Week 2 Flashcards
What is target population
People you want your results to apply to
What is source population or sampling frame
People from whom the population is selected
What is the sample
People approached to take part in the survey
What is the study population
People who actually took part in the survey
What are the 4 types of proability sampling
- Simple random sampling
- Stratified random sampling
- Cluster sampling
- Multistage sampling
What is simple random sampling
12 out of 36 people are randomly selected
What is stratified sampling
Random samples from distinct groups
Geography
Sex
3 from each stratum are randomly selected process is random
What is cluster sampling
There are natural clusters rather than individual units and observations are made on all units within a cluster
more convient
1) Four out of the 10 clusters are randomly selected
2) All within the selected cluster are recruited
What is Multistage sampling
Primary sampling units are selected
Secondary units selected within primary units
Five out of the 10 clusters are randomly selected
Within the selected clusters participated are again randomly sampled
What is convenience sample
Selection from a non probability based source population due to ease of access to those individuals schools workplace organization or communities different than cluster because it involves randoming
What is purposive sampling
recruitment of the participants for a qualitative study based on the special insights they can provide
What is key informants
Individuals selected to participate in a qualittive study because they have expertise relevant to the study question
What is berksons bias
Can occur when cases and controls for a study are recruited from hospitals and therefore are more likely than the general population to have comorbid conditions sampling problem
What is healthy worker bias
When partcipants are recruited from occupational populations and therefore are systematically healthier than the general population
What is exclusion bias
Occurs when different eligibility criteria are applied to cases and contorls such as when controls with health conditions related to an exposure are excluded but cases with those comobidilites are not exlcuded
What can you base your sample size on
The effect estimate of exposure on the outcome
The ammount of errors we can accept
Variation in the population
What is type one error
You think something is there when it is not
What is type two error
When something is there but you missed it
What are some other methods of data collection
Direct measurment of physical functioning
Blood work
Sampling other tissues
Imaging
What is semi structured interview
Starts with a list of open ended questions these questions or lists are just starting points
What is probing
Is an interviewing technique that prompts an interview to provide a more complete or specific response
What are pros of interviewing
Train interviews to ensure the accuracy and completeness of each questionnaire
What are the cons of interviewing
May requrie major time commitments expensive
What are pros of survey
Cost and time effcient
Possibly of approaching a large number of participants
Best way to get hones answers to sensitive questions
What are the cons of survey
Problematic for low literacy populations and who have limited intrent acess or to be unfamiliar with computer
What is interview bias
repeat questions if we feel they did not answer them correctly
What is uniformity
Is easiest to acoomplish when all interviewers are provided with the tools they need to follow a standardized set of procedures dosent eliminate bias just less bias
What is the questionnarie desgin plan
Indentify general question categoried
Select specific question topics
Choose question and answer types
Check wording
Check order
Format layout
Pretest
Revise
USe
What should the order of questions be
Better to start with easy or least general questions
Group similar questions with similar response types so that they are asked consecutively
What are two data recording methods
- Record the response on paper and to enter or scan them into a computer later for older people more chance to manage and see trends you want to rectify
- Directly into a database some populations are uncomftable with computer techonology
What are some layout and formating things you should consider
Paper based and electronic survey pages checked for gramar and mispelling
if you force a person to put in an answer they will get the wrong data or quit the survey
What is Skip logic
Codes can automatically hide irrelevant question sfrom participants based on their responses to filter questions
What is back translation
International studies have harmonizes studies one person translates the questionnarie from the orginal language to a new language then a second person then translates the survey instrument in the new language back into the orginal language
What is pilot testing
A small scale preliminary study conducted to evaluate the feasibility of a full scale research project
The survey instument is revised based on these observations
