HomeMy WebLinkAboutWORK ORDER - RFP - 7226 SURVEY SERVICES - MISC PUBLIC OPINION SURVEYS (2)EXHIBIT "A"
WORK ORDER FORM
PURSUANT TO AN AGREEMENT BETWEEN
THE CITY OF FORT COLLINS
Nv+tunul PSND tau7�n Lein �Pr
DATED: ! I
Work Order Number. i
Purchase Omer Number: Q%
Project Title: Ar-Qyrll Ssl;d War SuryPZFP/ 7.2z9)
Commencement Date: S-434.I
Completion Dam: q/Z 3/l!
Maximum Fee:(time and relmbursabie direct coats): �7f9�9lee-
Projectoescripnon: G74uct ci;r jual4ulsmlrri WD-0C— S--un2fA
� Q f'PS u i:s t papt'a Ce Dom}
Professional agrees to perform the services
identified above and on the attached forms In
accordance with the terms and conditions
contained herein and In the Professional Semces
Agreement between the parties. In the event of a
conflict between or ambiguity in the terms of the
Professional Services Agreement and this work
order (including the attached fors) the
Professional Services Agreement shall control.
The attached forms consisting of ExNbits
consisting of_ U pages are hereby accepted
and Incorporated herein, by this remrence, and
Notice to Proceed Is hereby given,
Professional
i
By: i
SONy/Y (yyT/NLfL/ Se Nic rt p5S4!/NlF
Dam: 5/ag/zou
City of Fort Collins
Submitted Byz
Pm act Manager
Date: S.; Cx 1 I
Reviewed by:
Approved by:
Approved by:
Director of Purchasing & Risk Management
(if over seum.)
Data:
P
T
P
J
U
O
V N
O
O
O
O
O
O
O
O
O
O
O
o
O
O
O
O
O
O
O
b
N
O
�
^
P
N
O
Sl
m
o
� o
�
o ,on
a^
o
0
0
0
0
0
0
0
0
0
0
0
o
n
o
a
W
'^
�
_
6
=
b
�
V
`a
O
o
d
d
o
a
m
a
o
0
6
d
e
c
p
O b
a
m
�
n
o
x
s
a
a
9
`o_
o>>
n`
S>>
v
o
v
jW
V1
a
v1
a
O
O
O
N
g
0
a
g
a
s
E
fL
d
w
m
v
a=
ni
u
.c
Y
j✓
N
N
N
m
b
P
b
Y
b
O
M
N
b
N
P
M
b
d
a\
b
J
V
W
O
c o
�
c o
0 0
M
w
o
0
0
0
0
0
0
0
0
0
0
0
o
N
o
Ci
O
p
O
O
O
O
O
O
O
O
O
m
�
Q
2
R
O
O
O
O
O
O
b
O
O
O
O
O
O
O
O
l0
N
N
I�
O
O
O
O
b
u
a
'o
c °
¢
o n
b9
�
R
P
x
a
v
m
d
d
a
v
c
o
0
i
o
o
n°
i
o
v
ao
s
c
c
2
c
z
«
c
d
d
¢
L
r
v
z
o
a
t
N
T q
d
O
d
O
°
O
B
r
_
�.'
�'n
jN
9v
G
gyp[
u
d
y
1/dl
J
W
O
d
d
O
O
O
d
d
1d'
N
E
At
.�
�
�o
a
00
�
|
$
°
,;!!!!!!2!`:!
!
y
--
�
�!!!
'
I
`/
��!!!!!!!!!«!
!!|�!!!
f)|.
..
!,
!_I!!l�..:;
±|!�!
_
{
!f|.°,
���!\\!!!!!!��
�..
§
,
'
�
/
!:_
!�!
,.
\
.,
:!!!!#l=;;,�!
!!!
�-�
)
}
)
)))\\\)|)�
�
!!�
!!!|;
i!!|
if
!
(ji�)||§|�))
�
�
_-
/\
(l,,l•!!!!!!})
|
\
)
\
r r City of Fort Collins Air Quality and Solid Waste Survey
Survey 1: 2011 Air Qualify/Solid Waste Survey
Task A: Project Initiation
It will be important to start this project with clear expectations, explicated barriers and incentives
that could motivate potential respondents and understood resources, including time and personnel.
We recommend, and note that the RFP requests, that we have a project initiation meeting to discuss
the overall scope of the project, and to begin refining the questions for the survey This meeting also
will serve to spell out the desired communication processes between NBC and the City of Fort
Collins for the duration of this project (e.g., points of contact, types and frequency of updates to be
provided throughout the project, intermediate timelines, etc.). Shortly after this meeting, we will
produce a timeline for the City that indicates project milestones and tasks, with dates. We have
provided a preliminary timeline in this proposal, but would work with the City to determine what
the important deadlines are, and craft a project schedule to meet the City's goals.
Task B: Choosing a Survey Administration Method
Based on NRC's experience and that of other leading researchers, we have created a table that
compares the strengths of various survey administration modes. A previous version of this table
was included in the book Citizen Surveys; How to do them, how to use them, what they mean (lCMA,
2000).
