PY 355 Notes- Week 5
PY 355 Notes- Week 5 PY 355
Popular in General Experimenta Psychology
Popular in Psychology (PSYC),Arts and Sciences
This 6 page Class Notes was uploaded by Alexia Acebo on Sunday October 2, 2016. The Class Notes belongs to PY 355 at University of Alabama - Tuscaloosa taught by Craig Walter Cummings in Fall 2016. Since its upload, it has received 2 views. For similar materials see General Experimenta Psychology in Psychology (PSYC),Arts and Sciences at University of Alabama - Tuscaloosa.
Reviews for PY 355 Notes- Week 5
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: 10/02/16
Chapter 5: Selecting Research Participants Sampling: the process of a researcher selecting participants for a study many different ways COMMON MISCONCEPTIONS: o Most beh. Reseach DOES NOT use random sampling o Random= difficult to obtain, don’t always work well Probability Sample: selected sample so that the likelihood that an individual in the population will be selected- can be identified. SIMPLE random sample: most common probability sample; every possible sample of desired size has same chance of being selected. requires sampling frame: list of population from which the sample comes o Prob. Samples= RARE in psychology beh. Research does NOT usually aim to describe how a population behaves If GOAL is to make inferences representative sample: accurate, unbiased estimates of characteristics of population can be drawn. Error of Estimation-degree to which data from sample are expected to differ from population only important when dealing with probability sample o Sampling error: amount individuals selected differ from population o why sample results differ from population FUNCTION OF THREE THINGS: 1. sample size 2. population size 3. variance of data Systematic Sampling: taking every so many individuals for the sample th EX: every 4 person that walks into the room is interviewed -don’t need sampling frame, because you can’t Stratified Random Sampling: population divided into strata, then randomly selected from each stratum: subset of pop. That shares particular characteristic ensures adequate number from each Cluster Sampling: sample groupings/ clusters of participants based on naturally occurring groups, usually based on proximity Multistage Cluster Sampling: 1. divide pop. Into large clusters & randomly smaple clusters 2. sample large cluster 3. sample smaller clusters if needed EX: counties schools classrooms students Nonresponse Problem: failure of participants to respond once selected Ways to prevent: 1. persistence 2. incentives 3. limit time requirement 4. tell people in advance that they will be contacted Misgeneralization: generalized results that differ from population which sample was drawn Nonprobability Sampling: researchers do not know the probability that a particular case will be chosen for sample. o Error of est. cannot be calculated o Most research= this type of sampling o Valid method when the goal is to test hypotheses about how variables relate to behavior than population Convenience Sampling: use whatever participants are readily available -common with college students -may not relate to general population o Quota Sampling: type of convenience sample where researcher ensures that certain types of participants are obtained in specific proportions o Ex equal # of girls/ boys Purposive Sampling: judgement is used to decide which participants to be used in sample; try to get respondents typical of population **IN probability samples, key issue in determining sample size is error of estimation so opt for economic sample: provides reasonably accurate estimate of population @reasonable effort/cost POWER: ability of research design to detect any effects of variables being studied that exist in the data all else equal, larger sample= higher power CHAPTER 6: Descriptive Research designed to describe characteristics/behaviors of a pop. In a systematic/accurate fashion MOST COMMON TYPE= SURVEYS Cross-sectional survey design: sample=cross section of population Successive independent samples survey design: 2+ samples answer same q at different points in time Longitudinal/panel survey design: single sample questioned more than once o dropouts Internet Surveys: inexpensive, no interviewers, no data entry, own time o Little control Demographic Research: describing patterns of basic life events/ experiences like birth, marriage, death etc. Epidemiological Research: studies occurrence of disease in different groups of people Describing and Presenting Data: Good description= accuracy, conciseness, understandability Raw data= not concise, not understandable NUMERICAL METHODS: summarize data by numbers (%, averages) GRAPHICAL METHODS: summarize data in graphical, pictoral groups Frequency Distribution: table summarizing raw data by hsowing # of scores/ category TYPES: Simple Frequency Distribution # of participants who obtained each score o Lowest to highest o Grouped Frequency Distribution- frequency of a subset of scores o Relative frequency: proportion of total number of scores per class interval o Frequency Histograms & polygons o Class intervals on x axis, number of scores per interval on y axis o HISTOGRAM= when variable on X axis is on interval or ratio scale o BAR GRAPH= when variable is on nominal or ordinal scale HISTOGRAM V. BAR GRAPH depends on equal intervals If NO= Bar graph If YES=Histogram o FREQUENCY POLYGON= axes labeled like histogram but lines drawn to connect frequencies of intervals Measures of Central Tendency Mean: mathematical average o MOST COMMON o When presenting a few, researchers present in text. o With several, presented in table or graph. Median: middle score of the distribution Mode: most frequent score Error Bars: above/below means in a graph -indicate confidence in mean value Confidence Interval- usually 95%, range within mean is likely to fall Measures of Variability -variability tells how typical the mean is -if variability is small= good rep. of scores -how much scores vary Range: difference between largest and smallest Variance: takes into account ALL SCORES when calculating variability Standard Deviation: square root of variance. Easier to interpret. Normal Distribution rises to rounded peak @ center, most scores= midrange (-1 to +1) SKEWS Positive Skew: more low scores than high scores Negative Skew: more high scores than low scores Z-Score: describe participant score relative to rest. -indicates how far from the mean -useful w/ outliers
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'