PSYC2 FINAL EXAM STUDY GUIDE

What is meant by between group and within group designs?

Between-group designs conduct their experiment with two or more groups where each group receives different treatment conditions. Within-group design exposes the same group of participants to all treatment conditions.

What is an experimental/treatment group and a control group?

Experimental/treatment- Independent variable is manipulated in order to test effects of "treatment" ○ Control group- No "treatment" is given in order to compare what effects in the given scenario might be a result of chance alone.

Know the difference between external and internal validity?

External Validity- Extent to which research findings can be generalized to individuals, cultures, situations and settings etc./ can be generalized beyond sample Internal Validity- Degree to which a study meets the criteria for establishing causality (free from flaws in its internal structure)

What is a factor? What is the difference between a single factor and a multifactor design?

Factor-an independent variable with two or more levels or groups. Single Factor Design-an experimental research design with a single independent variable that includes two or more levels. Multifactor Design-are experimental research designs with multiple independent variables

Distinguish between different factorial and regression designs ?

Factorial designs- Are used to in assessing significance and determining correlations ■ Correction - Used in assessing significance and determining differences between groups ○ Regression designs- are used in order to establish causation and to predict variable y' given variable x

Explain methods to counterbalance design?

Full counterbalancing- Researchers make sure that every order of treatment is administered. ○ Partial counterbalancing- There are so many possible orders that accounting for all in a single study is not reasonable. The researcher accounts for enough possible orders as to account for order and sequence effects ■ Latin Square ■ Williams Latin Square

What is statistical power?

Statistical Power - probability of rejecting the null hypothesis when it is in fact false Equation for power is 1-β where β is the probability of making a Type II error

What is the difference between a statistic and a parameter?

Statistics-draw conclusions about how well the characteristics of a sample Parameter-approximate the characteristics of the population,

What are participant variables?

The differing individual characteristics that may impact how a participant responds in an experiment Example: gender, age, sex, ethincity, socioeconomic status

Median

The midpoint in a distribution; that is, the score or value that divides it into two equal-sized halves. The median is particularly useful when analyzing data that have outliers, as it is more resistant to the influence of extreme values than is the mean.

Mode

The most frequently occurring score in a set of data. To determine the mode, simply tabulate the frequency of each value in the data set. The mode is the most frequent.

What information is given in a correlation coefficient?

The relationship between two variables represented by X & Y indicating strength and direction

What is the difference between Type 1 and Type 2 errors?

Type I error: Rejecting the null hypothesis when it is true; also known as a false positive. Type II error: Failing to reject the null hypothesis when it is false; also known as a false negative.

Whats a mixed factorial design?

a multifactorial design in which there is at least one between-groups independent variable and at least one within-group independent variable.

What is regression?

a statistical technique that can be used to predict or forecast a criterion variable (dependent variable) based on one or more predictor variables (independent variables)

What are post-hoc comparisons?

a test that isolates a difference identified by an omnibus test in a single-factor design. Is done when a result is significant

Sample

is the specific group that you will collect data from

What is the difference between simple and multiple regression?

○ Simple Regression-a regression design with one predictor variable. Multiple Regression-a regression design in which there are two or more predictor variables (independent variables).

What is the difference between independent and dependent variables?

independent variable- the variable that is manipulated in an experiment ○ dependent variable- the variable that is measured to assess the impact of the independent variable.

Population

- is the entire group that you want to draw conclusions about

What is meant by different "levels" of an independent variable

A level of independent variable refers to the different levels of the treatment ○ Ex. Studying the effects of alcohol on a driving. Driving simulation groups are composed of 0 drinks, 2 drinks, 4 drinks, and 6 drinks. Each of those groups can be considered a level of the independent variable.

What does it mean to "manipulate" a variable

A manipulated variable is the independent variable in an experiment. It's called "manipulated" because it's the one you can change ■ Ex. You can decide ahead of time to increase it or decrease it.

Descriptive statistics-

A range of procedures for depicting the main aspects of sample data, without necessarily inferring to a larger population. Descriptive statistics includes calculations such as the mean, median, mode, range, standard deviation, and correlation.