Comparison of administration methods for general population surveys"
have
Expense per completed survey
Moderately
expensive
Mail
Moderately
inexpensive
Web
Moderately
inexpensive*
Speed ofadministration
Moderately
fast
Moderately
slow
Moderately
fast
Typical response rate
Fair
Excellent
Poor
Ability to obtaining candid responses
Fair
Excellent
Excellent
Elimination of interviewer bias
Fair
Excellent
Excellent
Ability to get at in-depth topics
I Good
Good
Fair
Use of visual aids
Poor
Good
Good
Enforcement of question order
Excellent
Poor
Good
Inclusion of illiterate respondents
Good
Poor
Poor
Inclusion of young adults
Poor
Poor
Fair
Inclusion of respondents of lower socioeconomic status
Fair
Fair
Poor
Specifying sub -geographic locations (districts etc)
Poor
Excellent
Poor
® Authors/ Research center, Inc., 2011
Asa stand-alone data collection method with recruitment We mailed postcard, roe response rote for Web is surprisingly low The
large mailing size required to achieve the desired number of completes significantly increases the cost ofdals collection We
Web. Web is more economical wham paired with a mailed survey 1permiding responses via either mehod) or when a complete
list of email addresses is available for the population ofinterest as often is Me case for members of organizations.
Some of the advantages of a mailed survey, especially for sampling within geographic areas,
include:
• Mailed surveys garner higher response rates than phone surveys.
• Mailed surveys are more efficient for sampling within geographic boundaries. (Precise
household locations can be identified in advance.)
National Research Center, Inc.
r City of Fort Collins Air Quality and Solid Waste Survey
• Mailed surveys have less "coverage" error than phone surveys. (No loss of cell -phone only
households.)
• Mailed surveys are less expensive than phone surveys per completed interview.
• Mailed surveys elicit more candid responses than do phone surveys. In particular this is true for
questions that may be considered "sensitive" like crime victimization or participation in socially
un/desirable behaviors (such as making trips by driving alone), but even for service evaluation
questions.
• Mailed surveys permit more thoughtful responses than phone surveys.
• Mailed surveys will not disturb residents during their dinner hour (or any other time).
Advantages of phone surveys include:
• Faster completion of the study. (Time is not needed to print and mail the surveys, or wait for
surveys to be returned by mail.)
• Inclusion of residents who do not have facility with a written language.
• Greater credibility from stakeholders used to receiving poll data from telephone data
collection.
For this project, we would recommend mailed survey data collection because of it's advantages and
because it was the method used in the previous implementation in 2007. This will allow
comparisons over time without worries about differences due to mode effect Mailed surveys have a
lower cost while allowing for both more respondents and a longer survey; they have higher
response rates which reduces concerns about bias; they facilitate geographic comparisons (if
desired), they permit more efficient oversampling of populations who tend to respond at lower
rates (younger and lower income residents who are more likely to be in multi -unit housing) and
they engender more candid responses. The tasks outlined below and our cost estimate assumes a
mailed survey methodology; we are happy to provide information on conducting a telephone
survey, if desired.
Task 1: Development of Survey Questions
It is our experience that, to achieve the best results, time must be invested up -front to craft the right
survey instrument and to tie survey design to the overall goals and objectives of the project. We
regard the questionnaire development process as an iterative one, with drafts being reviewed and
revised by a project oversight committee or point person and our team.
NRC will work with the City to develop a comprehensive questionnaire that covers the objectives of
the study. The obvious starting point will be the 2007 survey instrument, but we have conducted a
number of air quality and solid waste surveys and can draw on our own library for example
surveys. If desired, we can also look for other similar questionnaires used for other jurisdictions.
We will work with the City so that we fully understand the use to which the data collected from this
effort will be put. NRC will ensure that each question is easily comprehended by respondents and
contributes to the overall analysis goals.
For a mailed survey, we would recommend that the survey be no longer than 5 pages in length, and
this is the assumption we have used in crafting our cost estimate.
Task 2: Sampling
Selecting survey recipients
In survey research, it is desirable for every household (or every adult person living in a household)
to have a known and equal chance of participating in the survey. A sample of all households is
selected to be given an opportunity to participate. Sampling is based on probability theory; the idea
National Research Center, Inc.
City of Fort Collins Air Quality and Solid Waste Survey
that if respondents are chosen randomly from the larger population, the results from that random
sample will be very close to what we would get by interviewing every member of the population.
The challenge is to find a list of all households from which survey recipients can be randomly
chosen. For a mailed survey, mailing lists exist from the United States Postal Office which include all
households with a mailing address.
All households located within the boundaries that define the City of Fort Collins, or whatever
boundaries the City determines are appropriate for this study, would be eligible for the survey. We
will geocode the location of each address to assure it is within the study boundaries (as well as any
desired subareas within the overall boundaries, if desired).
We will use systematic sampling from the list of eligible households to select the sample of
households, Systematic sampling is a procedure whereby a complete list of all possible addresses is
culled, selecting every Nth one until the appropriate number of households is sampled. Not only
will NBC scientifically and randomly sample households, but we also will select without bias the
household member to participate. In cases where more than one household member is 18 or older,
a procedure called "the birthday method" will be used to select the survey respondent without bias.
