Lecture 1: Welcome to the World of Psychological Science PDF

Lecture 1: Welcome to the World of Psychological Science Zhou Fang Learning Objectives Today 1. Understand how to think scientifically 2. Understand why research methods are important for psychological science Think of Smiling improves your mood...

Lecture 1: Welcome to the World of Psychological Science Zhou Fang Learning Objectives Today 1. Understand how to think scientifically 2. Understand why research methods are important for psychological science Think of Smiling improves your mood Even a fake smile can activate facial muscles that signal the brain to release dopamine and endorphins, making you feel Something happier. You Have Emotions are contagious Loading… Being around positive and optimistic people can make you Learned feel happier, while prolonged exposure to negativity can increase anxiety or sadness. about How to you “prove” it to Psychology others? What if People Try to Prove it by…. (1) Angel will bless smiling people and make them happy. (2) People smile just should feel happier, shouldn’t they? (3) Dr. Fang told me that smiling makes people happy. (4) Your memory of happy things are linked with smile, so when you smile those memories should be reactivated. (5) I do feel happier when I try to make a smile.  Science is the acquisition of knowledge through observation, evaluation, interpretation, and Science and theoretical explanation. Psychological science, or psychology, is the scientific study of mind and behavior. Research Loading… The scientific method, or research method, is a set of systematic techniques used to acquire, modify, and Method integrate knowledge concerning observable and measurable phenomena. Observable and Measurable To use the scientific method, we make measurable observations. Something is observable if it can be perceived directly through the senses (e.g., sight, hearing, touch) or indirectly using tools or instruments. For instance, we can directly observe student enrollment changes or test scores. However, some behaviors, like learning, cannot be directly observed. Instead, we indirectly measure them, such as through pre- and post-tests. Something is measurable if it can be quantified or assigned a specific value using a standard unit or scale. Similar to learning, abstract behaviors like love, resilience, or creativity require precise definitions to measure them indirectly. The Six Steps of the Scientific Method Step.1 Identify a Problem (1) Determine an Area of Interest. (2) Review the Literature. (3) Identify New Ideas in Your Area of Interest. (4) Develop a Research Hypothesis A research hypothesis or hypothesis is a specific, testable claim or prediction about what you expect to observe given a set of circumstances. Step 2: Develop a Research Plan Define the Variables Being Tested. A variable is any value or characteristic that can change or vary from one person to another or from one situation to another. An operational definition is a description of some observable event in terms of the specific process or manner by which it was observed or measured. Identify Participants or Subjects and Determine How to Sample Them. Select a Research Strategy and Design. Evaluate Ethics and Obtain Institutional Approval to Conduct Research. Step 3: Conduct Analyze and Evaluate the Data as They Relate to the the Study Research Hypothesis. Data (plural) are measurements or observations Step 4: Analyze that are typically numeric. A datum (singular) is a single measurement or observation, usually called and Evaluate the a score or raw score. Summarize Data and Report the Research Results Data Step 5: Communicate Communicating your work allows other professionals the Results to review your work to learn about what you did, test whether they can replicate or build upon your results Loading… or use your study to generate their own new ideas and hypotheses. Step 6: The most typical ways of sharing the results of a study are orally, in written form, or as a poster. Generate More New Ideas Other Ways to Know the World Tenacity Tenacity is a method of knowing based largely on habit or superstition; it is a belief that exists simply because it has always been accepted. Intuition Intuition is an individual’s subjective hunch or feeling that something is correct. Intuition is sometimes used synonymously with instincts. Authority Authority is knowledge accepted as fact because it was stated by an expert or respected source in a particular subject area. Rationalism Rationalism is any source of knowledge that requires the use of reasoning or logic. Empiricism Empiricism is knowledge acquired through observation. This method of knowing reflects the adage “seeing is believing.” Theory-Hypothesis-Data A theory is a well-established framework that explains phenomena by integrating facts and observations. From a theory, researchers derive a hypothesis—a specific, testable prediction. Data collection tests the hypothesis through systematic observation and measurement. Findings may support or refute the theory. In most cases, psychological studies can only provide support for certain theories but cannot prove them. The Goals of Behavioral Science Quick Check What is the primary purpose of the scientific method? A) To generate opinions about a topic B) To systematically investigate phenomena and acquire knowledge C) To collect data without analyzing it D) To prove a hypothesis correct Extended Readings Textbook Chapter 1 Fact Sheet 1 (on canvas) Lecture 2: Data and Variables Zhou Fang Learning 1. Understand the Concept of Variables Objectives 2. Distinguish Types of Variables 3. Understand the Concept of Data and Dataset Today Variable Loading… How Many Variables Can You Find Here?  