Inferential statistics

A range of statistical techniques that allow inferences about characteristics of a population to be drawn from a sample of data from that population. These techniques include approaches for testing hypotheses, estimating the value of parameters, and selecting among a set of competing models

What is the difference between alternative and null hypothesis?

Alternative hypothesis (Ha): The hypothesis that there is a meaningful difference between the groups or conditions under investigation. Null hypothesis (H0): The hypothesis that there is no meaningful difference between the groups or conditions under investigation

What is a confounding variable and give examples?

Confounding variable (or confound): a variable other than the independent variable that causes a change in the dependent variable. It is conceptually distinct but empirically inseparable from one or more independent variables; it is a type of "extra" variable that the researcher has not accounted for in an experiment.

What are the controls for outside experience?

Contamination by Communication: If participants who have completed their research participation communicate their experiences to those who are waiting their turn to participate, then the waiting participants' foreknowledge of the experiment may confound the study. History Effect: Sometimes events or circumstances outside an experiment can influence the outcome, thereby confounding the study, particularly in pretest-posttest studies. To be considered a history effect, an event must occur for only the experimental or control group in the time between the pretest and posttest that could influence the results in the same way as the independent variable.

What is the difference between counterbalancing and partial counterbalancing

Counterbalancing-an arrangement in which multiple orders of the experimental conditions are administered and compared. Partial Counterbalancing-experimenters do not use all possible orders although they can still control for order and sequence effects.

What is meant by experimental manipulation?

Experimental manipulation is the act of manipulating the independent variable in order to measure the effect of the independent variable on the dependent variable.

Mills three criteria for establishing causality?

Covariance: The independent variable and dependent variable covary, or vary together. In other words, the variables are related. The presence or level of one variable is related to the presence or level of another variable Temporal precedence: A cause must come before the effect. Therefore, the independent variable must be manipulated before there is a measured difference in the dependent variable. Elimination of alternative explanations: The researcher has ruled out other possible explanations and is confident that the effect of the independent variable on the dependent variable has been isolated. In other words, there is no confounding variable to explain the relationship between the independent and dependent variable.

Why is the null hypothesis never accepted?

It is because the probability of making a Type II error can be relatively large that scientists say that they "fail to reject the null hypothesis" and do not say that they "accept the null hypothesis." ■ A good β value (the probability of making type II error) is no more than 0.2 ■ When you have a 20% (0.2) chance where you're supposed to have rejected the null, it is hard to say that we "accept the null hypothesis" if it has a 20% chance of being wrong - so we say "fail to reject the null hypothesis" instead ■ You can't really accept anything with a 20% probability error rate

How do you get involved in more research?

List and describe ways that research experience will help you get a job. List and describe ways that research experience will benefit you if you plan to go to graduate school. List and describe ways that research experience will help you make a contribution to your community.

What are main and interaction effects?

Main Effect-an overall difference in the levels of one independent variable collapsing over the levels of the other independent variable. Interaction Effect-a possible outcome of a multiple factor design when one independent variable depends on the effect of the other independent variable

What are matched pair and block designs?

Matched Pair-an experimental design in which each participant is matched to another participant based on some important variable, and then participants in the pair are each randomly assigned to different experimental conditions. This type of design may include a pretest and always includes a posttest Block Designs-a research design in which participants are divided into relatively homogeneous subsets, or blocks, based on a variable of interest, and from these blocks are assigned to the experimental or control conditions. The purpose of a block design is to ensure a characteristic of

What are considerations for changes over time?

Maturation: Sometimes, naturally occurring time-related changes in participants can influence the outcome of a study, thereby confounding it. Regression to the Mean: Extremely high or extremely low scores naturally tend to become more moderate (i.e., closer to the mean) with repeated measurement of the dependent variable. Testing Effect (also called Practice Effect): If participants are tested multiple times, then practice or repetition of test items, tasks, or activities can influence participants' performance in subsequent tests.

Know the difference between narrative and parenthetical citations

Narrative citation: Author-date information in APA style that is used within the text to introduce or credit information from an outside source, thus: "Author and colleagues (2015) explained that...." Parenthetical citation: Author-date information in APA style placed in parentheses following information from an outside source, thus: (Author, Year).