The birthday method requests that the respondent be the eligible adult in the household who most
recently had a birthday (irrespective of the year of birth). This methodology helps ensure the
attitudes expressed by our respondent "sample" closely approximate the attitudes of all adult
residents living in Fort Collins. Without this step in survey research, it is likely that results will be
biased towards those who are more sedentary and those without jobs (who may have different
opinions about some services).
Choosing the number of completed surveys ("sample size")
The relationship between sample size and precision of estimates (the 95% confidence interval or
margin of error) is shown in the adjacent table. The margin of error or 95% confidence interval is
determined solely by the number of completed
surveys, and not the size of the population from
which the sample is drawn, as long as the
"population' size is greater than about 4,000.
The table can be interpreted as follows: If 61% of
400 respondents said they would support a
mandatory vehicle emissions program in Fort
Collins even though it is not Federally required, we
can be confident that, had we gotten ratings from all
residents, somewhere between 56%and 66%would
haves rtd dt hi
Sample
SW
Margin of Error
(95% Confidence Interval)
100
±9,8%
zoo
±6.9%
400
±4.9%
Goo
±4.0%
Boo
±3.5%
a,zoo
±a.8%
z,000
ia.a%
uppo a man a ory ve c e emissions.
In the 2007 survey, surveys were sent to 1,500 households, from which 577 completed surveys
were returned. As response rates have been declining over time, we would recommend that
surveys be sent to 1,600 households, for a likely final completed sample size between 550 and 600,
which would provide a 95% confidence interval of plus or minus 4 percent.
Task 3: Survey Administration
Below is outlined our survey administration procedures. We encourage our clients to inform the
public about the survey through local newspapers, newsletters, community meetings and any other
appropriate media. The publicity provides an opportunity to inform them about the purposes of the
survey and the uses - for programming and policy- to which it will be put. The publicity,
furthermore, will assist the survey process by increasing willingness of potential respondents to
participate.
National Research Center, Inc.
City of Fort Collins Air Quality and Solid Waste Survey
Mailed Survey Data Collection
As described above, a sample of addresses from within Fort Collins will be selected to be part of the
survey. This database of addresses will be processed for certification and verification. NRC vendors
use CASS' /NCOA software that relies on the USPS National Directory information to verify and
standardize the address elements and assign each a complete, nine -digit zip code where possible. In
addition, the software will sort and barcode the addresses, allowing significant postage discounts.
We propose mailing all materials pre-sorted first class. This ensures a fast delivery time of the
materials, but provides an opportunity for a discount on the full first-class postage rates.
Our mailhouse will oversee the printing and preparation of the prenotification postcards, survey
packets and reminder postcards. As a part of the quality control process, proofs of the survey
materials are reviewed by NRC staff before the final job is printed. We will include a point person at
Fort Collins as a "seed" in the mailing list, so they will receive the mailing materials at the same time
as the sampled recipients.
We propose three contacts with each sampled household:
1) A prenotification announcement, informing the household members that they have been
selected to participate in the community survey will be sent to each household. This
announcement should be scheduled to arrive about a week before the survey packet.
2) Approximately one week after mailing the prenotification, each household would be mailed a
survey containing a cover letter (ideally signed by the mayor) enlisting participation. The
packet would also contain a postage paid return envelope that would send all completed
surveys directly for data entry.
3) A reminder letter and survey, will be scheduled to arrive 1 week after the first survey. The
second cover letter asks those who have not completed the survey to do so and those who have
already done so to refrain from turning in another survey. We mail the survey twice because
anonymity is promised in the cover letter to enhance the likelihood of honest responses. We
take this implicit contract with respondents as a serious principle of the survey trade, which, if
violated, harms the survey research industry no less than the client or respondent. We can also
check for duplicates if we include a survey code for later mapping of responses. Generally we
find only one or two duplicates in our responses.
When the survey administration mode has been chosen, a sample size selected and the survey
materials finalized, NRC will produce a memo for the City outlining the survey protocols and
containing the final survey materials.
Task 4: Data Tabulation
Survey processing
Mailed surveys will be returned to an NRC affiliate directly via postage -paid business reply
envelopes where staff will assign a unique identification number to each survey. Additionally, each
survey will be reviewed and "cleaned' as necessary. For example, a question may have asked a
respondent to pick two items out of a list of five, but the respondent checked three; NRC staff would
choose randomly two of the three selected items to be coded in the dataset. We have found that
very little cleaning is needed on most surveys due to our expertise in question construction and
survey formatting. However, extensive cleaning tends to be needed in surveys containing
complicated question structure or skip patterns.
Once all surveys have been assigned a unique identification number, they will be entered into an
electronic dataset This dataset will be subject to a data entry protocol of "key and verify," in which
survey data are entered twice into an electronic dataset and then compared. Discrepancies are
National Research Center, Inc.
City of Fort Collins Air Quality and Solid Waste Survey
evaluated against the original survey form and corrected. Range checks as well as other forms of
quality control will also be performed.