Variables can be broadly classified into two categories: Quantitative Variables are numerical and represent measurable quantities. Examples include height, Types of Variables Loading…reaction time, or number of pets. Qualitative Variables are categorical and represent groupings or characteristics. Examples include gender, eye color, or preferred type of music.  Continuous Variables: Can take any value within a range. Reaction Time: Measured in seconds (e.g., 1.23 seconds, 2.56 seconds). Stress Level Scores: Scale from 0–100, where scores can be 45.5, 72.3, etc. Quantitative Brain Activity: Measured in frequency or amplitude (e.g., EEG signals in Hz). Variables: Discrete Variables: Can only take specific values, often Discrete vs whole numbers (all qualitative variables are also discrete). Continuous Number of Correct Answers: E.g., 0, 1, 2, 3 correct answers on a test. Number of Siblings: E.g., 1 sibling, 2 siblings. Frequency of Behavior: E.g., 3 instances of aggression during an observation. In practice, discrete variables with a sufficiently large number of values, such as income, are often treated as continuous. Discuss: Quantitative Variables are numerical and What Type represent measurable quantities. Examples include height, reaction time, or number of pets. of Variable Qualitative Variables are categorical and represent groupings or characteristics. is Your Examples include gender, eye color, or preferred type of music. UIN?  Quantitative variables are about measuring or counting. Quantitative = These variables are expressed as numbers and represent quantities. “Quantifying” Age (e.g., 20 years old) means you have been to this Something world for 20 years, age is quantifying the length of time since you were born.  Quantitative data can be used for calculation, especially Quantitative basic operations (addition, subtraction, multiplication, and division). Variable Should 1 + 1 = 2: You have one cat, I have one cat, together we have two cats. be Suitable for 1 x 2 = 2: A has one sibling and B has two, then B has Basic Operations twice the number of siblings as A.  Interval data consists of numeric values with equal intervals between measurements. There is no true zero point, meaning zero does not represent an absence of the variable. IQ Scores: A score of 0 does not mean "no intelligence." Temperature: Measured in Celsius or Fahrenheit (e.g., 10°C, 20°C). Interval or Ratio Likert Scales: Treated as interval in advanced analysis (e.g., 0 = Strongly Disagree, 5 = Strongly Agree). in Numeric Ratio data is numerical, with equal intervals and a true zero point, meaning zero represents the complete absence of the variable. Number of Errors: E.g., 0 errors, 5 errors. Heart Rate: Measured in beats per minute (e.g., 0 bpm means no heart activity).  Qualitative Variables can be divided into: Nominal Variables: Categories without a meaningful order. Qualitative Gender: Male, Female, Non-binary. Therapy Type: CBT, Mindfulness, Psychoanalysis. Variables: Nominal vs Loading… Ordinal Variables: Categories with a meaningful order. Satisfaction Ratings: Very Unsatisfied, Unsatisfied, Ordinal Neutral, Satisfied, Very Satisfied. Education Levels: High School, College, Graduate School. Please note although Likert scales are ordinal variables, in practice psychologists often treat it as numeric.  Sometimes the type of a categorical variable is not clear, it depends on whether you can find a meaningful order. For example, marital status is typically accepted as a Meaningful nominal variable just like gender and race. However, you can also categorize them as “never married”, Order “married”, and “once married”; which follows a meaningful order. The key difference between nominal and ordinal variables is that in ordinal variables, higher-ranked categories are assumed to encompass or build upon the "experience" of the lower levels.  