PSCH 242 UIC Exam Solved Answers 2025

Level of constraint - -how much control the researcher has over the design and progression of the study Archival study - -a study in which data is collected from a variety of historical records and pre-existing sources. Archival study advantages - -can often rely on huge data sets, and there is no researcher influence risk. Archival study limitations - -there are alternatives present that can explain hypotheses in a variety of cases and few ways to amend this. Combinations of statistics could also be used to limit this issue, such as baseball attendance and weather to limit bias. Additionally, sources are not always reliable, and there is no control over data collection. Naturalistic observation - -observing and recording behavior in naturally occurring situations without trying to manipulate and control the situation. Naturalistic observation advantages - -realistic picture of behavior, actions are pure. Naturalistic observation limitations - -limited scope of observation, reliable and valid measures are very difficult to create. General limitations of low-constraint methods - -limited generalizability, limited replicability, lot of room for experimenter (confirmation) bias, very limited validity of measure at times, mistaken causality. Differences between correlational lower methods of research - -higher levels of constraint, narrower focus, more standardized procedures, control over when and how variables are measured. Differences between differential and lower methods of research - -narrower focus, standardized procedures, control over how and when variables are measured, and *additional* control over confounding variables. Problem statements in correlational research - -always contain at least two variables. "is there a relationship between variable x and variable y?" Problem statements in differential research - -"does group a differ from group b on variable y (the dependent variable)?" PSCH 242 PSCH 242 Differences between correlational and differential studies - -correlational observes a relationship between two variables while differential observes a relationship between two variables based on two or more pre-established groups. Confounding variables - -variables that vary along with the independent variable. A variable that is likely to have an unwanted effect on the dependent variable. How to deal with confounds in correlational research - -statistically control for effects of possible confounding variables How to deal with confounds in differential research - -select appropriate comparison groups. Goal: "all else equal." Limitations of correlational research - -cannot draw conclusions about causality. Relies exclusively on measured variables. Limitations of differential research - -cannot draw conclusions about causality. Relies exclusively on measured variables, though there is more control as they may be separated by characteristics. Operational definition - -the procedure used to measure and/or manipulate variables. Research hypothesis - -the hypothesis that the variables under investigation are related in the population - that the observed effect based on sample data is true in the population. Logic behind testing a research hypothesis - -the research hypothesis may not be proven correct, but support for it can be found by proving it possible (e.g., proving the null hypothesis false, and alternative explanations can be ruled out.) Null hypothesis - -the hypothesis that there is no significant difference between specified populations, any observed difference being due to sampling or experimental error. Possible alternative explanations (confounding variables) - -the "hypothesis" that something other than the independent variable caused the dependent variable. Difficult to perfectly rule out, but lends credibility to the research hypothesis if ruled out. Statistical validity - -the extent to which statistical conclusions derived from a study are accurate and reasonable Construct validity - -the extent to which the operationalization of the variables measure what they are supposed to measure External validity - -extent to which we can generalize findings to real-world settings PSCH 242 PSCH 242 Internal validity - -extent to which we can draw cause-and-effect inferences from a study (causality) Mundane realism - -extent to which an experiment is similar to a real-life situation. Psychological realism - -the extent to which psychological processes generated in an experiment are similar to those that occur in everyday life situation of interest Maturation - -results can be attributed to time passing and internal changes that happen over time rather than the independent variable. Selection - --any factor that creates groups that are not equal at the start of the study -always a problem when participants are not randomly assigned to treatments Statistical regression - -tendency for participants selected because of extreme scores to be less extreme on a retest Attrition - -loss of participants during a study Diffusion of treatment - -changes in participants' behavior in one condition because of information they obtained about other conditions Sequence effects - -behavior in one condition is due to experience with previous conditions Testing effects - -repeated measurement of the same individual may impact a person's subsequent scores. History - -external events that take place during the course of a research study that influence the outcome of the study. Subject effects - -participants are not passive recipients of treatment Reactivity - -changes in the behavior of research participants as a result of their knowledge that they are part of a research project. Demand characteristics - -cues available to the participants that enable them to detect the purpose of the research, or what is expected of them by the researcher. Placebo effect - -people show psychological and physiological changes from the suggestion that such changes should take place. Response sets - -tendencies of research participants to distort their responses to questionnaire items Experimenter effects - -biased treatment of participants. PSCH 242 PSCH 242 Self-fulfilling prophecy - -the tendency for people to behave as they are expected to behave as they are treated a certain way in the experiment. General control procedures - -preparation of the setting (make it a constant), validate instruments, ensure replication is possible. Replication - -the ability to demonstrate that the effect is reliable by reproducing it elsewhere. Blind procedures - -best control for expectancy effects (like placebo) Single-blind - -the participant does not know what condition they are in. Double-blind - -neither the experimenter nor the participant knows what condition the participant is in. Automation - -remove contact between subjects and the experimenter, so there are no opportunities to influence participants unintentionally. Objective measures - -focus on reliable measures rather than subjective measures. Multiple observers - -reduces bias because it challenges observers to be as objective as possible Deception - -to hide (actively or passively) the purpose of the study from participants. Ethics must also be taken into account. Target population - -the group of people you are ultimately interested in learning something about Accessible population - -portion of target population that is available to you (practical constraints) Sample - -participants selected from the accessible population Stratified random sampling - -random sampling withing various subgroups (strata) of accessible population Random sampling - -every participant in accessible population (hopefully identical target population) has an equal chance of being sampled Ad hoc samples - -non-random sample from the accessible population. It's non representative and should describe sample to help define the limits of generalizability. Free random assignment - -random assignment of participants to conditions PSCH 242 PSCH 242 Matched random assignment - -random assignment of participants in matched sets to conditions. Experimental design - -control over independent variable, random assignment to iv conditions, all else kept constant Systematic between-groups variance - -variability between groups that is brought about by either the experimental manipulation or by a confounding variable. Experimental variance - -(explained variance) due to the independent variable Extraneous variance - -due to confounds Nonsystematic within-groups variance - -due to chance factors and individual differences. Includes error variance, which is simply variance that has no explanation Controlling variance - --maximizing experimental variance: make sure groups differ on iv, create as strong a manipulation as possible -controlling extraneous variance: ensure that the only difference between groups is the level of the iv Minimizing error variance: "all else constant," precise measurements Ex post facto design - -a scientific study in which the values of the independent variable are not manipulated, but selected by the experimenter after the groups have naturally divided themselves Single-group, posttest-only design - -draw a sample - apply a treatment - measurement Completely useless study. There is no reference point. Single-group, pretest-posttest design - -pretest - treatment - posttest. Provides a reference point, but no comparison group. Pretest-posttest, natural control-group design - -two naturally occurring groups are defined, then given a pretest measure, either a treatment or no treatment, then measured in a posttest and compared. Almost a true experiment, but there is no random assignment so it doesn't control for selection. Randomized, posttest-only, control-group design - -randomly assign sample, take two groups, give one treatment and not the other, then take a posttest measurement and compare. Random assignment controls for selection, control group controls for things like history and maturation. PSCH 242 PSCH 242 Randomized, pretest-posttest, control-group design - -randomly assign sample, split into two groups, give pretest, apply treatment to one and not to the other, posttest both, then compare. Allows for quantification of the extent of improvement due to treatment, and verify initial equality. Multilevel, completely randomized, between-subjects designs - -multi-group extension of the basic experimental designs. Enables the inclusion of more than one type of control condition. May or may not include a pretest. Between vs. Within-subjects designs - -between: independent groups designs where each condition contains different participants and the comparisons are made between different participants. It's the most common experimental proc