×
Log in to StudySoup
Get Full Access to UA - PY 355 - Study Guide
Join StudySoup for FREE
Get Full Access to UA - PY 355 - Study Guide

Already have an account? Login here
×
Reset your password

UA / Science / EN 355 / cumulative final exam definition

cumulative final exam definition

cumulative final exam definition

Description

School: University of Alabama - Tuscaloosa
Department: Science
Course: General Experimental Psychology
Professor: Craig cummings
Term: Fall 2016
Tags:
Cost: 50
Name: Cumulative Final Exam Portion PY 355
Description: Exam 1, 2, and 3 study guides combined for cumulative portion.
Uploaded: 11/29/2016
13 Pages 284 Views 3 Unlocks
Reviews



Of the terms in the previous bullet, what are some of the disadvantages associated with some of the measures of central tendency?




When trying to classify research as applied or basic, why is it necessary to look at factors other than the methods used?




Review the logical impossibility of proof, why is proof logically impossible?



PY 355­001 Fall 2016 Exam 2 Study Guide Chapter I 1. For the following sets of terms, be able to 1.) define each term 2.) explain hDon't forget about the age old question of gaming entertainment is the business of hospitality and entertainment with a core strength of:
We also discuss several other topics like fsu mis
Don't forget about the age old question of cbio 2200 uga
If you want to learn more check out slu final exam schedule
We also discuss several other topics like chm 2045 usf
Don't forget about the age old question of umd short answer questions
ow they differ from one another: descriptive research vs. applied research, inductive reasoning vs. deductive  reasoning, model vs. theory, experimental vs. descriptive vs. quasi­experimental, independent  variable vs. dependent variable, operational definition vs. conceptual definition. - Descriptive research vs. applied research: descriptive research describes  the behaviors, thoughts, or feelings of a particular group of individuals.  The goal of applied research is to find solutions for certain problems  rather than to enhance general knowledge about psychological  phenomenon. - Inductive reasoning vs. deductive reasoning: inductive reasoning is the  process of making decisions after observing. Deductive reasoning is the  process of reasoning from one or more statements and no observations.  - Model vs. theory: a model is the attempts to describe ow concepts are  related but not why. A theory is a set of propositions that attempts to  specify the interrelationships among a set of concepts.  - Experimental vs. descriptive vs. quasi-experimental: experimental  research can determine whether certain variables cause changes in  behavior, thought, or emotion. Experiments involve the manipulating of at least one independent variable and control of extraneous influences.  Descriptive research describes the behaviors, thoughts, or feelings of a  particular group of individuals. Quasi- experimental research examines  the effects of naturally occurring events. The researcher is unable to  manipulate the independent variable or control all other factors that  might influence people’s responses.  - Independent variable vs. dependent variable: an independent variable is a variable in an experiment that is manipulated or changed. A dependent  variable is a variable that the researchers look at but do not manipulate or change.  - Operational definition vs. conceptual definition: operational definition  specifies precisely how a concept is measured or manipulated in a  particular study. A conceptual definition is much like a definition that we  would find in a dictionary and often lack the precision needed for scientific communication.  2. Review the logical impossibility of proof, why is proof logically impossible? - Proof is logically impossible because confirming a hypothesiss with  research findings does not logically indicate that the theory from which  the hypothesis is derived is correct.  3. Review the primary functions of behavioral research (we discussed 3 total). - The three goals of behavioral research are describing behavior, explaining behavior, and predicting behavior. Describing behavior could include  changes in behavior across the lifespan or what type of cereal certain  people buy. Explaining behavior includes research that goes beyond what  happened to see why it happened. Most behavioral researchers view PY 355­001 Fall 2016 Exam 2 Study Guide explanation as the primary goal of science. Predicting behavior can  include job and academic performance or violent and criminal behavior.  4. When trying to classify research as applied or basic, why is it necessary to look at factors  other than the methods used? - It is important because the only difference between applied and basic  research is that applied research is to find solutions and basic research is  just to understand a phenomenon. The methods used may not be able to  identify which type of research is being conducted without looking at  other factors.  5. Which factors are used to determine research strategies? (i.e.,  descriptive, correlational, experimental, quasi­experimental) - Experimental research can determine whether certain variables cause  changes in behavior, thought, or emotion. Experiments involve the  manipulating of at least one independent variable and control of  extraneous influences. Descriptive research describes the behaviors,  thoughts, or feelings of a particular group of individuals. Quasi experimental research examines the effects of naturally occurring events.  