Help
Options
Didn't know it?
click below
click below
Knew it?
click below
click below
Don't Know
Remaining cards (0)
Know
retry
shuffle
restart
0:00
Embed Code - If you would like this activity on your web page, copy the script below and paste it into your web page.
Normal Size Small Size show me how
Normal Size Small Size show me how
PSY 215 Exam 2
| Term | Definition |
|---|---|
| Experiments | Investigations where researchers manipulate an independent variable |
| The effect on the dependent variable | Means the results denote causality |
| Nuance for Experiments | - Groups of participants must be equal - If not, this is a quasi-expiement - Can still yield causal results |
| Correlational Studies | An investigation that explores the effect of a subject variable on a dependent variable - Do NOT yield causal Information - identify relationships |
| How to make a correlational study experimental? | - randomly assign participants to two groups - Placebo-control (minimize bias) |
| Between-Subjects Design | -Experiment that has two or more groups of subjects each being tested by a different testing factor simultaneously |
| Types of Groups | Control Groups: Exposed to the same conditions as the experimental group, except for the manipulation of the independent variable Experimental Group: Exposed to the specific treatment or manipulation of the independent variable being investigated |
| 3 Requirements to have Casual Results | 1. The groups compared must be equivalent before the independent variable is introduced(equivalent group) 2. The independent variable must be introduced before the dependent variable is measured(temporal priority) 3. Control of Extraneous Variables |
| Equivalent Groups | - Control and experimental group must be equal - Any difference seen shouldn't be because of group differences - Random Assignment |
| Avoiding Selection Bias | DON'T - select which participants are going into which group - Allow participants to select which group they're in |
| Perks of Random Assignment | - Doesn't guarantee groups will always be completely equal -Any difference occur by chance - Such differences will have little/no effect on the end results |
| Matching | Identifying alike participants then randomly assigning them to different groups |
| Pretesting | Identify similar characteristics prior to matching |
| Downsides of Matching | -Can be hard to find matching criteria for every participant - Don't match every participant on the same criteria --> Stratification - Resource and time intensive - Loss of generalizability |
| Within-Subjects Design | An investigation where every subject receives every level of the independent variable at least once - don't need to worry about equal treatment - Pretest-posttest design & Repeated measures design |
| Counterbalance | Systematically varying the sequence in which participants are exposed to the independent variable - create all variation combinations |
| Cross-Sectional Study | Data is collected from different groups of participants at a single point in time with the aim of comparing difference between these groups - Correlational between-subjects design - Give test to different age groups - Similar to longitudinal study |
| Pros and Cons of Cross-Sectional Study | Pros - Efficient - No participant drop out - Good for population trends (prevalence of certain phenomena) Cons - Does NOT generate causal results - Can't track change over time - Susceptible to cohort effects |
| Examples of Cross-Sectional Topics | - Education Level and Political Views - SES and Parenting Styles - Child Abuse and Development |
| Temporal Priority | A cause must precede its effect ( IV before DV) |
| Control of Extraneous Variable | Variables that can affect the dependent variable -There should be no confounds that could act as alternate explanations - If an extraneous variable exists for one group and not the other - no longer causal results; at most, we can say they're related |
| Ways to avoid Extraneous Variables | - Hold constant: control an extraneous variable & keep it consistent across all groups - Counterbalance: systematically varying the sequence in which participants are exposed to the independent variable |
| Which way is Generally Better? | Holding a Variable constant = less error variance than counterbalancing Counterbalancing typically has improved external validity - generalizes better to the larger population - potentially more logistically complicated |
| Extraneous Vs. Confounding Variables | Extraneous: Anything that could influence the dependent variable Confounding: Influences the dependent variable, and also correlates with or causally affects the independent variable - A type of extraneous variable |
| Internal Validity | The extent to which the design of an experiment ensures that the IV caused a measured difference in the DV - perfectly internally valid study has no extraneous variables or other problems that would confound the results |
