Methods and Designs
Methods and Designs PSYC 328
Popular in Methods and Design in Behavioral Science
Popular in Psychology (PSYC)
This 3 page Class Notes was uploaded by Hope Good on Sunday October 9, 2016. The Class Notes belongs to PSYC 328 at University of South Carolina Aiken taught by Dr. Weed in Fall 2016. Since its upload, it has received 4 views. For similar materials see Methods and Design in Behavioral Science in Psychology (PSYC) at University of South Carolina Aiken.
Reviews for Methods and Designs
Report this Material
What is Karma?
Karma is the currency of StudySoup.
You can buy or earn more Karma at anytime and redeem it for class notes, study guides, flashcards, and more!
Date Created: 10/09/16
Chapter 6: Sampling v Population v. Sample o Population: a fairly large group of people/animals we want to learn about § Identified by specific characteristics § There are often to many individuals in a population to include in a study so researchers would have a difficult time locating each individual and persuading them to participate. o Sample: a small group of people with characteristic that match the population in important ways § The goal is to choose individuals for the sample who will represent the behaviors and attitudes of the entire population. o Sampling § Sample error: difference in scores from the population and sample • All research will have some amount of sampling error because the sample will never give you the same observations as the whole population • Minimize the sample error as much as possible § Descriptive statistics describes the performance of your sample. § Inferential Statistics are conducted to see how well findings from the sample may be generalized to the broader population v Probability Samples: individuals are chosen at random from the population such that the chance of any one individual being selected is known. o Most likely to be representative of the population o 3 types: § Simple random: individuals are chosen at random from the population such that all members have an equal chance of being selected • Example: if a population has 100 individuals, the chance of any one individual being selected for the sample is 1 in 100or 1%. § Cluster Sample: individuals are chosen at random from groups within the population. • Allows researchers to obtain a probability sample from a large population more easily than they would with a simple random because the list from which individuals are selected is easier to obtain § Stratified Random Sample: individuals are chosen at random from the population such that the proportion of individuals with a particular characteristic is equivalent in the population and sample v Convenience Sample: individuals are chosen at non-random from the population such that available individuals are chosen and the chance of any one individual being selected is not known o The sample may not represent the population as well as a probability sample but can be obtained more easily o 2 types: § Haphazard/volunteer: individuals are chosen from the population such that available individuals are chosen • common in psychological research • used because they are typically the most convenient means of obtaining a sample for a study and don’t generalize the results. § Quota: individuals are chosen from the population non-randomly such that the proportion of individuals with a particular characteristic is equivalent in the population and sample • Unlike stratified, quota sample will make use of convenience sampling techniques such as recruiting participants from a participant sign-up pool or asking students sitting in the library to fill out the survey. v Recruiting Participants o Regardless of type of sampling, researchers must consider how to actually recruit the participants for a study. § To use incentives or not § Flyers, emails, calls o The number of participants needed should be based on a power analysis o Internet Samples § Increase sample size over method § Can be more representative than other samples § Can include bias that in-person samples do not have Chapter 7: Summarizing/Interpreting Data v Descriptive v. Inferential Statistics o Descriptive: measures that help us summarize data sets o Inferential: a set of statistical procedures used by researchers to test hypothesis about populations v Central Tendency: value that represents typical score in a distribution o Mean- the calculated average of the scores in a distribution o Median: the middle score in a distribution, such that half of the scores are above or below that value o Mode: the most common score in a distribution v Variability: indicates how much the scores in the distribution differ from each other across response scale o Range: the most basic measure and is simply the difference between the highest and lowest scores o The range ignores all the score between the most extreme scores and therefore is a crude measure of validity o The standard deviation and variance are much more precise measures of variability o Standard Deviation: a measure representing average difference between the scores and the mean of the distribution § However, if you were to simple calculate the difference between the scores and the mean and add them up, you would find the value is always 0 § Thus, the standard deviation is determinded by calculation the difference between each score and the and the mean, square those values, add them and divide by n (n is the number of scores o Variance: the variance is simply the standard deviation squared § the standard deviation and variance measures are important for inferential statistical tests v Graphs and Tables o Graphs (figures) and tables of date are useful tools for quickly summarizing data in a visual way § They can represent a frequency distribution for a data set, which indicates how often each score or category appears in a distribution § In a frequency distribution, the different responses are graphed on the x- axis (horizontal) and the frequency of each response in the distribution is graphed on the y-axis (vertical) § Bar-graph: a graph of the means for different conditions in a study where the bar height represents the size of the mean § Line-graph: a graph of the means for different conditions in a study where each mean is graphed as a point and the points are connected in a line to show differences between mean scores. v Inferential Statistics o Hypothesis § Null: predicts no effect or relationship in the population § Scientific/alternative hypothesis: predicts an effect or relationship in the population o Significance Testing: determine likelihood of obtaining sample data when null is true. § Alpha level: chose by researcher: highest probably value taken as evidence against the null (sample value is too extreme for null) • Usually .05 § Critical region: portion of distribution of sample means containing extreme scores- size is equal to alpha level § p value: probability of obtaining sample values when the null is true- compared with alpha to determine if null can be rejected (test is significant) o Errors § Type I: reject the null when it is true § Type II: retain the null when it is false
Are you sure you want to buy this material for
You're already Subscribed!
Looks like you've already subscribed to StudySoup, you won't need to purchase another subscription to get this material. To access this material simply click 'View Full Document'