The researcher is unable to manipulate the independent variable or  control all other factors that might influence people’s responses. Chapter II 1. Be familiar with the following terms: inferential statistics vs. descriptive statistics, meta analyses, variance, error variance, systematic variance, effect size, total sum of squares,  deviation scores, mean, range. - Inferential statistics vs. descriptive statistics: inferential statistics are used to draw conclusions about the reliability and generalizability of one’s  findings. Descriptive statistics are used to summarize and describe the  behavior of participants in a study.  - Metaanalyses: a procedure used to examine every study that has been  conducted on a particular topic to assess the relationship between  whatever variables are the focus of the analysis.  - Variance: statistic used to indicate the amount of variability in  participants’ responses. - Error variance: the portion of the total variance in participants’ scores that is unrelated to the variables under investigation in the study; variance  that remains unaccounted for.  - Systematic variance: the portion of the total variability in participants’  scores that is related in an orderly, predictable fashion to the variables  the researcher is investigating.  - Effect size: a measure of the strength of the relationship between two  variables; indicates the proportion of the total variance that is  sympathetic variance.  - Total sum of squares: the sum of the squared deviations of the scores  from the mean.  - Deviation scores: how much each score differs from the mean.PY 355­001 Fall 2016 Exam 2 Study Guide - Mean: the mathematical average of a set of numbers.  - Range: the difference between the highest and the lowest scores.  2. Of the terms in the previous bullet, what are some of the disadvantages associated with  some of the measures of central tendency?  - The disadvantage of the range is that two sets of data could be very  different but still have the same range.  Chapter III 1. Be familiar with the 4 scales of measurement. Be prepared to provide a novel example of  each. - Nominal scale: numbers assigned are simply labels for characteristics or  behaviors; for example, males=1 and females=2. Ordinal scale: the rank  ordering of people’s behaviors or characteristics; for example, the order in which runners complete a race. An ordinal scale does not tell us the  distance between participants. Interval scale: equal differences between  the numbers reflect equal differences between participants, but there is  no true zero point; for example, scores on an IQ test. Ratio scale: contains a true zero point; for example, weight.  2. Know the following terms, how they are defined, how they are used to characterize  scientific data: correlation coefficient, construct validity, concurrent validity, face validity,  predictive validity, hypothetical construct, validity, reliability, interrater validity, self­report,  psychometrics. - Correlation coefficient: expresses the strength of the relationship between two measures; can range from -1.0 to 1.0. - Construct validity: the extent to which a measure of a hypothetical  construct relates as it should to other measures. - Concurrent validity: scores on a measure are related as expected to a  criterion that is assessed at the time the measure is administered.  - Face validity: the extent to which a measure appears to measure what it’s  supposed to measure.  - Predictive validity: scores on a measure are related as expected to a  criterion that is assessed in the future.  - Hypothetical construct: entities that cannot be directly observed but are  inferred on the basis of empirical evidence. - Validity: the degree to which a measurement procedure actually measures what it is intended to measure rather than measuring something else (or  nothing at all). - Reliability: the consistency or dependability of a measuring technique; an  inverse function of measurement error.  - Interrater validity: the consistency among two or more researchers who  observe and record participants’ behavior.  - Self-report: produced by the researcher, behavioral record is produced by  the participant; can be used to measure thoughts, feelings, and/or  actions. PY 355­001 Fall 2016 Exam 2 Study Guide - Psychometrics: the science of measuring mental capacities and  processes. Examples of free-response question formats 1. What is a correlation coefficient? - A correlation coefficient expresses the strength of the relationship  between two measures.  2. Name a scientist or philosopher known for their view of the nature vs.  nurture debate. Secondly, provide a brief summary of their view. - Francis Galton believed that the influence of heredity and environment on  social advancement was the most important influence that there was.  Chapter 4 Approaches to Psychological Measurement 4.1 What factors must be considered when selecting the methods for an observational study  (3 important decisions to make, and the characteristics associated with each) 1. Will the observation occur in a natural or contrived setting? 2. Will the participants know they are being observed? 3. How will the participants’ behavior be recorded? 