Ordinal variables can be coded with numbers, but these numbers only represent order. Numbered In other words, the numbers can not be used for calculations. For example, if we code education levels Ordinal Variables as 0=under high school, 1= high school graduate, 2=college graduate; the difference between 2 and 1 is not the same as 3 and 2. Transferring Quantitative to Qualitative Quantitative data can often be transformed into qualitative data by grouping or categorizing numerical values into distinct categories. This process simplifies the data, making it easier to interpret or analyze in contexts where detailed numerical precision is not necessary. For example, in developmental psychology, we also mark age into age groups, all the way from infant to late adulthood. Dummy Variable: Quantitative and Qualitative A dummy variable is a numerical variable used in statistical modeling to represent categorical (qualitative) data. It takes on values of 0 or 1 to indicate the presence or absence of a specific category or attribute. Common dummy variables in psychology include biological sex, treatment vs. control group, etc. You can often transfer a categorical variable with more than 2 categories to a dummy by combining the categories. For example, you can combine education levels to “no college degree” and “college degree or higher”.  Data are facts collected together for reference or analysis. Data and Dataset A dataset (or data set) is a collection of related data that's usually organized in a standardized format. Raw Data and Processed Data Raw Data refers to the original, unprocessed information collected during a research study or experiment. It is also known as source data, atomic data, or primary data. Raw data is in its most basic and unorganized form, representing the original observations, measurements, or responses. Raw data comes in various formats. In addition to being ready for use as quantitative or qualitative variables, data can also exist as text data, comprising words or sentences like names or open-ended survey responses. Image data, such as photographs or brain scans, offers visual insights, while audio data, like speech recordings or heartbeats, captures sound-based information. Data can even take the form of videos, providing dynamic and detailed observations. Processed Data is the transformed or analyzed version of raw data. It has undergone corrections, cleansing, aggregation, or other forms of transformation to remove errors and organize the information.  Data and Dataset License Date of Heigh Weigh Eye License Expiration Number Name Gender Birth Age t (cm) t (kg) Color State Class Date A12345678 John 5/15/199 Male 34 180 75 Brown Texas Class C 5/15/2026 9 Smith 0 In a dataset, columns are referred to as Emily variables. Each column represents a specific B98765432 8/22/198 Californi Johnso Female 39 165 60 Blue Class M 8/22/2028 characteristic or attribute being measured in 1 n 5 a the dataset. Michae C65498732 12/3/199 Rows in a dataset are called cases or 1 l Male 5 29 175 82 Green Florida Class E 12/3/2027 observations. Each row corresponds to a Brown single unit of analysis, such as a participant D32145698 Sarah 7/11/200 New Female 24 160 55 Hazel Class D 7/11/2029 in a study, a specific event, or a single trial. 7 Wilson 0 York The cells in a dataset contain the values of E789123456 James Male 3/20/199 32 185 90 Black Texas Class C 3/20/2025 Lee 2 the data. Each cell is the intersection of a column (variable) and a row (observation), representing the value of a specific variable for a particular case. In-Class Activity Form groups of 4–5 students. Introduce yourselves to your group members to create a dataset of the group members that includes at least one of each type of variable: Continuous Quantitative Discrete Quantitative Nominal Qualitative Ordinal Qualitative A dummy other than the four Grading rubric: 1 point for correctly identifying at least one variable, and 0.5 points for each additional variable identified. Quick Check Which scale of measurement allows for meaningful zero and all arithmetic operations? A) Nominal B) Ordinal C) Interval D) Ratio Which of the following is an example of nominal data? A) Rankings in a competition (1st, 2nd, 3rd). B) Eye color (Brown, Blue, Green). C) Temperature in Celsius. D) Height in centimeters. What distinguishes qualitative variables from quantitative variables? A) Qualitative variables can only be discrete. B) Quantitative variables are always continuous. C) Qualitative variables describe categories or labels. D) Quantitative variables involve ranks or orders Extended Readings Textbook Chapter 4.1-4.4 If you want to read a simple version: https://www.abs.gov.au/statistics/understanding- statistics/statistical-terms-and-concepts/variables A more extended one: https://www.mayo.edu/research/documents/data-types/doc- 20408956 Lecture 3&4: Population and Sample Zhou Fang Learning Define populations and samples and their roles in research. Objectives Describe key sampling methods and their applications. Today Understand the implications of sampling bias.  My girlfriend was buying a handbag to take to school, most of our classmates/friends are girls. She selected a few that she liked and felt indifferent about, then asked me which one looked better. While I was trying to figure out, she said, "Never mind, asking you is pretty useless." Whose Opinions Then she took photos of the bags and asked her two does She Really Loading… best female friends for their opinions via messages. She used their feedback to decide and bought one. Care? Why does she say my opinion is pretty useless? Does that mean she doesn’t care about my opinion? Why does she ask her two besties? Does that she mainly care about their opinions? Whose opinions does she really care?  