| External Validity | How well the experiment results can be generalized |
| Common Confounds | - Experimenter Bias (expectations affect study outcome) - Subtle Cues (Body language, tone of voice, facial expressions) - Interpretations of Responses (results actual meaning clouded by preconceived notions) - Data Recording (align with expectations) |
| How do we Avoid Experiment Bias? | - Have RAs who don't know what the hypotheses are - Use standardized protocols for interactions with participants to ensure consistency - Use automated data collection methods to minimizer the subjective influence on data recording |
| Demand Characteritics | Cues or aspects of research setting that may unintentionally signal to participants how they are expected to behave or respond - Participant Bias |
| Avoiding Demand Characteristics | - Use Double or single blind procedure |
| Instrumentation Effect | Occurs when the way the DV is measured changes in accuracy over time - threat to internal validity - Changing the wording of a question on a longitudinal survey question - Batteries run low on electronic measuring device |
| Subject Attrition | When a participant quits the study before it is completed - Subject mortality - Nonsystematic and systematic attrition |
| Nonsystematic Attrition | When participants leave a study for reasons unrelated to the subject of the experiment itself (random reasons) - minor inconvenience, not a real threat to internal validity |
| Systematic Attrtion | Participants who quit are unevenly distributed among groups because they have quit for a common, specific reason - |
| Sensitivity of the dependent variable | Sensitive enough to detect difference between conditions, not too insensitive to where the difference might be missed - Ceiling effect & Floor effect |
| Ceiling Effect | A measure yields scores near the top limit of measurement for one or all groups |
| Floor Effect | Dependent variable measurements yields scores near the lower limit |
| Pretest-Posttest | One group of participants is tested twice using the same measurement tool - Once before and once after the IV is manipulated in some way |
| Is pretest-posttest a ture experiment? | NO - Change could simply be a function of time - Need to add a "control" group and also takes same testing measures |
| Repeated Measures Design | Involves multiple measurements per participant |
| Is the repeated measures design a true experiement? | YES - Doesn't involve a single testing session - Randomly assign participant to receive one or the other first |
| Longitudinal Design | Within-subjects design where participants are tested multiple times, except this looks for changes over a long period of time |
| Advantages of Within-Subject Design | - Requires fewer participants than between-subjects design - Takes less time - Subject variables remain constant across the experimental conditions -Error variance is reduced so that the test is more powerful |
| Less error variance = | More powerful test of the IV's effect - Less likely to make a Type II Error than between-subjects design |
| Jump Cut: Type I and Type II Errors | Type I Error: Occurs when you incorrectly reject a true null hypothesis - False positive Type II Error: Occurs when you fail to reject a false null hypothesis - Fail to detect a significant difference when it actually exists |
| Pros and Cons of Within-Subjects | - Demand Characteristics - Carryover Effects - Unrelated Event Impact |
| How to protect against Demand Charactertics | - Deceptions within reason - ask several other questions |
| Carryover Effects | Having a participant repeat some measure multiple times - If this repetition impacts the results, its a carryover effect - Can confound results -Practice & Fatigue Effect |
| Practice Effects | When performance improves - More sleep, driving improves |
| Fatigue Effects | When performance declines - Repetition is making participants feel more tired |
| History Effects | The result of an event that occurs outside the experiment at the same time the IV is being changed |
| Maturation Effect | A change in performance simply due to the passage of time - Especially a potential factor in longitudinal studies |
| Regression towards the mean | Extreme scores, upon retesting move closer to the mean - Due to the natural occurrence of error variance |
| Examples of regression towards the mean | - Weight: Static measure, not very susceptible - Winning the lottery: ALWAYS a dead average, very susceptible |
| Order Effects and Counterbalancing | Presenting experimental conditions to participants in different order so that carryover effects are controlled - Complete within-subject deisgn - Incomplete between-subject design |
| Complete Within-Subjects Design | All subjects experience each experimental condition several times until they have had all possible orders of conditions - ABBA counterbalancing & Block Randomization |
