UofT-DSI | Sampling- Assignment 2

02_activities/assignments/a2_survey_design_and_evaluation.md

@@ -21,58 +21,202 @@ Select one of the scenarios below and design a survey to meet the need(s) outlin
 
 For the **Canadian General Social Survey on Giving, Volunteering, and Participating, 2018 (cycle 33)**, conducted by Statistics Canada find any and all available documentation for the data gathered and identify and describe the survey features indicated below.
 
-1. Sample type
-2. Sample size
-3. Target population
-4. Sampling frame
-5. Survey mode(s) 
-6. Timeline
-7. Response rate
-8. Weights
-9. Data processing
-10. Cleaning, imputation, etc
-11. Sources of error
-12. Limitations, known biases, etc
-13. Link to documentation and any additional sources used
 
+# Your Changes -
 
-# Your Changes
+## Part A - Survey Design:
 
-## Part A - Survey Design: 
-
-The number of your chosen topic: `#`
+The number of your chosen topic: `1`
 
 Describe the purpose of your survey:
-```
-write your answer here...
-```
+
+The purpose of my survey is to understand why the company across many of its departments is experiencing a high turnover rate, specifically in entry- and lower-level positions, and to help determine what changes are needed to stop this by improving employee satisfaction.
 
 Describe your target population, sampling frame, sampling units, and observational units:
-```
-write your answer here...
-```
+Target population: The target population consists of all currently employed entry- and lower-level employees across all departments at the company. In addition, a secondary but related population includes employees in entry- and lower-level positions who have submitted their resignation, who would be surveyed through a separate exit survey
+
+Sampling Frame: The sampling frame is the company’s Human Resources employee database, which contains a complete list of current employees, their job level, department, and work email address. For the exit survey, the sampling frame consists of employees who have formally notified HR of their resignation.
+
+Sampling units: The sampling units are individual employees classified as entry- or lower-level staff within each department. Each employee represents one unit of analysis.
+
+Sampling startegy: A cross-sectional survey design will be used. The survey will be distributed electronically via work email to all eligible entry- and lower-level employees, resulting in a census of the target population rather than a random sample. A separate cross-sectional exit survey will be administered to employees who are leaving the company. This approach allows the organization to capture a snapshot of employee experiences and perceptions related to job satisfaction and turnover at a single point in time. 
 
 Your 5-10 question survey:
-```
-1. write your question here...
-2. write your question here...
-3. write your question here...
-4. write your question here...
-5. write your question here...
-6. write your question here... (optional)
-7. write your question here... (optional)
-8. write your question here... (optional)
-9. write your question here... (optional)
-10. write your question here... (optional)
-```
+Current Employee Survey
+Company Culture & Communication
+1. How would you describe the overall company culture?
+a. Very positive
+b. Somewhat positive
+c. Neutral
+d. Somewhat negative
+e. Very negative
+
+2. Do you feel you are part of a diverse and inclusive work environment?
+a. Strongly agree
+b. Agree
+c. Neither agree nor disagree
+d. Disagree
+e. Strongly disagree
+
+3. How comfortable do you feel communicating concerns or feedback to your manager?
+a. Very comfortable
+b. Somewhat comfortable
+c. Neutral
+d. Somewhat uncomfortable
+e. Very uncomfortable
+
+Job Satisfaction & Growth
+4. Do your job responsibilities align with what you expected when you were hired?
+a. Very well aligned
+b. Somewhat aligned
+c. Neutral
+d. Somewhat misaligned
+e. Very misaligned
+
+5. How would you rate your current workload?
+a. Very manageable
+b. Somewhat manageable
+c. Neutral
+d. Somewhat unmanageable
+e. Very unmanageable
+
+6. Do you feel you have opportunities for professional development or career growth?
+a. Yes, many opportunities
+b. Yes, some opportunities
+c. Unsure
+d. Very few opportunities
+e. No opportunities
+
+Management & Compensation
+7. Do you feel supported by your direct manager?
+a. Strongly agree
+b. Agree
+c. Neither agree nor disagree
+d. Disagree
+e. Strongly disagree
+
+8. How satisfied are you with your compensation and benefits?
+a. Very satisfied
+b. Somewhat satisfied
+c. Neutral
+d. Somewhat dissatisfied
+e. Very dissatisfied
+
+9. What is one change the company could make to improve your overall job satisfaction?
+(Open text)
+
+
+Exit Employee Survey
+
+Reasons for Leaving
+1. What is the primary reason for leaving the company? (Select one)
+a. Compensation and benefits
+b. Lack of career growth opportunities
+c. Workload or burnout
+d. Management or leadership issues
+e. Company culture or values
+f. Work-life balance
+g. Role not aligned with expectations
+h. Personal reasons
+i. Other (please specify)
+
+2. Was there a specific event or factor that influenced your decision to leave?
+a. Yes
+b. No
+c. Not sure
+
+Company Culture & Environment
+3. How would you describe the overall company culture?
+a. Very positive
+b. Somewhat positive
+c. Neutral
+d. Somewhat negative
+e. Very negative
+
+4. Did you feel included and respected in the workplace?
+a. Strongly agree
+b. Agree
+c. Neither agree nor disagree
+d. Disagree
+e. Strongly disagree
+
+Job Satisfaction & Growth
+5. Did your job responsibilities align with your expectations?
+a. Very well aligned
+b. Somewhat aligned
+c. Neutral
+d. Somewhat misaligned
+e. Very misaligned
+
+6. Were you provided with adequate tools, resources, and training to succeed?
+a. Strongly agree
+b. Agree
+c. Neither agree nor disagree
+d. Disagree
+e. Strongly disagree
+
+7. Were there sufficient opportunities for professional development or career growth?
+a. Yes, many opportunities
+b. Yes, some opportunities
+c. Unsure
+d. Very few opportunities
+e. No opportunities
+
+Management & Compensation
+8. Did you feel supported by your direct manager?
+a. Strongly agree
+b. Agree
+c. Neither agree nor disagree
+d. Disagree
+e. Strongly disagree
+
+9. How satisfied were you with your compensation and benefits?
+a. Very satisfied
+b. Somewhat satisfied
+c. Neutral
+d. Somewhat dissatisfied
+e. Very dissatisfied
+
+10. What could the company have done to encourage you to stay?
+(Open text)
+
+
 