4.2 Compare and contrast naturalistic observation and contrived observation ­ A naturalistic observation is an observation of ongoing behavior as it occurs  naturally with no intrusion or intervention by the researcher. A contrived  observation is behavior that is observed in settings that are arranged specifically  for observing and recording behavior.  4.3 Compare and contrast disguised observation and non­disguised observation. Identify  potential problems associated with each method.  ­ In a disguised observation the participant does not know that they are being  observed. In some cases this can be an issue about a participants’ rights of  privacy. In a non­disguised observation the participants know that they are being  observed. This can cause issues because if someone knows that they are being  watched they may act in a different way which could cause the results to be not  accurate.  4.4 Identify measures of behavior latency and duration.  ­ Measures of latency: reaction time, task completion time, and interbehavior  latency. Duration­ how long a particular behavior lasts.  a. Which measure was utilized in the social behavior experiment conducted by  Conger and Killeen 1974? Measures of behavior latency 4.5 What name is given to the measure of how consistent observational ratings are between,  or among, multiple observers?  ­ Reliability.  4.6 How do psychophysiological and neuroscientific approaches to measurement differ from  other approaches to behavioral observation? How are they alike?  ­ Psychophysiological and neuroscientific approaches study biochemical,  anatomical, physiological, genetic, and developmental processes involving the PY 355­001 Fall 2016 Exam 2 Study Guide nervous system. Physiological processes are used to measure some of these  observations that cannot always be seen.  ­ Be able to think of an experimental question best suited for each of the 5  psychophysiological and neuroscientific methods listed in the PPTs and  textbook. Or, reiterate an example from class.  1. Measures of neural electrical activity (EEG)­ Abnormalities in REM  sleep 2. Neuroimaging (fMRI)­ Different areas activated when someone is  picturing playing tennis and when someone is picturing their normal walk  to work 3. Measures of autonomic nervous system activity (heart rate, respiration)­ identifying anxiety or measure reaction to different types of questions 4. Blood and saliva assays (cortisol)­ identify cortisol levels to see how  anxious a person is or the presence of drugs/toxins 5. Precise measurement of overt reactions (EMG)­ measure muscle  contractions  4.7 Regarding interviews and questionnaires, what is meant by an item? What is meant by a  construct? How might the two relate?  ­ An item is the questions and statements in self report measures. A construct is  just an idea in psychology or a concept. Each item can relate to separate  constructs or they can all relate to the same or similar constructs.  a. What on earth is a double­barreled item?  ­ Asking two questions at once such as have you ever tried Pepsi or crack cocaine? Or Do you enjoy listening to music and exercising? b. When should researchers make assumptions about respondents?  ­ Only when it is warranted. 4.8 Distinguish among the three common forms of bias in self­report measures.  1. Social desirability response bias­ the tendency to answer questions in a socially  acceptable way 2. Acquiescence response style­ the tendency to agree with statements, regardless of  their content 3. Nay­saying response style­ the tendency to disagree with statements, regardless of  the content 4.9 What sets archival data apart from other forms of observational data?  ­ Archival data is useful for studying: social and psychological phenomena of the  past, social and behavioral changes over time, topics that involve articles,  advertisements, or speeches, and anything that must be studied after it has  occurred. Archival data is found by analyzing data from existing records.  Observational data is data that is analyzed by the researchers at a given time.  4.10 What term is given to the conversion of textual information into numerical data?  What steps might be involved in this process? PY 355­001 Fall 2016 Exam 2 Study Guide ­ Content analysis. Steps: decide what units of text will be analyzed, define how  the units of text will be coded, classify into categories or rate, and raters code the textual material for all participantsPY 355­001 Fall 2016 Exam 2 Study Guide Chapter 5 Selecting Research Participants 5.1 Know the definitions for the following key terms/concepts: sample /sampling­ the process by which a researcher selects participants for a study probability sample­ a sample that is selected such that the likelihood that any particular individual in the population will be selected for the sample can be identified. nonprobability sampling­ researchers do not know the probability that a particular case will be chosen for the sample representative sample­ a sample from which we can draw accurate, unbiased estimates  of the characteristics of the population sampling error­ the extent to which characteristics of individuals selected for the  sample differ from those of the population  error of estimation­ indicates the degree to which the data obtained from the sample are expected to deviate from the population sampling frame­ a list of the population from which the sample is to be drawn stratified random sample­ the population is divided into strata, then participants are  randomly selected from each stratum stratum­ a subset of the population that shares a particular characteristic such as gender, race, location