diff --git a/02_activities/assignments/a1_sampling_and_reproducibility.ipynb b/02_activities/assignments/a1_sampling_and_reproducibility.ipynb index 11852458..ba4bcc00 100644 --- a/02_activities/assignments/a1_sampling_and_reproducibility.ipynb +++ b/02_activities/assignments/a1_sampling_and_reproducibility.ipynb @@ -16,7 +16,42 @@ "cell_type": "markdown", "id": "4ea73db3", "metadata": {}, - "source": [] + "source": [ + "Step 1: Setting Up the DataFrame\n", + "Function Used: pd.DataFrame\n", + "Sample Size: 1000 individuals\n", + "Sampling Frame: We are sampling from a population of 1000 individuals that will be attending either a wedding or a brunch\n", + "Procedure: the population structure is fixed\n", + "Underlying Distribution: none. This step defines the population\n", + "\n", + "Step 2: Infecting a Random Subset of Individuals\n", + "\n", + "Function Used: np.random.choice\n", + "Sample Size: 10% of the population (100 individuals), as defined by the ATTACK_RATE.\n", + "Sampling Frame: the 1000 individuals in the population\n", + "Procedure: we are randomily sampling without replacement our sampling frame of 10% individuals from the 1000 individuals. \n", + "Underlying Distribution: we are assuming that our mean distribution rate of infection will be around 10% of the 1000 individuals that will attend either the wedding or the brunch. \n", + " \n", + "Step 3: primary contact tracing and determining who gets traced.\n", + "Function Used: np.random.rand\n", + "Sample Size: ~20 for weddings and ~80 for brunch\n", + "Sampling Frame: the people that attended each event\n", + "Procedure: \n", + "Underlying Distribution: we are assuming that our mean distribution rate of infection will be around 20% of the people that attended the wedding and brunch event with slight variability around the mean\n", + "\n", + "Step 4: secondary contact tracing\n", + "Function Used: value_counts()\n", + "Sample Size: depends on if any event exceeds the set treshold\n", + "Sampling Frame: people at the events (weddings and brunches)\n", + "Procedure: Events with at least SECONDARY_TRACE_THRESHOLD = 2 traced cases are flagged and all infected individuals attending those events are subsequently marked as traced (cluster sampling)\n", + "\n", + "Step 5: Simulate event \n", + "Function Used: simulate_event(m)\n", + "Sample Size: 1000\n", + "Sampling Frame: all possible data points\n", + "Procedure: The entire model is rerun independently 1,000 times.\n", + "Underlying Distribution: hopefully normal distribution around the predicted mean occurence" + ] }, { "cell_type": "markdown", @@ -30,7 +65,24 @@ "cell_type": "markdown", "id": "4cf5d993", "metadata": {}, - "source": [] + "source": [ + "Here is a copy of the code that I modified.\n", + "Upon re-running the code multiple times, I noticed that the shape and distribution of the stimulated data kept changing everytime i ran the code. This means that the data could not be reproduced unless we set a random seed.\n", + "\n", + "for n_runs in [10, 100]:\n", + " results = [simulate_event(m) for m in range(n_runs)]\n", + " props_df = pd.DataFrame(results, columns=[\"Infections\", \"Traces\"])\n", + "\n", + " plt.figure(figsize=(10, 6))\n", + " sns.histplot(props_df['Infections'], alpha=0.75, color=\"blue\", kde=False, binwidth=0.05, label='Infections from Weddings')\n", + " sns.histplot(props_df['Traces'], alpha=0.75, color=\"red\", kde=False, binwidth=0.05, label='Traced to Weddings')\n", + " plt.title(f\"Simulation with {n_runs} repetitions\")\n", + " plt.xlabel(\"Proportion of cases\")\n", + " plt.ylabel(\"Frequency\")\n", + " plt.legend()\n", + " plt.tight_layout()\n", + " plt.show()" + ] }, { "cell_type": "markdown", @@ -44,7 +96,9 @@ "cell_type": "markdown", "id": "77613cc3", "metadata": {}, - "source": [] + "source": [ + "If you scroll to the end, I have repeated the code above in a code block but set a random seed to ensure reproduciilty of the data when run multiple times." + ] }, { "cell_type": "markdown", @@ -56,10 +110,21 @@ }, { "cell_type": "code", - "execution_count": null, + "execution_count": 1, "id": "ab8587a0", "metadata": {}, - "outputs": [], + "outputs": [ + { + "data": { + "image/png": "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", + "text/plain": [ + "