Weighting the Data
The last step in preparing the data for analysis is to weight the data to reflect the demographic
profile of the Fort Collins population. Weighting is an important method to adjust for potential non -
response bias. In general, residents with certain characteristics (for example: those who are
younger or rent their homes) are less likely to participate in surveying, whatever the data collection
mode. Weighting allows us to look at the demographic profile of residents who returned the survey
compared with the US Census profile. We consider these disparities along with others and
accordingly increase or decrease the weight of each respondent to mimic as closely as possible the
population demographics. The weighting variables to be considered will be all those demographics
included on the survey, as well as any geographic variable used for sampling. NRC has extensive
experience with complex weighting schemes required with stratification. if the 2007 survey data
are available in a useable format, we will weight those data as well to enable meaningful
comparison to the most recent past survey.
Basics of Data Analysis and Reporting
It is paramount that the result of this study be more than a nice looking report that sits on a shelf,
and as such we will work with the City of Fort Collins to ensure that we ask the right questions to
feed into an actionable analysis plan.
For quantitative analysis, we rely on the Statistical Package for the Social Sciences (SPSS). We
believe that analysis must be replicable and leave a clear path. To this end, we keep every label and
command run in SPSS in a syntax file available for audit and re -running as necessary. We also have
trained clients on SPSS analysis and, for small recurring analyses, how to use Microsofts Excel.
We will code open-ended responses using both an emergent approach, where themes are revealed
through the analysis, combined with a deductive approach, where a scheme or codes are
predetermined and applied to the data. Techniques include word counts, content analysis,
comparative analysis, componential analysis and taxonomic analysis, among others and codes are
applied based on the unit of analysis. Our qualitative analysis of verbatim responses will be done
using Microsoft® Access, Microsoft® Excel or QSR qualitative software, depending on the types and
complexity of the open-ended questions.
The data and report will undergo a thorough quality assurance review. We will audit the original
data files, our syntax/analysis files, compare automatically generated output to the formatted
output in the report and data check all numbers and text prior to submitting the report
We will provide basic descriptive statistics such as frequencies and means summarizing the
responses to the survey questions. If it makes sense to create scales or indices that summarize
information from a number of survey items, we can use factor analysis and other psychometric
testing to create valid factors. Additionally, NRC staff often have employed other advanced data
analysis techniques to transportation survey findings to determine what the key drivers of
respondent satisfactions are (using linear or logistic regression to demonstrate the factors that are
most important in respondent satisfaction), cluster analysis (market segmentation) to identify
groupings of respondents whose members share characteristics but whose clusters differ in
important way. For example, in a study we did for the Regional Air Quality Council on ground level
ozone pollution, we found there were four clusters or segments of the population in regards to
attitudes towards and behaviors to ameliorate ground level ozone, ranging from the "Negative
National Research Center, Inc.
r r City of Fort Collins Air Quality and Solid Waste Survey
Normans"(comprising 12%of the population) who did not feel ground level ozone was a problem
and were unlikely to make any behavior changes to decrease ground level ozone to'"rhe Eager'
(comprising 22% of the population) who reported already making lifestyle changes to reduce
ground -level ozone pollution and who were ready to be influenced to change behavior.
Upon completion of the data analysis, NRC can provide an electronic copy of the dataset to the City
of Fort Collins in a variety of formats. Typically, clients prefer to receive the data as an Excel
worksheet, but we can also provide an ASCII dataset, an Access dataset, or an SPSS dataset. We will
provide information about the layout and value labels of the data so that you will have no trouble
accessing the raw data. As a note of caution: while we can provide the dataset in Excel, including the
appropriate weight for each case, applying the weights in Excel is quite difficult. SPSS or another
statistical application may be required to apply the statistical weights and derive the identical
results to what would be displayed in the report of results.
However, we keep all the data files on our own server, and will be happy to run additional
crosstabulations for you (at no additional cost) as questions come up as you use and disseminate
the report.
Task 5: Reporting the Results
Report of Results
NRC understands that most readers want to understand the broader patterns and interpretations of
data, so our professionally designed graphics are engaging and pop with clear information. Our
reports are comprehensive and include technical and detailed numbers and information, but not at
the expense of the day-to-day usefulness of the documents. We are careful about our
communication. You will not need a degree in statistics to understand the survey results. All the
technical details are in appendices for those who wish to read them (and so that the survey can be
repeated by any vendor you choose), but we make sure the report body tells the story of the survey
results in a stylish, colorful, informative way. For further ease, we also include an executive
summary that gives a quick overview of results while highlighting key findings. We will prepare the
report in Microsoft® Word (as well as convert documents into a PDF format).
Drafts of the report will be provided to the City and the final report will incorporate any comments
we receive from you. We will meet with you to review the draft report, and answer any questions or
comments you have.
We will provide an electronic copy of the report in Microsoft Office Word® format along with a
version in PDF format (readable by Adobe Acrobat). We will also provide a hard copy of the report.
Recommendations
In order to best use the resources available for this project, we are proposing not to provide
recommendations, but to devote the resources to conducting the research and analyzing the results.
