ISS Exam 3

Experimental Designs

Research designs that allow researchers to make claims about causality.

Null Hypothesis

States that there is no effect or no difference between groups or conditions in a study.

Experimental Hypothesis

A statement predicting a specific effect or relationship between variables in a study.

Variable

Any factor that can be changed or measured in an experiment.

Control Variables

Factors kept constant in an experiment to ensure that observed effects are due to the independent variable.

Dependent Variables

The factor that is measured in an experiment, dependent on changes to the independent variable.

Independent Variables

The factor that is manipulated in an experiment to observe its effect on the dependent variable.

Demographics

Characteristics of a population, such as age, gender, and income level.

Control Group

The group that does not receive the experimental treatment, used for comparison.

Experimental Group

The group in a study that receives the treatment or intervention being tested.

Independent Groups Design (Between subjects designs)

A between-subjects design is an experimental setup where different participants are assigned to different groups or conditions, and each group experiences only one level of the independent variable. This means that each participant is only exposed to one condition, allowing researchers to compare the effects across different groups

Repeated Measures Design (Within subjects designs)

A within-subjects design is an experimental approach where the same participants are exposed to all levels of the independent variable. This means that each participant experiences every condition in the study, allowing researchers to compare their performance across different conditions directly.

Multivariate Designs

An experimental approach that involves the simultaneous examination of multiple dependent variables. This type of design allows researchers to understand how different independent variables may affect several outcomes at once, rather than focusing on just one dependent variable

Multi-method Analysis

A multi-method analysis is an approach in research that combines different methods or techniques to collect and analyze data. This can include qualitative methods (like interviews or focus groups) and quantitative methods (like surveys or experiments) within the same study. 

Double-Blind Design

An experimental setup where neither participants nor researchers know which group participants are in.

Matched-Groups Design

A design involving pairing participants based on certain characteristics before assigning them to conditions.

Counterbalancing

A technique used in experimental research to control for order effects, particularly in repeated measures designs. It involves varying the order in which participants experience different conditions to ensure that no single condition is consistently favored or disadvantaged due to its position in the sequence (helps increase internal validity). 

Fatigue from Repeated Testing

When participants become tired or disengaged from completing the same task multiple times.

Order Effects

Refer to the potential influence that the sequence in which participants experience different conditions can have on the results of an experiment. This can include various types of effects, such as practice effects, fatigue effects, carryover effects, and sensitization effects. 

Practice Effects

Improvements in performance due to repeated exposure to a task rather than the independent variable.

Placebos

Substances with no therapeutic effect used to control for psychological effects in research.

Random Assignment

A technique for assigning participants to different groups in a random manner.

Population

The entire group of individuals that a researcher is interested in studying.

Sample

A subset of the population selected for the actual study.

Random Sample

A sample where every member of the population has an equal chance of being selected.

Stratified Sampling

Dividing the population into subgroups and taking random samples from each stratum.

Snowball Sampling

A non-probability sampling technique where existing subjects recruit future subjects.

Purposive Sampling

Selecting participants based on specific characteristics relevant to the research question.

Saturation

The point in qualitative research when no new information or themes are emerging.

Quantitative Measures and Designs

Involves collection and analysis of numerical data to understand patterns and relationships. refer to the potential influence that the sequence in which participants experience different conditions can have on the results of an experiment. This can include various types of effects, such as practice effects, fatigue effects, carryover effects, and sensitization effects. 

Qualitative Measures and Designs

Focus on understanding meaning and experiences through non-numerical data. This approach often employs methods such as interviews, focus groups, or observations to gather rich, descriptive information. 

Correlational Designs

Examine relationships between variables without manipulating them.

Ethnographic Studies

A qualitative method involving in-depth exploration of a particular culture or social group.

Exploratory Studies

Investigate topics that are not well understood to gather preliminary insights. (qualitative methods)

Grounded Theory

A methodology to develop a theory based on data collected from participants.

Phenomenological Studies

Focus on understanding lived experiences of individuals regarding a specific phenomenon.

Immersion

The process of researchers engaging deeply with a setting to gather qualitative data.