convenience sampling­ use whatever participants are readily available purposive sampling­ researchers use their judgment to decide which participants to  include in the sample, trying to choose respondents who are typical of the population quota sampling­ convenience sample in which the researcher takes steps to ensure that  certain kinds of participants are obtained in particular proportions economic sample­ a sample that provides a reasonably accurate estimate of the  population at reasonable effort and cost power­ the ability of a research design to detect any effects of the variables being  studied that exist in the data cluster sample­ based on naturally occurring groups that are usually in close proximity simple random sample­ every possible sample of the desired size has the same chance  of being selected from the population systematic sampling­  involves taking every so many individuals for the sample 5.2 Distinguish between cluster sampling and stratified random sampling.  ­ Cluster sampling is based on naturally occurring groups that are usually in close  proximity. Stratified random sampling is when the population is divided into  different strata and then participants are randomly selected. These participants  may not always be close in proximity compared to a cluster sampling.  5.3 What are the distinctions between quota sampling and purposive sampling? PY 355­001 Fall 2016 Exam 2 Study Guide ­ Quota sampling is a convenience sample in which the researcher takes steps to  ensure that certain kinds of participants are obtained in particular proportions.  Purposive sampling is when researchers use their judgment to decide which  participants to include in the sample, trying to choose respondents who are  typical of the population. The main difference between the two is that purposive  the researchers decide exactly which participants to include, in quota the  researchers take steps to get certain kinds of participants but do not decide  exactly who they are using and still has a little bit of randomability to it.  5.4 How are stratum different than clusters?  ­ Stratum are subset of the population that shares a particular characteristic. In a  cluster they are usually close in proximity, however, stratum are not necessarily  close in proximity but they share a certain characteristic.  5.5 What are the differences between systematic sampling and simple random sampling? ­ Systematic sampling involves taking every so many individuals for a sample.  Simple random sampling is every possible sample of the desired size has the  same chance of being selected from the population. In systematic sampling not  everyone has the same chance of being selected from the population.   5.6 What 3 factors influence the extent of sampling error that is to be expected?  ­ 3 factors that influence the extent of sampling error is sample size, population  size, and the variance of the data. Sampling error will be small with a large  sample size, a small population, and/or a small level of variance in the data. PY 355­001 Fall 2016 Exam 2 Study Guide Chapter 6 Descriptive Research 6.1 Define  descriptive research­ is designed to describe the characteristics or behaviors of a given  population in a systematic and accurate fashion  6.2 Be able to define  cross­sectional survey design­ sample consists of a “cross section” of the population  successive independent samples survey design­ two or more samples of respondents  answer the same questions at different points in time longitudinal survey design­ a single sample of respondents is questioned more than once Also, be prepared to describe the distinction among these design strategies.  6.3 What are the conceptual differences between demographic research and epidemiological  research? Are these methods considered nomothetic or ideographic?  As a comparison,  consider the goals of case studies and/or the distinction between applied and basic  research.  ­ Demographic research is concerned with describing patterns of basic life events  and experiences. Epidemiological research studies the occurrence of disease in  different groups of people. These methods are considered to be nomothetic. 6.4 Be familiar with quantitative and graphical approaches to summarizing data collected  from descriptive research. Which quantitative methods would likely not be used to  characterize descriptive research data?  a. Distinguish among the following;  simple frequency distribution­ indicates the number of participants who  obtained each score; scores arranged lowest to highest grouped frequency distribution­ shows the frequency of a subset of scores  (class intervals of equal sizes); often shows relative frequency relative frequency distribution­ proportion of the total number of scores that  falls in each class interval cumulative frequency distribution­ used to determine the number of  observations that lie above or below a particular value in a data set b. Distinguish among the following;  Histogram­ are used when the variable on the X axis is on an interval or ratio  scale of measurement frequency polygon­ axes are labeled as they are for the histogram but lines are  drawn to connect the frequencies of the class intervals bar graph­ are used when the variable is on a nominal or ordinal scale of  measurement scatterplot­ displays values for typically two variables for a set of data c. What purpose is served by the addition of error bars to graphical summaries?  