Our expertise is in research methods, analysis and facilitation.
The best recommendations are likely to come from the City's own review and discussion of the
results. For an extra cost, we could provide a half day "next steps" workshop, facilitated by Dr.
Miller. In this workshop, he will work with up to 20 key staff, elected officials and/or resident
decision -leaders to describe survey results and to plan for next steps that the City of Fort Collins
should take. The workshop will result in identification of key findings and an action plan for moving
forward with each. The cost of such a workshop is $1,800.
National Research Center, Inc.
4 City of Fort Collins Air Quality and Solid Waste Survey
Consulting and Continued Support
We know that an effective report will be reviewed and discussed by many people in Fort Collins
after we have completed the survey projects, and that new questions may arise. We commit to
supporting these discussions by offering crosstabulations and other additional analyses of results
when needed. And, though we will not abandon you with your data, we always will provide you
with the electronic dataset of your responses for your future reference and use.
National Research Center, Inc.
r r City of Fort Collins Air Quality and Solid Waste Survey
Survey 1: 2011 Air Quality/Solid Waste Survey
Task A: Project Initiation
[twill be important to start this project with clear expectations, explicated harriers and incentives
that could motivate potential respondents and understood resources, including time and personnel.
We recommend, and note that the RFP requests, that we have a project initiation meeting to discuss
the overall scope of the project, and to begin refining the questions for the survey This meeting also
will serve to spell out the desired communication processes between NRC and the City of Fort
Collins for the duration of this project (e.g., points of contact, types and frequency of updates to be
provided throughout the project, intermediate timelines, etc.). Shortly after this meeting we will
produce a timeline for the City that indicates project milestones and tasks, with dates. We have
provided a preliminary timeline in this proposal, but would work with the City to determine what
the important deadlines are, and craft a project schedule to meet the Cityrs goals.
Task B: Choosing a Survey Administration Method
Based on NRC's experience and that of other leading researchers, we have created a table that
compares the strengths of various survey administration modes. A previous version of this table
was included in the book Citizen Surveys; How to do them, how to use them, what they mean (fCMA,
2000).
Comparison of administration methods for general population surveys"
Expense per completed survey
Moderately
expensive
Moderately
Inexpensive
Moderately
•Inexpensive*
Speed of administration
Moderately
fast
Moderately
slow
Moderately
fast
Typical response rate
Fair
Excellent
Poor
Ability to obtaining candid responses
Fair
Excellent
Excellent
Elimination of Interviewer bias
Fair
Excellent
Excellent
Ability to get at in-depth topics
Good
Good
Fair
Use of visual aids
Poor
I Good
Good
Enforcement of question order
Excellent
I Poor
Good
Inclusion of illiterate respondents
Good
Poor
Poor
Inclusion of young adults
Poor
Poor
Fair
Inclusion of respondents of lower socioeconomic status I
Fair
Fair
Poor
Specifying sub -geographic locations (districts etc)
Poor
Excellent
Poor
®Nalsmal ReseamN center, Inc, 2011
As a Stan -alone data collecdan method will mcrultment vie mailed postcard, the response late M web is surprlsirply b .. The
Mtge mailing slm requlmdfo achieve the deslmd number arcompletes significantly imaeases the cost or date crol iftin We
Web. Web u more economical when pelretl with a maim survey (parmittbp resporwes Wa eifhermeMod) or when a complete
fist otemall addresses is available torthe population of mmmst as 'tan is the case farmeessim aorgansusions.
Some of the advantages of a mailed survey, especially for sampling within geographic areas,
include:
• Mailed surveys garner higher response rates than phone surveys.
• Mailed surveys are more efficient for sampling within geographic boundaries. (Precise
household locations can be identified in advance.)
National Research Center, Inc.
City of Fort Collins Air Quality and Solid Waste Survey
Proposed Time line
This timeline has a 4 month project length; this can be compressed or expanded, if needed.
Task
Contract awarded
Finalize prenotification
Date
.................. I...... May 23, 2011
1 week of contract signing
...................................... week 3
Other survey materials and questionnaire finalized.....................................................................................week
4
Mail prenotification postcard..................................................................................................................................
week4
Mail first wave survey................................................................................................................................................week
5
Mail second wave of surveys...................................................................................................................................
week 6
Allow surveys to be returned..............................................................................................................................
week 10
Electronicdata entry ..............................................................................................................................through
week 11
Data analysis and report writing.......................................................................................................through
week 14
Draft report for review by City............................................................................................................................
week 14
Review by City, meeting with NRC...................................................................................................through
week 16
Final report and letter delivered........................................................................................................................
week 17
National Research Center, Inc.
t City of Fort Collins Air Quality and Solid Waste Survey
• Mailed surveys have less "coverage" error than phone surveys. (No loss of cell -phone only
households.)
• Mailed surveys are less expensive than phone surveys per completed interview.
• Mailed surveys elicit more candid responses than do phone surveys. In particular this is true for
questions that may be considered "sensitive" like crime victimization or participation in socially
un/desirable behaviors (such as making trips by driving alone), but even for service evaluation
questions.
