The flashcards below were created by user
on FreezingBlue Flashcards.
Entire group of people of interest from which sample will be selected. You want to generalize the results from your sample back to the target population
A subgroup of the target population that will (hopefully) participate in your research.
your sample should be similar to the population on the characteristics of interest.
process whereby a small proportion of the target population is selected for your study
Steps in the sampling process
- Identify the target population
- Identify the accessible population (division 1 football players in utah versus division 1 football players in u.s.)
- Determine desired sample size
- select the specific sampling technique
- random (or probability) sampling
- Nonprobability sampling
- or probability sampling
- random selection: everyone has an equal chance of being selected
does not use random processes so not everyone has equal chance of being selected may not accurately reflect the population of interest
Population is represented by?
Sample is represented by?
Simple random sampling
- uses random selection (equal chance)
- The selection of one person does not interfere with the selection chances of another (put the names back in the hat after your draw so all the chances are the same to draw another name)
Stratified random sampling
- divide the population into specific subgroups, or strata, based on critical characteristics (sex: male, female)
- a set number of research participants are randomly selected from each strata
Ways to randomly select from strata
select proportionally (there are 450 males so 25% would be 113; there are 550 females so 25% would be 138)
Select equally: since I want a total of 250, I'll select exactly 125 participants from each strata
- sampling unit is a naturally occurring group or clusters of members of the population
- instead of sampling individual members you randomly select the clusters (I could choose "Houses" as my cluster, and everyone within the selected houses would participate)
- sample is drawn by choosing every kth person from a listing of the population (k=a constant and represents the sampling interval)
- 1000 greek students but only want 250 so 1000/250 = 4 so use 4 as my k or interval. Have to make sure is really random it depends on how the order of the names on list happened
you include any participants who are readily available and accessible.
When a questionnaire is measuring what is intended to be measured
Ways to establish validity
- Content - related
- construct - related
- way to establish validity
- Experts in the field of topic of questionnaire review my questionnaire to make sure my questions are appropriate and complete
I use a statistical approach to be sure I am measuring the construct of resilience, the whole construct of resilience, and nothing but the construct of resilience
- I take new questionnaire and using a statistical approach determine if it correlates with a certain "criterion" (something that theoretically resilience should be able to predict - like optimism)
- 'I take another new questionnaire and determine using a statistical approach if it can distinguish between resilience and something very different (like defeatism)
when a questionnaire measures consistently each time it is used
Ways to establish reliability
- Alpha reliability
- test-retest reliability
- way to establish reliability
- using a statistical approach to examine each item on the questionnaire compared with the other items on the questionnaire
- way to establish reliability
- using a statistical approach to examine day-to-day stability of the questionnaire by correlating day 1 scores with day 2 scores (there is a time lapse on this one) Participants take it one day and then another day take it and the scores should correlate