The population (or target population) represents the entire group of individuals or objects that the researcher aims to generalize the study findings to. A sample is a smaller subset chosen from the Key Concepts population. The sampling frame is a list or source used to select the sample. It represents the portion of the population that the researcher can realistically access, also known as the accessible population. Example 1: Population: All college students in the country. Accessible Population: College students at TAMU Studying the (college students in one specific city or district that the Mental Health of Loading… researcher can access) Sampling Frame: A list of enrolled students provided US College by the registration office. Sample: 300 students randomly selected from that list Students to participate in the study.  Population: All patients worldwide diagnosed with Example 2: generalized anxiety disorder (GAD). Examining the Accessible Population: Adults with GAD who are seeking treatment at mental health clinics in College Effects of Station-Bryan area. Sampling Frame: A list of patients with GAD at these Cognitive- clinics who meet the inclusion criteria (e.g., ages 18– 50, no history of substance abuse, and not currently on Behavioral medication for anxiety). Therapy (CBT) Sample: 60 patients randomly selected from the list who agree to participate in an 8-week CBT program on Anxiety and complete pre- and post-treatment assessments of anxiety levels.  In groups of 4 or 5, discuss the following question: As a student, you want to study the relationship between social media usage and academic performance among college students. Discussion What is your population? What is your accessible population? What could be your sampling frame? What would your sample be?  Studying an entire population is often unrealistic due to Why do We Take time, cost, and logistical challenges. a Sample? Sampling allows researchers to collect data quickly and analyze it more effectively.  Probability Sampling: Each member has a known Types of chance of selection. Non-Probability Sampling: Individuals are selected Sampling based on convenience, judgment, or other non-random criteria. Not all individuals have a chance of being Methods included in the sample.  Simple Random Sampling: Each individual has an equal chance of being selected. Probability Systematic Sampling: Selecting every nth individual from a list. Sampling Stratified Sampling: Dividing the population into strata Methods (groups) and sampling from each. Cluster Sampling: Dividing the population into clusters, then randomly selecting clusters.  A method where each individual in the population has Simple Random an equal probability of being selected. Sampling Loading… Using a random number generator to select participants.  A method where every nth individual is selected from a Systematic list after a random start. Sampling Surveying every 10th person on an alphabetical list.  Dividing the population into subgroups (strata) based on a characteristic, then randomly sampling from each stratum. Dividing by age groups (e.g., 20-30, 30-40) and Stratified sampling from each. Sampling Stratification can be proportionate or disproportionate. With proportionate stratification, the sample size of each stratum is proportionate to the population size of the stratum.  Identify Strata: Divide the population into meaningful subgroups based on a variable of interest (e.g., age groups: 18–25, 26–35, etc.). Determine Proportions: Proportionate Calculate the proportion of each stratum in the total population. Stratification Allocate Sample Size: Assign sample sizes to each stratum proportionally. If Stratum A constitutes 40% of the population, 40% of the sample will come from Stratum A. Select Randomly: Perform random sampling within each stratum.  Population: A small town has 1,000 residents, divided into three age groups: 0–25 years: 400 residents (40% of the population). 26–40 years: 300 residents (30%). Practice 41+ years: 300 residents (30%). Sampling: If the researcher wants a sample of 100, what should be the sample size for each age group? 40-30-30 RESPECTIVELY  Dividing the population into clusters (e.g., schools, neighborhoods), then randomly selecting some clusters and surveying everyone within them. Cluster Sampling Selecting certain schools and surveying all students within. Non-Probability Convenience Sampling: Selecting individuals who are easy to reach. Sampling Quota Sampling: Setting quotas for certain Methods characteristics, then sampling to meet these quotas. Convenience Sampling individuals who are readily available. Surveying people at a shopping mall. Sampling  Setting quotas to ensure certain groups are represented in the sample. Quota Sampling Ensuring 50% of the sample is male and 50% is female. Voluntary Allowing individuals to self-select into the study by Response responding to an open invitation. Online polls where users choose to participate. Sampling Judgmental Selecting participants based on specific criteria set by the researcher. (Purposive) Choosing only experts in a certain field for an interview Sampling study.  