 ## Part B - Survey Evaluation:
 
-Identify and describe survey features:
+1. Sample type: This is a household-based probability sample. One eligible household member aged 15 or older was randomly selected from each sampled household. Proxy responses were not permitted.
+
+2. Sample size: A field sample of approximately 50,000 units was drawn. About 40,000 invitation letters were sent to selected households across Canada, with an expected completion of approximately 24,000 questionnaires.
+
+3. Target population: IThe target population includes all non-institutionalized persons aged 15 years and older living in the ten provinces of Canada. Full-time residents of institutions (those residing for more than six months) were excluded.
+
+4. Sampling frame: The sampling frame was created using linked sources, including the Census, administrative data, billing files, and Statistics Canada’s dwelling frame. The frame combined landline and cellular telephone numbers associated with household addresses. Households without telephone access were excluded, though coverage was improved compared to earlier random-digit-dialing methods.
+
+5. Survey mode(s): The General Social Survey (GSS) is a cross-sectional sample survey conducted every five years. Data were collected through telephone interviews and self-completed electronic questionnaires.
+
+The survey used a stratified probability sampling design. Stratification was conducted at the province and Census Metropolitan Area (CMA) level, resulting in 27 strata. A two-stage sampling design was used: groups of telephone numbers were selected first, followed by the selection of one eligible individual per household.
+
+To address the low prevalence of volunteers in the population, a rejective sampling approach was implemented. All respondents identified as volunteers completed a long interview. Non-volunteers were randomly assigned to either a long or short interview.
+
+6. Timeline: Reference period: past 12 months precending interview date, Collection Period: Every 5 years, from September to December
+
+7. Response rate: The overall response rate for the survey was 41.9%.
+
+8. Weights: Person-level survey weights (WGHT_PER) were provided to produce population estimates. Bootstrap weights were also created and used for design-based variance estimation. Survey estimates were weighted to represent the entire target population, including individuals not fully covered by the sampling frame.
+
+9. Data processing: Extensive quality assurance procedures were applied, including validation through cross-tabulations, analysis of changes over time, and comparison with similar data sources. Despite these measures, the data remain subject to both sampling and non-sampling error. Sampling variability was estimated using the bootstrap method.
+
+10. Cleaning, imputation, etc : Missing data were primarily addressed using donor imputation based on a score function that matched recipients with similar donor records. When donor imputation was not possible, mean imputation was used. Imputation occurred in multiple stages, including income, volunteering, donation, and solicitation variables.
+
+For the 2018 GSS, personal income data were obtained through linkage with respondents’ 2017 tax records (T1FF), with missing values imputed as needed.
+
+11. Sources of error: Sampling error arises from using a sample rather than a census and was estimated using bootstrap weights. Non-sampling errors include coverage error, non-response, response error, and processing error. Survey weights were adjusted to account for non-response at both the household and individual levels.
+
+12. Limitations, known biases, etc: Potential biases stem from incomplete coverage (e.g., households without telephones) and non-response. To mitigate non-response bias, survey weights were adjusted using administrative data on income and household composition. While these adjustments reduced bias, some residual bias may remain.
 
-```
-write your answer here
-```
+13. Link to documentation and any additional sources used: 
+Information found here: https://www23.statcan.gc.ca/imdb/p2SV.pl?Function=getSurvVariableList&Id=796234&wbdisable=true
+https://www23.statcan.gc.ca/imdb/p2SV.pl?Function=getSurvey&Id=796234
 
 ## Rubric