" + ] + }, + "metadata": {}, + "output_type": "display_data" + } + ], "source": [ "# Import necessary libraries\n", "import pandas as pd\n", @@ -107,13 +172,21 @@ " ppl['traced'] = ppl['traced'].astype(pd.BooleanDtype())\n", "\n", " # Infect a random subset of people\n", + " #THE TYPE OF SAMPLING TECHNIQUE USED FOR THE INFECTED_INDICES IS SIMPLE RANDOM SAMPLING WITHOUT REPLACEMENT WHERE WE EXAMINE 10% OF THE INDIVIDUALS (SAMPLE FRAME POPULATION) \n", + " #FROM THE POPULATION OF 1000 INDIVIDUALS (TARGET POPULATION)\n", + " #\n", " infected_indices = np.random.choice(ppl.index, size=int(len(ppl) * ATTACK_RATE), replace=False)\n", " ppl.loc[infected_indices, 'infected'] = True\n", "\n", + "\n", " # Primary contact tracing: randomly decide which infected people get traced\n", + "\n", + "\n", " ppl.loc[ppl['infected'], 'traced'] = np.random.rand(sum(ppl['infected'])) < TRACE_SUCCESS\n", "\n", " # Secondary contact tracing based on event attendance\n", + "\n", + "\n", " event_trace_counts = ppl[ppl['traced'] == True]['event'].value_counts()\n", " events_traced = event_trace_counts[event_trace_counts >= SECONDARY_TRACE_THRESHOLD].index\n", " ppl.loc[ppl['event'].isin(events_traced) & ppl['infected'], 'traced'] = True\n", @@ -136,8 +209,8 @@ "\n", "# Plotting the results\n", "plt.figure(figsize=(10, 6))\n", - "sns.histplot(props_df['Infections'], color=\"blue\", alpha=0.75, binwidth=0.05, kde=False, label='Infections from Weddings')\n", - "sns.histplot(props_df['Traces'], color=\"red\", alpha=0.75, binwidth=0.05, kde=False, label='Traced to Weddings')\n", + "sns.histplot(props_df['Infections'], alpha=0.75, color=\"blue\", binwidth=0.05, kde=False, label='Infections from Weddings')\n", + "sns.histplot(props_df['Traces'], alpha=0.75, color=\"red\", binwidth=0.05, kde=False, label='Traced to Weddings')\n", "plt.xlabel(\"Proportion of cases\")\n", "plt.ylabel(\"Frequency\")\n", "plt.title(\"Impact of Contact Tracing on Perceived Flu Infection Sources\")\n", @@ -146,6 +219,51 @@ "plt.show()" ] }, + { + "cell_type": "code", + "execution_count": 10, + "id": "1cff6c23", + "metadata": {}, + "outputs": [ + { + "data": { + "image/png": "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", + "text/plain": [ + "
" + ] + }, + "metadata": {}, + "output_type": "display_data" + }, + { + "data": { + "image/png": "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", + "text/plain": [ + "
" + ] + }, + "metadata": {}, + "output_type": "display_data" + } + ], + "source": [ + "#set random seed for reproducibility\n", + "np.random.seed(42) \n", + "for n_runs in [10, 100]:\n", + " results = [simulate_event(m) for m in range(n_runs)]\n", + " props_df = pd.DataFrame(results, columns=[\"Infections\", \"Traces\"])\n", + "\n", + " plt.figure(figsize=(10, 6))\n", + " sns.histplot(props_df['Infections'], alpha=0.75, color=\"blue\", kde=False, binwidth=0.05, label='Infections from Weddings')\n", + " sns.histplot(props_df['Traces'], alpha=0.75, color=\"red\", kde=False, binwidth=0.05, label='Traced to Weddings')\n", + " plt.title(f\"Simulation with {n_runs} repetitions\")\n", + " plt.xlabel(\"Proportion of cases\")\n", + " plt.ylabel(\"Frequency\")\n", + " plt.legend()\n", + " plt.tight_layout()\n", + " plt.show()\n" + ] + }, { "cell_type": "markdown", "id": "f418c720", @@ -193,7 +311,7 @@ ], "metadata": { "kernelspec": { - "display_name": "Python 3", + "display_name": "sampling-env", "language": "python", "name": "python3" }, @@ -207,7 +325,7 @@ "name": "python", "nbconvert_exporter": "python", "pygments_lexer": "ipython3", - "version": "3.13.0" + "version": "3.11.2" } }, "nbformat": 4, diff --git a/02_activities/assignments/a2_survey_design_and_evaluation.md b/02_activities/assignments/a2_survey_design_and_evaluation.md index a955d827..4c2509b1 100644 --- a/02_activities/assignments/a2_survey_design_and_evaluation.md +++ b/02_activities/assignments/a2_survey_design_and_evaluation.md @@ -21,7 +21,7 @@ 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 +1. Sample type : 2. Sample size 3. Target population 4. Sampling frame @@ -40,39 +40,63 @@ For the **Canadian General Social Survey on Giving, Volunteering, and Participat ## 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 the factors contributing to high turnover among entry and lower level employees at XYZ company. The survey aims to assess employee satisfaction, workplace experiences, and perceived opportunities for growth in order to identify areas for improvement. Findings will inform policy and organizational changes to improve retention and employee well-being. Describe your target population, sampling frame, sampling units, and observational units: -``` -write your answer here... -``` +Target Population is all the current entry and lower level employees at XYZ company, across all departments. +Sampling frame is XYZ company’s internal human resources employee database, containing all active employees classified as +entry- or lower-level staff. +Observational units are the individual employees +Sampling strategy: a sample of convinience strategy will be used where the survey is distributed through internal communication platforms, and annonymous participation is open to all eligible employees who choose to respond. This method is selected due to time constraints and the need for rapid feedback to address ongoing turnover issues. 