Inversely, what information is missing in the absence of error bars?  ­ Error bars are included because they add another description that characterizes  standard deviation/variance/standard error when the average or mean does not.  These bars add a visual description of the variance which you cannot identify if  they are not included at all. PY 355­001 Fall 2016 Exam 2 Study Guide 6.5 What on earth is a… measure of central tendency­ convey information about a distribution by providing  information about the average or most typical score normal distribution­ rises to a rounded peak at its center and tapers off at both tails;  most scores will fall toward the middle of the range of scores confidence interval­ a range of values so defined that there is a specified probability that the value of a parameter lies within it positive skew­ more low scores than high scores negative skew­ more high scores than low scores standard deviation (SD)­ the square root of the variance, generally easier to interpret z­score­ describes a particular participant’s score relative to the rest of the data 6.6 What percentage of a normal distribution falls within 1 SD (i.e., above and below) of the  mean? What percentage fall outside + 3 SD?  ­ 68% of the scores fall plus or minus 1 SD from the mean. 34% fall below and  34% fall above the mean. Only about 4% fall outside of + 3 SD.  7.1 (Note: this chapter was not covered during in-class lecture I recorded a lecture with  the PPT slides outside of class and posted it to class as a Tegrity recording. This  lecture can be accessed by following the Tegrity link in the main Blackboard menu to  the left of the course homepage screen) 7.2 How does the correlation coefficients reflects the strength of a relationship between  two variables? ­ The strength of a relationship is measured from -1.00 to +1.00 (the pearson  correlation coefficient, r). The closer to positive or negative 1.00 the stronger  the relationship is. A correlation of .000 means that there is no correlation  between the two variables. The magnitude or numerical vvalue of a  correlation expresses the strength of the relationship between two variables.  7.3 On a scatterplot, how might a positive, negative, or zero correlation be reflected by  the pattern of the data? ­ In a positive correlation the graph would be going up. In a negative correlation the graph would be going down. In a zero correlation the graph would have no pattern.  7.4 If the correlation between two variables is .00, what might you conclude? ­ You might conclude that there is no correlation between two variables and  that as one increases/decreases the other does not either increase or  decrease.  7.5 A partial correlation is different than a correlation in what way? ­ Partial correlation is the correlation between two variables with the influence  of one or more other variables statistically removed. In a correlation the other  variables are not statistically removed.  7.6 How would you describe a directional vs. non-directional hypothesis?  ­ A directional hypothesis states which of the two condition means is expected  to be larger and uses a one tailed test. A non-directional hypothesis states  that the two means are expected to differ but does not specify which will be  larger and uses a two tailed testPY 355­001 Fall 2016 Exam 2 Study Guide 8.1 (Note, the exam will only cover regression analysis (pp 163 – 165) and facor analysis  (pp 176 – 178) 8.2 Regression analysis can be used to do what? In the equation y = mx+b what is the  predictor variable, the regression constant, and the regression coefficient? ­ The goal of regression analysis is to develop a regression equation from which  we can predict one score on the basis of one or more other scores. Regression  provides a mathematical description of how the variables are related and  allows us to predict one variable from the others. In y=mx+b the predictor  variable is y (the dependent variable), the regression constant is b (the y  intercept), and the regression coefficient is m (the slope of the line). 8.3 Be able to provide a rationale for using a factor analysis.  ­ Factor analysis can be used to study the underlying structure of psychological  constructs, to reduce a large number of variables to a smaller more  manageable set of data, and to confirm that self report measures of attitude  and personality are unidimensional (measure only one thing). 9.1 How many groups must there be in an experimental design?  ­ 2.  9.2 What is the distinction between a subject variable and an independent variable?  What is the distinction between experimental design and quasi-experimental design?  ­ A subject variable is a personal characteristic of research participants, such as age, gender, self esteem, weight, or extraversion. A subject is different from  an independent variable because it is not manipulated by the researcher like  the independent variables are. In an experimental design participants are  randomly assigned to either the treatment or the control group and in a quasi experiment they are not assigned randomly.  9.3 When simple random assignment to groups is used what is the probability that any  one participant will be assigned to any one condition? Is simple random assignment  used in repeated measures design? Why or why not?  ­ The probability of any one participant being assigned to any condition is equal for every participant in a simple random assignment. Simple random  assignment is not used in repeated measures design because each participant serves in all conditions of the experiment.  