| ABBA Counterbalancing | Simplest complete within-subject design - Participants get condition A, then B Next the get B, then A - Try and remove bias - Don't want results just based on measure sequence |
| Block Randomization | Used when you have 3 or more conditions - Every subject gets every possible order of the conditions in a randomized order |
| Incomplete Within-Subjects Design | Participant does not receive all possible sequences of conditions - They receive a unique order of the conditions at least once - ONLY used when ABBA and Block aren't appropriate |
| Random order with Rotation | 1. First participant receives a randomly ordered sequence of the conditions (B, C, D, A) 2. Move first condition to the end and thats the the next subject receives ( C, D, A, B) - ALWAYS multiples of 4 - Subject number needs to be a multiple of 4 |
| Extraneous Variable | Anything that could influence the dependent variable - Can only influence the DV |
| Confounding Variable | A type of extraneous variable that influences the DV, and also correlated with or causally affects the IV |
| Sources of error variance for test taking | -Hunger -Sleep amount -How alert you are -Etc. |
| Scientific Method | The process by which scientist collect information and draw conclusions about their disciplines - How an IV or subject variable change effects the DV |
| The clearer you are when designing a study, the more easily you can foresee... | - Pitfalls - Ambiguity - Confounds |
| Operational Definiton | Clear and specific description of how a variable will be measured, observed, or manipulated in a research study - Someone with no experience can understand with extra research |
| What does Operational Definitions Help with? | - Obtaining consistent results - Replications by other researchers |
| Reliability | The consistency with which the same results are obtained from the same test, instrument, or procedure |
| Different researchers, use same procedures, measure the same phenomenon, obtaining the same results | Reliability |
| Validity | The extent to which a measurement actually measures what it is supposed to - Accuracy |
| Types of Validity | External & Internal |
| Internal Validity | The extent to which the design of an experiment ensures that the IV ( and not some other variable), caused the change in DVs. - Well designed and conduced without confounds |
| External Validity | The generalizability of the study - Easier it is to generalize, higher degree of external validity |
| Population | All the people to which the researcher wishes to generalize their research reuslts |
| Sample | A subset of the population used in a study |
| Random Sampling | Randomly selecting subjects from the population to be part of the study |
| Convenience Sample | Subjects are not chosen randomly - Right place, right time - Can impact external validity |
| Types of Convenience Sampling | - Online Surveys - Street Interviews |
| Hypothesis is more general than a... | Prediction |
| Hypothesis | An educated guess about the world |
| Prediction | What you expect to see in a test of that hypothesis |
| Two Types of Hypothesis | - Null - Alternative |
| Null Hypothesis | The prediction that nothing is different, there is no difference between groups |
| Alternative Hypothesis | The hypothesis upon which researcher's prediction is made - there is a difference in scores between groups in some way |
| Two-tailed Hypothesis | Researcher does not predict a specific direction of the difference between groups - No prediction of directionality, just that there is a difference |
| One-tailed Hypothesis | Researcher predicts the direction of the difference between groups |
| What type of hypothesis is actually tested? | The null hypothesis |
| When testing, you either... | - "Reject the null hypothesis" - "Fail to reject the null hypothesis" |
| Reject the null hypothesis | - The difference between groups is so large it is unlikely to have happened by chance |
| Two possibilities for any research problem | 1. The null is correct, and there is no difference between groups 2. The null is incorrect, and there is a difference between groups |
| Type 1 Error | Rejecting the null when it is true - False positive - Typically more serious |
| Type 2 Error | Failing to reject the null when it is false - False negative |
| The probability of a Type 1 Error is called... | Alpha, a - .05 --> 5% chance of making such error |
| Region of Rejection | A special zone that helps researchers decide whether their data provides strong evidence to support a new idea or hypothesis - If it falls into this region, it has a statistically significant difference (top 5%) |
| Two-tailed Hypothesis, region of rejection | a = 0.025 or 2.5% on each side |
Created by:
Buchiajaezu
Popular Psychology sets