Recruiting participants via referrals from initial Snowball subjects, often used for hard-to-reach populations. Studying social network connections by having Sampling participants refer others.  Form groups of 4–5 students. Your task is to investigate students' favorite dining hall on campus. As a group, In Class Activity design three plans to recruit participants using different sampling methods other than simple random sampling. For each method, describe how you would implement it. Extended Readings Chapter 5.1-5.4 Fact Sheet 3 https://www.scribbr.com/methodology/sampling-methods/ Lecture 4.5: Representative Sampling and Bias Zhou Fang  It was peak tourist season in Los Angeles, and rumors were everywhere: Disneyland tickets were impossible to get. A local reporter decided to uncover the truth and headed straight to the park gates to interview visitors. As he stood near the entrance, he began asking random people one simple question: “Do you have a ticket?” Wow! Everyone A cheerful family of four replied, “Of course! We’ve had these tickets for months!” Has a Ticket! He moved to a group of friends wearing matching Mickey Mouse hats. “Do you have a ticket?” “Yep,” they said, flashing their entry passes. Everyone he spoke to had a ticket. After an hour of interviews, the reporter scratched his head, puzzled. If tickets are supposedly sold out, how does everyone here have one? Back at the newsroom, he published his story: “Disneyland Tickets Not Hard to Get: Everyone I Asked Got One!”  Sampling Bias occurs when a study's selection process favors certain groups, making the sample unrepresentative of the target population. Nonresponse Bias arises when participants choose not Potential Bias to respond, leading to a sample that only reflects those willing to participate. What is A sample that accurately reflects the characteristics of the population. Representative Ensures findings can be generalized to the broader population. Sampling? Reduces the risk of bias. Simple Random Minimal bias if done correctly. Sampling and Loading… Issues arise from incomplete sampling frames or execution errors. Bias Systematic Efficient and reduces random errors. Sampling and Bias arises when a hidden population pattern aligns with the selection interval. Bias Stratified Reduces bias by ensuring subgroups are represented. Sampling and Bias can occur if strata are poorly defined. Bias  Useful for large populations. Cluster Sampling Bias occurs if clusters are not representative of the and Bias population. Convenience Easy and quick to implement. Sampling and High risk of selection bias due to limited diversity. Bias Voluntary Attracts participants with strong opinions. Response Prone to voluntary response bias and lacks Sampling and representativeness. Bias  Ensures specific subgroups are included. Quota Sampling Bias arises from non-random selection and potential and Bias overrepresentation.  Allows researchers to focus on specific groups or Judgmental individuals relevant to the study. Sampling Subjective selection by the researcher can introduce personal or unintentional bias, reducing objectivity.  Access to Hard-to-Reach Populations. Snowball Participants often recruit others with similar characteristics, limiting diversity. Sampling Those without strong social connections or part of smaller groups may be excluded.  What is the population in a research study? a) The group that participates in the study b) The entire group the researcher wants to generalize results to c) The group of people who responded to the survey d) The sample used for the study What is a sample in research? a) A subset of the population selected for study Exercise b) The complete list of participants c) The entire population being studied d) A list of individuals in a cluster What is the sampling frame? a) The entire population the researcher is studying b) A list or source used to select the sample c) The specific criteria for selecting participants d) The location where the sample is collected  Which of the following is a characteristic of simple random sampling? a) Each individual has an equal chance of being selected b) Participants are selected based on their availability c) Researchers target a specific subgroup d) Selection is based on referrals from participants Stratified sampling involves: a) Selecting every nth individual from a list Exercise b) Dividing the population into subgroups and sampling from each c) Choosing participants based on their convenience d) Selecting participants by random referrals In cluster sampling, the researcher: a) Randomly selects clusters and surveys everyone in those clusters b) Surveys the entire population c) Ensures every individual has an equal chance of being selected d) Selects individuals based on their availability  What is a key feature of convenience sampling? a) It ensures every individual has an equal chance of being selected b) Participants are