Focus Groups

Qualitative method involving a small group discussing specific topics, guided by a moderator.

Structured Interviews

Interviews that follow a predetermined set of questions for consistency.

Unstructured Interviews

Flexible interviews that adapt to the responses of the interviewee for deeper insights.

Single-case Designs

Research methods examining a single individual, group, or situation over time.

Surveys

Tools used to gather information on opinions, attitudes, perceptions, and behaviors.

Quasi-experimental Designs

Aim to evaluate the effects of an intervention without random assignment to groups. In these designs, researchers compare groups that are already formed or that have been exposed to different conditions, which can introduce potential confounding variables.

Independent Variables in 4 X 2 X 3 Design

There are three independent variables: one with 4 levels, one with 2 levels, and one with 3 levels.

Levels in 4 X 2 X 3 Design

There are 24 conditions calculated by multiplying the number of levels of each independent variable.

Internal Validity

The extent to which a study can establish a cause-and-effect relationship between variables. Threats: confounding variables, selection bias, maturation, history, and instrumentation. 

External Validity

The generalizability of a study's findings to other settings, populations, or times. Threats: sample characteristics, setting, time, interaction events (how treatment interacts with participant characteristics) 

Attrition

The loss of participants from a study over time.

History

Events outside of the study that may impact participants' responses.

Instrumentation

Changes in measurement tools that affect the consistency of data collection.

Maturation

Changes in participants over time that can influence outcomes.

Selection Bias

Pre-existing differences affecting results if not randomly assigned to groups.

Testing Situation Bias

Bias caused by conditions under which a test is administered.

Test Bias

A situation where a test unfairly advantages or disadvantages certain groups.

Descriptive Statistics

Summarize or describe the main features of a dataset without drawing conclusions.

Inferential Statistics

Allow predictions or generalizations about a population based on a sample. (T-tests, ANOVA, Chi-square tests, Confidence intervals, p-values) 

Mean

The average calculated by dividing the total sum by the number of values.

Median

The middle value when the dataset is arranged in ascending order.

Mode

The value that appears most frequently in a dataset.

Central Tendency Measures

Mean, median, and mode are used to describe the center of a dataset.

Outliers

Data points that are significantly higher or lower than the other values.

Bimodal Distributions

Distributions with two peaks or modes.

Normal Distributions

Bell-shaped curve where mean equals median equals mode.

Standard Normal Distributions

A normal distribution with a mean of 0 and a standard deviation of 1.

Skewed Distributions

Distributions that are not symmetrical, stretching more on one side.

Variability / Spread

Refers to how much data points differ from each other and from the mean.

Alpha Value

The threshold for statistical significance in hypothesis testing, often set at 0.05. It represents the probability of making a Type I error, which is rejecting the null hypothesis when it is actually true. 

Effect Size

A measure of the strength of the relationship between two variables.

Power

The probability that a test will correctly reject a false null hypothesis.  It is influenced by sample size, effect size, and alpha level. 

Confidence Interval

A range of values likely to contain the true population parameter.

Correlation Coefficients

Measure the strength and direction of relationships between variables.

Sampling Error

The difference between a sample statistic and the actual population parameter.

Standard Error

Measure of the variability of a sample statistic from sample to sample.

Sample Size

The number of observations or data points collected in a study.

Independent Samples T-Test

This test is used to compare the means of two independent groups to determine if there is a statistically significant difference between them.

Repeated Measures Test

This test is used when the same participants are measured multiple times under different conditions. It helps to determine if there are significant differences in the means across those conditions.

One-Way ANOVA

This test is used to compare the means of three or more independent groups to see if at least one group mean is different from the others. For instance, it could be used to compare the effectiveness of three different teaching methods.

Two-Way ANOVA

This test extends the one-way ANOVA by examining the effect of two independent variables on a dependent variable, as well as any interaction between the two. For example, it could analyze how both teaching method and student gender affect test scores.

Chi Square

This test is used to examine the association between categorical variables. It helps to determine if the distribution of sample categorical data matches an expected distribution. For example, it could be used to see if there is a relationship between gender and preference for a particular product.