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) +1. How satisfied are you with your current role at the company? (5 point likert scale from very satisfied to very dissatisfied) +2. How manageable is your current workload? (5 point likert scale from very Managable to very un manageable) +3. To what extent do you feel supported by your direct manager? (4 point likert scale from not at all to I feel very supported) +4. How satisfied are you with your compensation relative to your responsibilities? (5 point likert scale from very satisfied to very dissatisfied) +5. How satisfied are you with your benefits relative to your responsibilities? (5 point likert scale from very satisfied to very dissatisfied) +6. Do you think you have clear opportunities for growth or advancement within XYZ company? (Yes or No) +7.How would you describe the overall workplace culture in your department? (5 point likert scale from very negative to very positive) +8. Have you considered leaving the company within the past six months? (YES OR NO) +9. What factor(s) most influences your decision to stay or leave? __________ +10.What changes would most improve your job satisfaction? ___________ ``` ## Part B - Survey Evaluation: Identify and describe survey features: -``` -write your answer here -``` +1. Sample type: stratified sampling with 2 stage sampling design +2. Sample size: A field sample of approximatively 50,000 units was used. About 40,000 invitation letters to the electronic questionnaire were sent to selected households across Canada. A completion of 24,000 questionnaires was expected. +3. Target population: all persons 15 years of age and older living in the ten provinces of Canada. It excludes full-time (residing for more than six months) residents of institutions. +4. Sampling frame : they integrated multiple address and telephone sources (including landline and cell phone listings) to ensure households across provinces are represented and to include “cell phone only” respondents. This frame supports drawing a probability sample of eligible households. +5. Survey mode(s) : Telephone interviews and Online Web questionnaire +6. Timeline : From September to December 2018. +7. Response rate : the response rate for 2018 Giving, Volunteering and Participating was "Not available " according to page 13 on this document https://www150.statcan.gc.ca/n1/en/pub/89f0115x/89f0115x2019001-eng.pdf?st=VLdoCYYG. However, similar GSS cycles show response rates around 41.9% nationally. +8. Weights : WGHT_PER a basic weighting factor for analysis at the person level was used. Estimation weights and Bootstrap weights were also created for the purpose of design-based variance estimation. +9. Data processing : Processing used the SSPE set of generalized processing steps and utilities to allow subject matter and survey support staff to specify and run the processing of the survey in a timely fashion. The steps included Editing for consistency, CATI data capture program was used fof coding of responses to standardized categories, Validation checks were done by the head office and Confidentiality/anonymization for public use was also carried out. +10. Cleaning and imputation: imputations were made using donor imputation selected through a score function. It was carried out in nine steps. The first step consisted of imputing personal income and family income. The next three steps involved imputing the formal volunteering variables in the master file. Steps five and six were imputing the informal volunteering variables in the master file. Finally, the last three steps involved imputing variables in the donation file and the solicitation methods in the master file. +11. Sources of error : +Sampling error — due to drawing a sample rather than a census. +Non-response error — when selected participants do not respond. +Measurement error — misunderstanding of questions or misreporting. +Processing error — errors introduced during coding and data entry. +12. Limitations, known biases : +Potential response bias (e.g., volunteers may over-report participation) +Mixed-mode effects (differences between online and telephone responses) +Coverage limitations (excluded institutional residents) +Changes in question wording and mode may affect comparability with past cycles especially because the 2018 GSS GVP offered an Internet option to survey respondents for the first time. +13. Link to documentation and any additional sources used +https://www23.statcan.gc.ca/imdb/p2SV.pl?Function=getSurvey&Id=796234, +https://www150.statcan.gc.ca/n1/en/pub/89f0115x/89f0115x2019001-eng.pdf?st=VLdoCYYG, +https://www23.statcan.gc.ca/imdb/p2SV.pl?Function=getMainChange&Id=143876 +https://www150.statcan.gc.ca/n1/daily-quotidien/210126/dq210126h-eng.htm?, +https://www150.statcan.gc.ca/n1/en/catalogue/45250011. + ## Rubric