Welcome to Stat Village
A statistical laboratory to enhance learning of application of statistics in research

[Final DO file] [Age and BMI DO file] [Data Wave 1-3]

Instructions:
    
     There are 6 Steps to follow. Steps 1 and 2 should be completed before attending the class. That is, 34 pieces of papers must be ready. These include an A4-size paper of the Random Number Table, an A4-size of the Annotated_StatVill, and 8 A4-size papers of CRF_StatVill which then cut into 4 pieces for each page to get a batch of 32 questionnaires. 
     The first day of training covers Steps 3 and 4, starting with a brief presentation for an overview of the program, followed by performing a random sampling, data collection, and data entry. Step 5 is for learning on population, sample, and sampling techniques conducted as a seminar based on the StatVill and expanded to other scenario to cover all methods. Step 6 starts after each participant finished data entry and had a data file. Duration of the training for Step 5 depends on depth of the statistical methods to be taught. [Note: Tools to generate the data for the teacher]

Materials: 

Steps:

  1. Step 1: Each participant will be instructed to conduct a household survey in StatVill, a village with a population of 300 households (N = 300)
    • Interview the head of the household
    • Perform a simple random sampling using a random number table provided below
    • Alternatively, select ID number randomly using Stata
      • clear
      • set obs 300
      • gen id = _n
      • set seed 13579 /* the seed number must be different from this example, please use number of your own */
      • sample 30, count
    • Sample size of 30 households (n = 30)
  2. Step 2: Download the following materials and print them in A4 papers:
    • Random Number Table (print out 1 page) [PDF]
    • CRF_StatVill [PDF] (print and arrange as a book with 30 CRFs)
    • Annotated_StatVill (print out 1 pages) [PDF] [DOC]
  3. Step 3: Random sampling of the household and data collection
    • Perform a simple random sampling using the Random Number Table  
    • Data collection, with a door-to-door survey at the StatVill, by transcribing the data at each sampled household to the CRF. The StatVill is located at the Data management and Statistical Analysis Center (DAMASAC), the 2nd Floor of the 2nd Building of the Faculty of Public Health, just above the faculty library.
  4. Step 4: Data entry into computer
    • Prepare a data file structure according to the Annotated_StatVill  
    • For a short training course, participants can use MS-Excel for data entry
    • For professional, participants are required to use any options, followings are some of them that are free of charge:
      • Option 1: Recommended -> Use EzForm in nCRC - Free online research tools at www.ncrc.in.th 
      • Option 2: Scan CRF papers using OMERET for data management using optical recognition technology
      • Option 3: Manual key punching using EpiData
      • Option 4: Online data entry using Google Forms
  5. Step 5: Semminar on Population, Sample, and Sampling techniques
  6. Step 6: Data analysis 
    • Exploratory data analysis for data cleaning
    • Concept of statistical inference
    • Data analysis for a research with continuous outcome
      • Formulate a research question
      • Plan for data analysis (design mock tables) according to the research question
      • Expand the topic to cover various methods of analysis for the purpose of a quick tour
    • Data analysis for a research with categorical outcome
      • Formulate a research question
      • Plan for data analysis (design mock tables) according to the research question
      • Expand the topic to cover various methods of analysis for the purpose of a quick tour 
    • Data analysis for a research with numerical count or Poisson outcome
      • Formulate a research question
      • Plan for data analysis (design mock tables) according to the research question
      • Expand the topic to cover various methods of analysis for the purpose of a quick tour
    • Data analysis for a research with event-free duration or survival outcome
      • Formulate a research question
      • Plan for data analysis (design mock tables) according to the research question
      • Expand the topic to cover various methods of analysis for the purpose of a quick tour

 

Sttaistical inference:

  1. N = 300 [Data in Exel] [Data in Stata] [Stata Main Do file] [Stata Age_BMI_Do file]          
    • Mean (mu) of income = ???
    • Standard deviation (sigma) of income = ???
  2. n = 30
    • Mean (x-bar) of income = ??
    • Standard deviation (SD) of income = ??
  3. Examine distribution of the raw data from the population (Income in the population, N of 300, has a highly skew distribution- skew to the right.)
  4. Examine  distribution of the raw data from the sample (Income in the sample, n of 30, is also highly skew.)
  5. Obtain x-bar from all of your classmates at http://www.cascap.in.th:9001/p/statvill (to get many x-bars) [Sampling x-bars and Do flie]
  6. Examine  distribution of the x-bar obtained your classmates (This is the distribution of the sampling mean.)
  7. Compute the standard deviation of the sampling mean => ??
  8. Compute the standar error from a single SD of your own sample => SD/[square root(n)] => ?? 
  9. Compare both SE and discuss
  10. Compute 95%CI of the mean of income from your sample, n of 30 => ?? to ??
  11. Draw a CI line at the white board provided the front of the class (http://www.cascap.in.th:9001/p/statvill ) then compare yours and that of other classmates and discuss
  12. [Post-test]

 

 Participants who used StatVill:

  1. 15 June 2013: MPH. (Health Administration) KKU
  2. 16 June 2013: DrPH., PhD. (Epi&Bio), PhD. (BioMed), M.Sc. (Clinical Epidemiology), MPH.(Biostatistics) International course
  3. 19 August 2014: DrPH., PhD. (Epi&Bio), MPH.(Biostatistics) International course
  4. 04 August 2015: Short Course in Clinical Epidemiology and Biostatistics
  5. 15 August 2016: Short Course in Clinical Epidemiology and Biostatistics
  6. 4 August 2016: DrPH., PhD. (Epi&Bio), MPH.(Biostatistics) International course
  7. 19 August 2017: DrPH., PhD. (Epi&Bio), MPH.(Biostatistics) International course
  8. 10 August 2018: PhD. (Epi&Bio)
  9. 7 August 2018: PhD. (Epi&Bio)
  10. 12 August 2018: International Short Course in Clinical Epidemiology and Biostatistics
  11. 14 August 2019: Ph.D. (Epi&Bio)
  12. 18 August 2020: PhD. (Epi&Bio)
  13. 16 August 2021: PhD. (Epi&Bio) 
 

 

 Practice using Stata for common statisticalmethods