9.4 In a within-subjects design what do order effects mean? How might an experimenter  control for order effects in a repeated-measures design?  ­ Order effects occur when the effects of a particular experimental condition are contaminated by its order in the sequence of experimental conditions in which participants are tested. To protect against order effects, researchers use  counterbalancing which involves presenting the independent variables in  different orders to different participants.  9.5 What is the difference between internal and external validity?  ­ Internal validity is the degree to which a researcher draws accurate  conclusions about the effects of the independent variable on a dependent  variable. To have internal validity researchers must eliminate all potential  confounds. External validity is the degree to which the results obtained in one  study can be replicated or generlaized to other samples, research settings,  and procedures.  9.6 How might participant’s expectations interfere with the results in a drug trial study?  What might this effect be called?  ­ Participant’s who are not administered the actual drug may still see some of  the benefits or side effects of the real medication known as the placebo effect. 9.7 The "experimenter's dilemma" refers to the trade-off between what to measures of  validity?  ­ The trade off between internal and external validity. Experimenters almost  always opt for internal over external validity. The more tightly controlled an PY 355­001 Fall 2016 Exam 2 Study Guide experiment, the stronger its internal validity. However, tight experimental  control makes the experiment more unique and less like other settings,  thereby lowering external validity.  10.1 Be familiar with factorial design nomenclature (special terms used to describe  the size and structure of factorial design) ­ Researchers use special terms to describe the size and structure of factorial  designs. A “2 x 2 factorial” is a design with two independent variables, each  with two levels. A “3 x 3 factorial” has two indpendent variables, each with  three levels. A “2 x 2 x 4 factorial” has three independent variables, two with  two levels, and one with four levels.  10.2 Know how to distinguish between main effects and interactions when the  results are verbally described as well as visually when results are graphically  displayed.  ­ The main effect of an independent variable is the effect of that independent  variable while ignorig the effects of all other independent variables in the  design. A factorial design will have as many main effects as there are  independent variables. An interaction occurs when the effect of one  independent variable differs across the levels of another independent  3 5 3 0 e l b a i r a V t n e d n e p e 2 5 2 0 1 5 1 0 C o n d i t i o n B 1 C o n d i t i o n B 2 5 D 0 variable. Graph of an interaction:  C o n d i t i o n A 1 C o n d i t i o n A 2 I n d e p e n d e n t V a r i a b l e A 10.3 What is a mixed design (aka expericorr design)? Is this designation realted to  the independent variables or dependent variables?  ­ Mixed factorial designs are designs that include both independent variables  (that are manipulated) and participant variables (that are measured). The  mixed design includes both the independent variables and the dependent  variables. Used to determine whether effects of the independent variable  generalize only to participants with particular characteristics, examine how  personal characteristics relate to behavior under different experimental  conditions, and reduce error vaariance by accounting for individual differences among participants.  11.1 For inferential statistics, be familiar with the following terms and their  conceptual meaning:  null hypothesis- the independent variable did not have an effect on the dependent  variable  alpha- the probability of making a Type I error and erroneously believing that an  effect was obtained when it was actually due to error variance  beta- the probability of making a Type II error and erroneously failing to find an effect that was actually present type I error- a researcher rejects the null hypothesis when it is true type II error- a researcher fails to reject the null hypothesis when it is false correct decision reject null- researcher concludes that the null hypothesis is wrong and that the  independent variable had an effect on the dependent variable fail to reject null- researcher concludes that the null hypothesis is correct and that  the indepndent variable did not have an effectPY 355­001 Fall 2016 Exam 2 Study Guide effect size- is an index of the strength of the effect of the independent variable on  the dependent variable error variance systematic variance t-test- are used to test the difference between two means; if the observed difference is much larger than the estimate, then the researcher rejects the null hypothesis t-obtained degrees of freedom- the total number of participants minus the numer of  conditions directional hypothesis- states which of the two condition means is expected to be  larger; use a one tailed test nondirectional hypothesis- states that the two means are expected to differ but  does not specify which will be larger; use a two tailed test

Page Expired
5off
It looks like your free minutes have expired! Lucky for you we have all the content you need, just sign up here