Brittney Ingraham BADM 520 Quiz #4 October 24th 2015 1) What are the main criteria for evaluating measure validity? There are 5 different types of validity that are used for evaluating measure. The first criterion is making sure the measure has face validity. Face validity of the measure means that it accurately describes the concept being studied. An easy way to think about this if you make a bakery, you want people to walk in and know it’s a bakery; you cannot sell cars at your bakery and expect people to believe it is a bakery. The second is making sure there is concurrent validity. This is where the researcher comes up with a criterion that is known to be different among people to see if the data that is measured shows any difference. …show more content…
There are a few factors that need to be taken into account when deciding the size of your sample. First, you need to think about the absolute sample size rather than the relative. The larger the sample size, the more likely the sample is to have precision in the findings. Thinking about the size of sample error you are willing to tolerate is also important when figuring out the size of sample needed. The smaller the sample error that is tolerated, the bigger the sample needs to be. Time and cost are also factors that need to be taken into account. The precision will be higher and the sample error will be smaller from a sample of 5 to a sample of 1000, however after about 1000, the differences in precision and sampling error become less noticeable. Another factor is the amount of people who will be non-responsive. When you think about the size of the sample, you have to think about the number of people who will not respond to make sure that the number that does respond is still large enough to be significant. You need to also think about the heterogeneity of the population; are the people of the sample more the same or more different. If they are more alike the variation will be less than if they are different. The last factor is the kind of analysis the researcher wants to do because different types of analysis require a different size of