Define the different levels of measurement

Nominal-Measurement that fits into discrete, unordered categories Ex: Age, Gender, Marital Status,Blood Type Ordinal-Measurement that often fits into discrete categories, but can be ordered or ranked along a scale, from lowest to highest. This measurement reflects a ranking of values, but does not indicate that there is equal spacing between each unit of measurement. 3rd place: Bronze, 2nd Place: Silver, 1st Place: Gold; 1-5 1 being completely unsatisfied, 5 being completely satisfied ○ Ratio-Similar to interval, but include a true, meaningful zero point. These data have the highest level of precision compared to nominal, ordinal, and interval data Ex: number of students, Kelvin Temperature Interval-Measured along a scale in which there is equal spacing between the units of measurement. This data lack can be described with a mean but lack a meaningful zero point. Ex: Temperate, GPA, IQ tests

Mean-

Numerical average of a set of scores, computed as the sum of all scores divided by the number of scores.

What is the difference between parametric and nonparametric tests?

Parametric tests: Statistical tests in which specific assumptions must be met before testing indicating that the data you are testing resemble a normal (i.e., bell-shaped) distribution. Can be used to compare the means of groups. Nonparametric tests: Statistical tests in which specific assumptions cannot be met

What are some threats to internal validity?

Participant Variables Difference in experiences between groups Contamination by communication History effect Maturation Regression to the mean Testing/Practice effect Placebo effect Instrumentation

Name and describe additional threats to validity?

Placebo Effect: If participants have expectations of the effects of an experimental condition (including the effects of a medication), their expectations will confound the study ■ If only the participants are unaware of their condition, this is known as a single-blind study. If both the participants and the researchers are unaware of the participant's condition, it is referred to as a double-blind study and would have the least potential for bias Instrumentation: A change in the measuring device during the course of a study can be a confound if the instrument is poorly calibrated or

What is the difference between post-test only between groups design and a pretest-posttest between groups design?

Posttest-only between-groups design: An experimental design in which each participant is exposed to only one experimental condition or the control, and the single score each participant contributes to the study is based on a posttest. Pretest-posttest between-groups design: An experimental design in which each participant is exposed to only one experimental condition or the control, but contributes two scores based on one pretest and one posttest.

What is a predictor and criterion variable?

Predictor Variable - independent variable Criterion Variable - dependent variable

What is random sampling?

Random sampling: Selecting items randomly from a population of interest, instead of systematically selecting items for the sample or by a biased method such as a convenience sampling.

Name and describe controls for participant variables?

Random selection. This means the selection of participants from the population is entirely random, which assures that the sample is representative of the population, including especially, individual differences. Random assignment. This means the assignment of participants to the different conditions of an experiment is entirely at random so that each participant has an equal likelihood of being assigned to any particular condition. Random assignment is the best way of distributing all possible variables across groups. Using a homogeneous sample. One way to make groups equivalent is to use a homogeneous sample, which means that all participants are highly similar, regardless of their assigned group. Using a homogeneous sample eliminates confounding participant variables, which increases internal validity—but it may also limit the degree to which study findings apply to other groups Using a matched-pairs design. In a matched-pairs design, the researcher matches each participant in one group with a participant in

What are the characteristics of the measures of variability or dispersion?

Range, deviation score, variance, standard deviation

What are repeated measures and longitudinal studies?

Repeated Measures-an aspect of a research design in which a dependent variable is measured on repeated occasions. Longitudinal Studies-a study that takes place over a period of time, sometimes several years.

Definitions of: Washout period and carry over effect

Washout Period-the time frame allotted for an administered drug to be eliminated from the body or for a previously administered intervention to become ineffective. Carry Over Effect-an order effect in which the outcome of one condition influences the outcome of a condition that follows.

What are Williams square and Latin square?

Williams Square-a Latin square design that counterbalances multiple conditions while also minimizing the carryover effect between adjacent conditions. Latin Square-a type of partially counterbalanced research design in which every participant or group receives every treatment, and every treatment is given equally often in each position of the sequence.

How do you determine statistical significance by looking at output?

You have to look at the p value. If the p value is greater than .05 it is not statistically significant. If the p value is less than .05 it is statistically significant

What is an order effect?

the influence of the order in which treatments are administered.

What is meant by statistical significance?

the likelihood that a relationship between two or more conditions is caused by something other than chance.