• Mailed surveys permit more thoughtful responses than phone surveys.
• Mailed surveys will not disturb residents during their dinner hour (or any other time).
Advantages of phone surveys include:
• Faster completion of the study. (Time is not needed to print and mail the surveys, or wait for
surveys to be returned by mail.)
• Inclusion of residents who do not have facility with a written language.
• Greater credibility from stakeholders used to receiving poll data from telephone data
collection.
For this project, we would recommend mailed survey data collection because of it's advantages and
because it was the method used in the previous implementation in 2007. This will allow
comparisons over time without worries about differences due to mode effect. Mailed surveys have a
lower cost while allowing for both more respondents and a longer survey; they have higher
response rates which reduces concerns about bias; they facilitate geographic comparisons (if
desired), they permit more efficient oversampling of populations who tend to respond at lower
rates (younger and lower income residents who are more likely to be in multi -unit housing) and
they engender more candid responses. The tasks outlined below and our cost estimate assumes a
mailed survey methodology; we are happy to provide information on conducting a telephone
survey, if desired.
Task 1: Development of Survey Questions
It is our experience that, to achieve the best results, time must be invested up -front to craft the right
survey instrument and to tie survey design to the overall goals and objectives of the project We
regard the questionnaire development process as an iterative one, with drafts being reviewed and
revised by a project oversight committee or point person and our team.
NRC will work with the City to develop a comprehensive questionnaire that covers the objectives of
the study. The obvious starting point will be the 2007 survey instrument, but we have conducted a
number of air quality and solid waste surveys and can draw on our own library for example
surveys. If desired, we can also look for other similar questionnaires used for other jurisdictions.
We will work with the City so that we fully understand the use to which the data collected from this
effort will be put. NRC will ensure that each question is easily comprehended by respondents and
contributes to the overall analysis goals.
For a mailed survey, we would recommend that the survey be no longer than 5 pages in length, and
this is the assumption we have used in crafting our cost estimate.
Task 2: Sampling
Selecting survey recipients
In survey research, it is desirable for every household (or every adult person living in a household)
to have a known and equal chance of participating in the survey. A sample of all households is
selected to be given an opportunity to participate. Sampling is based on probability theory; the idea
National Research Center, Inc.
s City of Fort Collins Air Quality and Solid Waste Survey
that if respondents are chosen randomly from the larger population, the results from that random
sample will be very close to what we would get by interviewing every member of the population.
The challenge is to find a list of all households from which survey recipients can be randomly
chosen. For a mailed survey, mailing lists exist from the United States Postal Office which include all
households with a mailing address.
All households located within the boundaries that define the City of Fort Collins, or whatever
boundaries the City determines are appropriate for this study, would be eligible for the survey. We
Will geocode the location of each address to assure it is within the study boundaries (as well as any
desired subareas within the overall boundaries, if desired).
We will use systematic sampling from the list of eligible households to select the sample of
households. Systematic sampling is a procedure whereby a complete list of all possible addresses is
culled, selecting every Nth one until the appropriate number of households is sampled. Not only
will NRC scientifically and randomly sample households, but we also will select without bias the
household member to participate. In cases where more than one household member is 18 or older,
a procedure called "the birthday method" will be used to select the survey respondent without bias.
The birthday method requests that the respondent be the eligible adult in the household who most
recently had a birthday (irrespective of the year of birth). This methodology helps ensure the
attitudes expressed by our respondent "sample" closely approximate the attitudes of all adult
residents living in Fort Collins. Without this step in survey research, it is likely that results will be
biased towards those who are more sedentary and those without jobs (who may have different
opinions about some services).
Choosing the number of completed surveys ("sample size")
The relationship between sample size and precision of estimates (the 95%confidence interval or
margin of error) is shown in the adjacent table. The margin of error or 95%confidence interval is
determined solely by the number of completed
surveys, and not the size of the population from
which the sample is drawn, as long as the
"population" size is greater than about 4,000.
The table can be interpreted as follows: If 61%of
400 respondents said they would support a
mandatory vehicle emissions program in Fort
Collins even though it is not Federally required, we
can be confident that, had we gotten ratings from all
residents, somewhere between 56%and 66%would
have supported mandatory vehicle emissions.
In the 2007 survey, surveys were sent to 1,500 households, from which 577 completed surveys
were returned. As response rates have been declining over time, we would recommend that
surveys be sent to 1,600 households, for a likely final completed sample size between 550 and 600,
which would provide a 95%conndence interval of plus or minus 4 percent.
Task 3: Survey Administration
Below is outlined our survey administration procedures. We encourage our clients to inform the
public about the survey through local newspapers, newsletters, community meetings and any other
appropriate media. The publicity provides an opportunity to inform them about the purposes of the
survey and the uses - for programming and policy- to which it will be put The publicity,
furthermore, will assist the survey process by increasing willingness of potential respondents to
participate.
