Kline, T. J. B. (2005). Psychological testing: a practical approach to design and evaluation. Thousand Oaks, CA: Sage Publications
Chapter 4
Briefly answer these questions separately. –

1. To use a probability sample, then, every English-speaking adult in the United States must have an equal chance of being selected to be in the sample, which is not realistic. Therefore, we typically use representative samples when establishing the psychometric properties of an instrument. What specific types of reliability and validity should we demonstrate for our new instrument before we use it in an actual research study?

2. According to Kline (2005) is when the sampling of each participant is unknown, and one of the downfalls can be that error cannot be estimated. With probability sampling, each participant has the equal opportunity to participate, and as a researcher, it is easier to estimate where an error could have occurred. Knowing this information which type of sampling would you use for data collection on a self-esteem survey?

3. It is important that we validate the instrument using samples that are representative of the population that will eventually be using the instrument. Once we select our sample, what would the steps be to determine the reliability and validity of the instrument? What types of reliability and validity should we demonstrate?