What is an Omnibus F-test?

the main test for a significant difference in a single-factor design when there are more than two groups.

Name tasks that students can do when getting involved in research?

○ Asking a question ○ Find out what is already known about the topic ○ Constructing a hypothesis ○ Testing the hypothesis/collecting data ○ Analyzing data and drawing conclusions ○ Reporting results

Techniques to avoid bias and reduce plagiarism in a research paper?

○ Bias ■ Reduce vagueness when describing things ● Instead of young adults, say "18 to 23 year olds" ■ Describe differences that influence generalization to the population of interest ■ Avoid stigmatizing language ● "the obese group was compared to a normal control group" ■ Use operational definitions ■ Use "they" if you don't know their pronouns ○ Plagiarism ■ Cite all sources in APA style ■ Use quotation marks around any exact sentences or phrases that came from one of your sources and are not your own words ■ Take extra care to use your own words when paraphrasing

What are the "roads to research" as discussed with PsychLearn?

○ Engage people in conversations and talk about your research interests. ○ Attend seminars and lectures about topics that are interesting to you and ask questions. ○ Pursue research topics that are interesting to you and then get involved. ○ Take notice of research opportunities in your community and then chart an action plan.

● What are the different kinds of research opportunities?

○ Independent and directed research. If you are interested in conducting your own research study or working on someone else's research, talk with your academic advisor about opportunities to do so on your campus. There are many different names for these opportunities-independent study, directed study, directed research, honors thesis, capstone project ○ Internships and fellowships. Internships and fellowships are formal experiences with clear objectives, mechanisms for training, and measurable outcomes. Internships and fellowships typically have set application, interview, and acceptance timelines. ○ Volunteering. In many cases, students get involved in research by volunteering their time to different kinds of research activities. ○ Part-time paid research positions. Part-time paid research positions are more difficult to find than are internship, fellowship, and volunteer opportunities, but they do exist. The money to pay for a research position

Know plagiarism and how to avoid it?

○ Plagiarism: The failure to properly credit the sources of information used in your work.

What are examples of between-subject design ?

○ Posttest-only, Pretest-Posttest, Matched Pair, Block.

● What is the difference between a resume and a curriculum vitae?

○ Résumé: A summary of personal accomplishments—including education, work and volunteer experiences, and skills—that is often submitted when applying for a job, internship, fellowship, or volunteer opportunity. ○ Curriculum vitae (CV): A summary of academic and scholarly accomplishments, including education

Identify ways to find research opportunities?

○ Tell everyone you know. Tell your professors, family, friends, classmates, academic advisor, acquaintances, and even the person sitting next to you on the bus that you want to get research experience. ○ Go to research presentations sponsored by the psychology department, Psi Chi (the International Honor Society in Psychology) or Psi Beta (the Community College National Honor Society in Psychology), and other campus groups. ○ Find out what research is going on in the psychology department. ○ Find out what research is going on in other departments on campus. ○ Find out what research is going on at other colleges and universities. ○ Find out what research is going on at local hospitals. ○ Connect with the career center on campus. ○ Look for SURF programs. Many schools have Summer Undergraduate Research Fellowship (SURF) programs ○ Look for opportunities in your community, your state, and the federal government. ○ Visit the APA, CUR, NSF, and NIH websites

Identify the proper APA style for different sections of a research paper

○ Title Page ■ Running head - title of up to 50 characters in all uppercase, flush left ■ Title of the Paper - brief, focused, centered, in bold, & same size font ■ Author's Name ● One double-spaced line below the title & centered ● Order of authorship, first contributed the most ■ Author's Affiliation ● Name of institution where research was conducted ● If different affiliations, place on own line and include superscript arabic numeral Abstract Page ■ Paragraph - no indent, only 1 paragraph ■ Header - the word "Abstract" is centered in bold ■ Keywords - indented 0.5 inch one double spaced line below abstract, the word "Keywords" is italized followed by Reference Page ■ Indented with a hanging indent ● All lines except first are indented 0.5in from left margin

What are different ways to contribute to others' research projects at every step of the scientific method?

○ practice skills you already have ○ enhance skills you want to improve, or ○ develop new skills you want to acquire