chosen based on ease of access c) It minimizes selection bias d) It randomly selects clusters from the population What is sampling bias? a) Errors that occur during data analysis Exercise b) Favoring certain groups during the selection process c) Errors caused by incomplete questionnaires d) Random errors in the data collection process What bias is common in convenience sampling? a) Overrepresentation of a subgroup easily accessible to the researcher b) Errors due to misclassification of strata c) Errors caused by random selection of participants d) Underrepresentation of strong opinions Extended Readings Chapter 5.7 https://www.scribbr.com/research-bias/sampling-bias/ Lecture 5: Introduction to Data Cleaning Zhou Fang  Understand the purpose and importance of data cleaning in research. Learning Identify common issues in raw data and their impact on analysis. Objectives Apply systematic data-cleaning techniques using practical examples. Today This lecture is “blue”, meaning the material we covered today won’t be included in quizzes or exams. Why is Data Cleaning Loading… Important?  Understand the dataset: Variables, data types, and context. Stages of Detect issues: Missing values, duplicates, outliers, inconsistent Data formatting. Resolve issues systematically: Cleaning Apply methods like imputation, deletion, or transformation. Validate the cleaned data: Ensure corrections didn’t introduce new errors.  Missing Data Common Duplicates Data Issues Loading… Outliers Inconsistent Formatting Typographical Errors  Missing data occurs when values are left blank due to errors or participant non-responses. It may appear as blank cells, "None," or placeholders like "NaN." Missing It can be handled by removing incomplete entries or imputing missing values using statistical methods. Data Simple imputations include using average (for numerical variables), using most common category (for categorical variable), or using the value from similar observations. Fill the Missing Values Name Age Gender Class_Standing Major Alice 20 Female Sophomore Psychology Bob 21 Male Junior Psychology Charlie 24 Male Biology David 20 Male Sophomore Psychology Eve 22 Female Freshman Mathematics Frank Male Junior Grace 20 Freshman Economics Hannah 19 Female Freshman Psychology  Duplicate entries occur when the same data is recorded multiple times, often due to data entry Duplicate errors. Removing duplicates ensures that results are not Data skewed by redundant information. Duplicate data often requires identification through other unique variables. Discuss What duplicate Indicators can you think of?  Inconsistent formats, such as dates or text Inconsistent capitalization, can make analysis difficult. Standardizing formats during data cleaning improves consistency and interpretability. Formatting Examples include mixed date formats, inconsistent capitalization, and incorrect variable types.  Outliers are extreme values that differ significantly from others in the dataset. They can distort the Outliers results and need to be carefully examined before Loading… analysis. Reaction times in psychological experiments may have extreme values due to distractions during trials. How to Investigate: Determine if the outlier is an error (e.g., a typo) or represents valid variability. Handle Transform: Apply transformations (e.g., logarithms) to reduce the effect of outliers on analysis. Outliers Exclude: If caused by error, remove the data point. If valid but extreme, analyze it separately.  Typographical errors are mistakes in data entry, such as misspellings or incorrect numerical inputs. These Typographical errors can occur during manual entry or data transcription. Errors While most typos can be corrected using logic, some may require manual review or context-specific adjustments to ensure accuracy.  Review the provided dataset carefully. In-class Identify all the data issues that require cleaning. Propose how you would clean or resolve each issue. Activity  Design a Clear Data Collection Plan Avoid Dirty Use Validation Rules During Collection Data in Data Reduce Manual Entry/Standardize Data Entry Formats Collection Conduct Pilot Testing Train Data Collectors and Participants Extended Readings https://www.youtube.com/watch?v=kNl7YDN-_js https://www.sigmacomputing.com/resources/learn/what-is-data- cleaning Lecture 6: Independent & Dependent Variables Zhou Fang  Define key variables used in research, including Learning independent, dependent, confounding, mediating, and moderator variables. Objectives Distinguish between dependent and independent variables in experimental and non-experimental research. Today Explain the role of confounding and mediating variables in influencing research outcomes.  