Columns
Align
Measure
Role
ID
Numeri
2
0
Preventive Care Survey
Participant ID #
None
None
8
Right
Nominal
Input
c
Age
Scale
Sex
Income
0 = Male
1 = Female
Numeri
-99
c
Income_a
Participant income:
Prefers not to answer
Educ
Race_a Race_f
0 = Not checked
1 = Checked
8
1
0
Race (White/Caucasian)
8
Input
Right
Nominal
Input
RaceOthr
String
Name
Type
Other participant race
(text)
Width
Decimals
Label
Values
Missing
Columns
Align
Measure
Role
RaceNoAn
Acc_Prev
NoPC_a NoPC_f
PC08 -
Numeri
PC17
c
PCTotal
HbA1c
0
1 = Strongly disagree
2 = Disagree
3 = Neither agree nor
disagree
4 = Agree
5 = Strongly agree
Total Preventive Care
Score (Max = 50)
8
Input
Right
Scale
TypeII
Name
Type
1
0
Width
Decimals
Height
0 = No diagnosis
1 = Pre-diabetes
2 = Type II diabetes
Label
Values
Missing
Participant height (in
inches)
Weight
6
2
Columns
Align
8
None
-999
SBP
DBP
Numeri
c
Diastolic blood pressure
(in mm Hg)
Right
Measure
Role
DHSC9035 Data Collection for Applied Research Project
SPSS Instructions for SPSS Part I – Purchase, Installation, and Dataset
Preparation
Steps to Creating the Codebook (i.e., data dictionary)
1. Complete the Variable View Worksheet (Preventive Care & HbA1c Worksheet.docx)
in preparation for completing the codebook in the SPSS® data file
(PrevCare_HbA1c.sav)
2. Once the Worksheet is complete, open the SPSS ® data file and click on the “Variable
View” tab to show the variable list. The Variable View is the codebook view in SPSS®.
3. Now complete the rows in the codebook using the completed Worksheet as a guide.
Steps to Locating and Assigning the Missing Data Code to All Missing Data
1. Click on the “Data View” tab in the SPSS® data file.
2. Review the data to locate and assign the missing data code (-99) for all missing data.
Missing Data
© 2015 – A.T. Still University – Last Updated: July 19
2014
1
SPSS Instructions for SPSS Part I – Purchase, Installation, and Dataset Preparation
DHSC9035 Data Collection for Applied Research Project
3. Now that all the missing data have been assigned the missing data code (i.e., -99), there
should be no blank cells in your data sheet. Then, be certain to add "-.99" (with no quotation
marks) as one of the “Missing” values in your codebook (Variable View) for that variable.
Otherwise, when you analyze your data, SPSS® will incorrectly treat "-99" as a valid entry. For
example, if you discover a blank cell for the variable “Age”, you would replace the missing
value with “-99” and then add “-99” to the “Missing” column in the “Age” row within the
codebook (Variable View).
© 2015 – A.T. Still University – Last Updated: July 19
2014
2
Preventive Care & HbA1c Variable View Worksheet (A1)
Complete this SPSS® Variable View worksheet, ensuring every cell contains the appropriate alphanumeric response setting(s). Like a
puzzle, some information is provided for you already. You must fill in the remainder. The recommendation is that you complete this
worksheet prior to populating the Variable View tab in the assignment SPSS® dataset (PrevCare_HbA1c.sav).
Here are the SPSS® Variable View column headings, with brief definitions/explanations:
Name (variable name). These have been provided for you and should not be changed.
Type (e.g., numeric, date, string)
Width* (The default is 8. Adjust as appropriate.)
Decimals (The default is 2. Decimals are only needed if the collected data points should logically be carried out to decimals.)
Label (Keep labels brief but informative. Labels assist with interpreting your output.)
Values (Used with nominal and ordinal variables. Nominal variables will have numbers assigned to the categories and ordinal
variables will have numbers assigned to the rankings.)
Missing (Defines the numeric values that should be considered missing [e.g., -99] or out of range [e.g., -98])
Columns* (The default is 8. Adjust as appropriate.)
Align (Right is the default. You can adjust to your preferences, although consistency is advised.)
Measure (Scale is for interval/ratio variables; Ordinal for ordinal; Nominal for nominal. String variables ("text") are
automatically defined as nominal.)
Role (The default is Input. You can retain this setting for all of your variables.)
* Width vs. Columns: "Width" refers to the size of the variable. This should be set based on the largest size data point you are likely to
obtain for a given variable. If your responses can range from "1" to "150", for example, your width would be "3". If your responses
can range from "1.25" to "150.99", then you width would be "6". Decimals count as characters.
Columns are not the same as Width, although they can be equal. Columns will determine how much of the variable name and
accompanying data will be visible on the screen. For ease in "reading" your dataset, always be sure the full name of the variable is
visible in Data View. Avoid presenting your dataset in a "squashed" manner as this is difficult to read. Consistency is recommended
across your variables, though.
Name
Type
Width
Decimals
Label
Values
Missing
Columns
Align
Measure
Role
ID
Numeric
2
0
Preventive Care Survey
Participant ID #
None
None
8
Right
Nominal
Input
Age
Numeric
8
2
N/A
None
None
8
Right
Scale
Input
Sex
Numeric
8
2
N/A
0 = Male
1 = Female
None
8
Right
Unknown
Input
Income
Numeric
8
2
N/A
None
-99
8
Right
Unknown
Input
Income_a
Numeric
8
2
Participant income:
Prefers not to answer
0 = Not checked
1 = Checked
None
8
Right
Unknown
Input
Educ
Numeric
8
2
N/A
None
None
8
Right
Unknown
Input
Race_a -
Numeric
1
0
Race
(White/Caucasian)
None
None
8
Right
Nominal
Input
8
2
8
0
Other participant race
(“please specify”)
None
None
8
Right
Unknown
Input
Race_f
RaceOthr
String
Name
Type
Width
Decimals
Label
Values
Missing
Columns
Align
Measure
Role
RaceNoAn
Numeric
8
2
N/A
None
None
8
Right
Unknown
Input
Acc_Prev
Numeric
8
2
N/A
None
None
8
Right
Unknown
Input
NoPC_a -
Numeric
8
2
N/A
None
None
8
Right
Unknown
Input
Numeric
8
0
N/A
None
8
Right
Unknown
Input
PCTotal
Numeric
8
2
Total Preventive Care
Score (Max = 50)
1 = Strongly
disagree
2 = Disagree
3 = Neither agree
nor disagree
4 = Agree
5 = Strongly agree
None
None
8
Right
Scale
Input
HbA1c
Numeric
8
2
N/A
None
None
8
Right
Unknown
Input
TypeII
Numeric
1
0
N/A
0 = No diagnosis
1 = Pre-diabetes
2 = Type II diabetes
None
8
Right
Unknown
Input
NoPC_f
PC08 PC17
Name
Type
Width
Decimals
Label
Values
Missing
Columns
Align
Measure
Role
Height
Numeric
8
2
Participant height (in
inches)
None
None
8
Right
Unknown
Input
Weight
Numeric
6
2
N/A
None
-999
8
Right
Unknown
Input
SBP
Numeric
8
2
N/A
None
None
8
Right
Unknown
Input
DBP
Numeric
8
2
Diastolic blood pressure
(in mm Hg)
None
None
8
Right
Unknown
Input
Purchase answer to see full
attachment