National Research Center. Inc.
t City of Fort Collins Air Quality and Solid Waste Survey
Mailed Survey Do to Collection
As described above, a sample of addresses from within Fort Collins will be selected to be part of the
survey. This database of addresses will be processed for certification and verification. NRC vendors
use CASS-/NCOA software that relies on the USPS National Directory information to verify and
standardize the address elements and assign each a complete, nine -digit zip code where possible. In
addition, the software will sort and barcode the addresses, allowing significant postage discounts.
We propose mailing all materials pre-sorted first class. This ensures a fast delivery time ofthe
materials, but provides an opportunity for a discount on the full first-class postage rates.
Our mailhouse will oversee the printing and preparation of the prenotification postcards, survey
packets and reminder postcards. As a part of the quality control process, proofs of the survey
materials are reviewed by NRC staff before the final job is printed We will include a point person at
Fort Collins as a "seed" in the mailing list, so they will receive the mailing materials at the same time
as the sampled recipients.
We propose three contacts with each sampled household:
1) A prenotification announcement, informing the household members that they have been
selected to participate in the community survey will be sent to each household. This
announcement should be scheduled to arrive about a week before the survey packet
2) Approximately one week after mailing the prenotification, each household would be mailed a
survey containing a cover letter (ideally signed by the mayor) enlisting participation. The
packet would also contain a postage paid return envelope that would send all completed
surveys directly for data entry.
3) A reminder letter and survey, will be scheduled to arrive 1 week after the first survey. The
second cover letter asks those who have not completed the survey to do so and those who have
already done so to refrain from turning in another survey. We mail the survey twice because
anonymity is promised in the cover letter to enhance the likelihood of honest responses. We
take this implicit contract with respondents as a serious principle of the survey trade, which, if
violated, harms the survey research industry no less than the client or respondent We can also
check for duplicates if we include a survey code for later mapping of responses. Generally we
find only one or two duplicates in our responses.
When the survey administration mode has been chosen, a sample size selected, and the survey
materials finalized, NRC will produce a memo for the City outlining the survey protocols and
containing the final survey materials.
Task 4: Data Tabulation
Survey processing
Mailed surveys will be returned to an NRC affiliate directly via postage -paid business reply
envelopes where staff will assign a unique identification number to each survey. Additionally;Each
survey will be reviewed and "cleaned" as necessary. For example, a question may have asked a
respondent to pick two items out of a list of five, but the respondent checked three; NRC staff would
choose randomly two of the three selected items to be coded in the dataset. We have found that
very little cleaning is needed on most surveys due to our expertise in question construction and
survey formatting. However, extensive cleaning tends to be needed in surveys containing
complicated question structure or skip patterns.
Once all surveys have been assigned a unique identification number, they will be entered into an
electronic dataset This dataset will be subject to a data entry protocol of"key and verify," in which
survey data are entered twice into an electronic dataset and then compared. Discrepancies are
Notlorwl Research Center, Inc.
t t City of Fort Collins Air Quality and Solid Waste Survey
evaluated against the original survey form and corrected. Range checks as well as other forms of
quality control will also be performed.
Weighting the Data
The last step in preparing the data for analysis is to weight the data to reflect the demographic
profile of the Fort Collins population. Weighting is an important method to adjust for potential non -
response bias. In general, residents with certain characteristics (for example: those who are
younger or rent their homes) are less likelyto participate in surveying, whatever the data collection
mode. Weighting allows us to look at the demographic profile of residents who returned the survey
compared with the US Census profile. We consider these disparities along with others and
accordingly increase or decrease the weight of each respondent to mimic as closely as possible the
population demographics. The weighting variables to be considered will be all those demographics
included on the survey, as well as any geographic variable used for sampling. NBC has extensive
experience with complex weighting schemes required with stratification. If the 2007 survey data
are available in a useable format, we will weight those data as well to enable meaningful
comparison to the most recent past survey.
Basics of Data Analysis and Reporting
It is paramount that the result of this study be more than a nice looking report that sits on a shelf,
and as such we will work with the City of Fort Collins to ensure that we ask the right questions to
feed into an actionable analysis plan.
For quantitative analysis, we rely on the Statistical Package for the Social Sciences (SPSS). We
believe that analysis must be replicable and leave a clear path. To this end, we keep every label and
command run in SPSS In a syntax file available for audit and re -running, as necessary. We also have
trained clients on SPSS analysis and, for small recurring analyses, how to use Microsoft® Excel.
We will code open-ended responses using both an emergent approach, where themes are revealed
through the analysis, combined with a deductive approach, where a scheme or codes are
predetermined and applied to the data. Techniques include word counts, content analysis,
comparative analysis, componential analysis and taxonomic analysis, among others and codes are
applied based on the unit of analysis. Our qualitative analysis of verbatim responses will be done
using Microsoft® Access, Microsoft® Excel or QSR qualitative software, depending on the types and
complexity of the open-ended questions.
The data and report will undergo a thorough quality assurance review. We will audit the original
data files, our syntax/analysis files, compare automatically generated output to the formatted
output in the report and data check all numbers and text prior to submitting the report.