Alice found that people who eat fast food more frequently are more likely to be overweight. She concludes that eating fast food causes people to gain weight, so we should avoid fast food to maintain a healthy weight. Do You Agree Bob found that people who purchase gym memberships with Them? Loading… tend to look more fit. He states that purchasing a gym membership directly leads to improved physical fitness, so we should sign up for a gym membership to get in shape even if we don’t have time to use it. Caitlyn observed that as Dr. Fang gained weight, the area of the Amazon rainforest was decreasing. She concludes that Dr. Fang's weight gain is causing soil erosion, so we should help Dr. Fang lose weight to save the rainforest. Variable A variable is any value or characteristic that can change or vary from one person to another or from one situation to another. By their rules, the most important two types of variables are: Independent Variable (IV) – The Cause Dependent Variable (DV) – The Effect  The dependent variable is the variable that is being measured or tested in an experiment. For example, we want to know if income influences Dependent happiness, the happiness is the dependent variable. Variable (DV) – Loading… There is usually only one dependent variable in a study. In some studies, particularly in exploratory or multidisciplinary research, multiple DVs may be used The Outcome to capture different dimensions of the outcome. For example, in a study on lecture mode and learning outcome, DVs could include both art and science learning outcomes. Independent Variable (IV) – The Cause An independent variable or factor is the variable that is manipulated in an experiment. For example, we want to know if income influences happiness, the income is an independent variable. There can be multiple independent variables in a study, for example, we can examine what variables might influence happiness.  What are the IV and DV in the following studies? The effect of class size on student performance. Practice Investigates whether meditation reduces stress levels. If a new advertisement increases product sales. Study the effect of a new drug on blood pressure. Confounding Variable – The Hidden Factor A confound is an outside factor that influences both the IV and DV. It makes it unclear whether the IV is actually causing the effect. Children who wore eyeglasses had better reading scores, vocabulary scores, and math scores compared to those who did not. While it could be because wearing glasses enhances learning ability, it could also be that extended study time leads to a decline in vision. Mediating Variable – The Bridge A mediator explains how or why an IV affects a DV. It helps clarify the process of the relationship. Steps to test if mediator exists: IV affects DV. IV affects Mediator. Mediator affects DV. If IV-DV effect weakens when the mediator is included, mediation exists.  A moderator is a variable that changes the strength or direction of the relationship between IV and DV. Moderator Variable- It helps explain when or for whom the IV affects the DV. The Condition For example, the number of dining halls could affect students’ life satisfaction, but it has a much greater impact on students living on campus. Practice A study finds that people who exercise more have better heart health. However, people who exercise more also tend to eat healthier diets. Loading… A study shows that students who sleep more perform better on exams. The researchers find that better sleep improves focus, which in turn improves exam performance. A study finds that interactive teaching methods increase student engagement, but this effect is stronger for students who prefer hands-on learning. A study finds that higher income is associated with greater life satisfaction. However, people with higher incomes also tend to have better access to healthcare, which could explain their higher satisfaction. A study finds that increased social media use is linked to higher rates of depression. However, people who use social media more also tend to have less face-to-face social interaction, which could contribute to depression. Practice A study finds that drinking coffee increases productivity, but this effect is stronger for people who are not regular coffee drinkers. A study finds that higher education levels are associated with higher incomes. However, people with higher education levels also tend to have more professional networks, which could explain their higher incomes. A study finds that higher temperatures are associated with increased ice cream sales. However, higher temperatures also lead to more people visiting the beach, which could increase ice cream sales. A study finds that job training improves job performance, but this effect is stronger for employees who receive mentorship during the training. A study finds that higher stress levels are associated with poorer sleep quality. However, people with higher stress levels also tend to drink more caffeine, which could contribute to poor sleep. In Class Activity Design a simple study on college students' life satisfaction. Identify three independent variables that may influence life satisfaction. For each independent variable, determine a potential confounding variable and a potential mediator. For each variable, state how you would like to measure it. Extended Readings https://www.davidschuster.info/books/methods/moderating-mediating-and- confounding-variables.html