We will provide basic descriptive statistics such as frequencies and means summarizing the
responses to the survey questions. If it makes sense to create scales or indices that summarize
information from a number of survey items, we can use factor analysis and other psychometric
testing to create valid factors. Additionally, NBC staff often have employed other advanced data
analysis techniques to transportation survey findings to determine what the key drivers of
respondent satisfactions are (using linear or logistic regression to demonstrate the factors that are
most important in respondent satisfaction), cluster analysis (market segmentation) to identify
groupings of respondents whose members share characteristics but whose clusters differ in
important way. For example, in a study we did for the Regional Air Quality Council on ground level
ozone pollution, we found there were four clusters or segments of the population in regards to
attitudes towards and behaviors to ameliorate ground level ozone, ranging from the "Negative
National Research Center, Inc.
r r City of Fort Collins Air Quality and Solid Waste Survey
Normans"(comprising 12% of the population) who did not feel ground level ozone was a problem
and were unlikely to make any behavior changes to decrease ground level ozone to "The Eager"
(comprising 22%of the population) who reported already making lifestyle changes to reduce
ground -level ozone pollution and who were ready to be influenced to change behavior,
Upon completion of the data analysis, NRC can provide an electronic copy of the dataset to the City
of Fort Collins in a variety of formats. Typically, clients prefer to receive the data as an Excel
worksheet, but we can also provide an ASCII dataset, an Access dataset, or an SPSS dataset. We will
provide information about the layout and value labels of the data so that you will have no trouble
accessing the raw data. As a note of caution: while we can provide the dataset in Excel, including the
appropriate weight for each case, applying the weights in Excel is quite difficult SPSS or another
statistical application may be required to apply the statistical weights and derive the identical
results to what would be displayed in the report of results.
However, we keep all the data files on our own server, and will be happy to run additional
crosstabulations for you (at no additional cost) as questions come up as you use and disseminate
the report.
Task 5: Reporting the Results
Report of Results
NRC understands that most readers want to understand the broader patterns and interpretations of
data, so our professionally designed graphics are engaging and pop with clear information, Our
reports are comprehensive and include technical and detailed numbers and information, but not at
the expense of the day-to-day usefulness of the documents. We are careful about our
communication. You will not need a degree in statistics to understand the survey results. All the
technical details are in appendices for those who wish to read them (and so that the survey can be
repeated by any vendor you choose), but we make sure the report body tells the story of the survey
results in a stylish, colorful, informative way. For further ease, we also include an executive
summary that gives a quick overview of results while highlighting key findings. We will prepare the
report in Microsoft® Word (as well as convert documents into a PDF format).
Drafts of the report will be provided to the City and the final report will incorporate any comments
we receive from you. We will meet with you to review the draft report, and answer any questions or
comments you have.
We will provide an electronic copy of the report in Microsoft Office Word® format along with a
version in PDF format (readable by Adobe Acrobat). We will also provide a hard copy of the report,
Recommendations
In order to best use the resources available for this project, we are proposing not to provide
recommendations, but to devote the resources to conducting the research and analyzing the results.
Our expertise is in research methods, analysis and facilitation.
The best recommendations are likely to come from the City's own review and discussion of the
results. For an extra cost, we could provide a half day "next steps" workshop, facilitated by Dr.
Miller. In this workshop, he will work with up to 20 key staff, elected officials and/or resident
decision -leaders to describe survey results and to plan for next steps that the City of Fort Collins
should take. The workshop will result in identification of key findings and an action plan for moving
forward with each. The cost of such a workshop is $1,800.
National Research Center, Inc.
MMMMMr r �Clty.f Fort Collins Air Quality and Solid Waste Survey
Consulting and Continued Support
We know that an effective report will be reviewed and discussed by many people in Fort Collins
after we have completed the survey projects, and that new questions may arise. We commit to
supporting these discussions by offering crosstabulations and other additional analyses of results
when needed. And, though we will not abandon you with your data, we always will provide you
with the electronic dataset of your responses for your future reference and use.
Notional Reseorch Center, Inc.
r Clty of Fort Collins Air Quality and Solid Waste Survey
Proposed Time line
This timeline has a 4 month project length; this can be compressed or expanded, if needed.
Task
Date
Contractawarded .............................................. _.................. _...................
_.................... .............. ................ May 23, 2011
Kickoff meeting......................................................................................................
within 1 week of contract signing
Finalize prenotification postcard ...................................... _....................
..... __............. _....... .......... ..... ........ week 3
Other survey materials and questionnaire finalized ........ _....................
_...................... ._....................... week4
Mail prenotification postcard ....................................... _......... _..............................
_........... .................................. week4
Mailfirst wave survey............................... _....................................................................
...... _............ ........ ......... week 5
Mail second wave of surveys................................................................................_.._......_...................................
week 6
Allow surveys to be returned....................................................................._............._.._...................................
week 10
Electronic data entry ..........................................................................___..._.._......_..._........_.............through
week 11
Data analysis and report writing..............................................................
_... _.... _............................ through week 14
Draft report for review by City.................................... _.....................
_.............................................................. week 14
Review by City, meeting with NRC................................................. _
.......................... _.................. _through week 16
Final report and letter delivered ................................ _............................
__........... .......................................... week 17
Notlonal Research Center, Inc.