Psychology Unit 0
Unit 0: Intro to Psychological Science Practices
Psychology is Science
Psychology relies on the ‘scientific method’—using careful observation and testing to study human thoughts and behaviors.
A ‘Scientific Attitude’ involves:
Curiosity – Asking questions and exploring new ideas
Skepticism – Challenging assumptions and evidence
Humility – Accepting when we’re wrong and updating beliefs
Critical thinking helps us test ideas by examining assumptions, checking sources, identifying biases, evaluating evidence, and assessing conclusions
Critical observation is the ability to notice subtle details or gain them through analysis which allow people to manoeuvre situations more tactfully.
The scientific observation definition is any sensory experience about a natural phenomenon
Common Thinking Errors
Hindsight Bias: After an event happens, we tend to believe we "knew it all along." This shows why we need research—common sense is better at explaining the past than predicting the future.
Overconfidence: We think we know more than we do, often seeking information that confirms our beliefs
‘Scientific Inquiry’ helps correct these biases by testing ideas with data instead of assumptions.
The Scientific Method
A step-by-step process for studying behavior:
Theory – A big idea that explains behaviors or events
Hypothesis – A testable prediction based on the theory
Experiment & Observation – Collecting data to test the hypothesis
Peer Review – Other experts evaluate the research before publication
Operational Definitions – Clear, measurable definitions of concepts to ensure accurate results
Non-Experimental/Qualitative Research Methods:
These methods describe behavior but don’t show cause and effect:
Case Study: In-depth study of one person or small group to reveal universal truths.
Naturalistic Observation: Watching behavior in real-life settings without interference (e.g., tracking Twitter posts to see when people feel happiest).
Survey: Asking people about their thoughts or behaviors. To avoid bias, researchers:
Phrase questions carefully to lower social desirability bias (giving "acceptable" answers)
Pair surveys with other methods to confirm accuracy.
Sampling in Research
Sampling Bias: When a sample doesn’t represent the whole population
Random Sample: Every person in a population has an equal chance of being included
Correlation in Qualitative Research
Statistical measure (the 'correlation coefficient') helps us figure out how two variables vary together, and thus how well either one predicts the other –
In a graph, the closet to 1.0 has the strongest correlation
‘Scatterplots’, showing patterns of correlation
A ‘positive correlation’ exists when two variables operate in unison so that when one variable rises or falls, the other does the same – ‘negative correlation’ is when two variables move opposite one another so that when one variable rises, the other falls
Correlational research has a directionality problem—it can’t tell which variable is the cause, and which one is the effect – there could be a ‘third variable’
Regression toward the mean – phenomenon where if one sample of a random variable is extreme, the next sampling of the same random variable is likely to be closer to its mean
Failure to recognize regression can cause superstitious thinking
When a fluctuating behavior returns to normal, fancy explanations for why it does so are often wrong. Regression toward the mean is probably at work.
Illusory Correlation: perceiving a relationship where none exists, or perceiving a stronger-than-actual relationship (E.g., Gamblers, remembering past lucky rolls, may come to believe they influenced the roll of the dice by throwing gently for low numbers).
Experimentation factors
Experiments let researchers isolate the effects of one or more factors by (1) manipulating the factors of interest and (2) holding constant (“controlling”) other factors
Experimental group, in which people receive the treatment (such as reduced screen time), and a contrasting control group, in which they do not
Experimenters randomly assign people to each condition
‘Placebo Effect’ in research
‘Single Blind Procedure’: an experimental procedure in which the research participants are ignorant (blind) about whether they have received the treatment or a placebo
‘Double Blind Procedure’: research staff are ignorant (blind) about whether the research participants have received the treatment or a placebo
Reduces 'experimental bias' with researchers in their conclusion
A key goal in an experiment is ‘validity’ by taking in account steps
Experiments manipulate an ‘independent variable’, measure a ‘dependent variable’, and control ‘confounding variables’
Two different conditions: an experimental condition and a comparison or control condition.
Random assignment works to minimize preexisting differences between the groups before any treatment effects occur (reduces the confounding)
In experiment tests the effect of at least one independent variable (what we manipulate) on at least one dependent variable (the outcome we measure).
Having a control group allows researchers to determine a cause-and-effect relation between the independent variable and dependent variable.
Laboratories are designed to create controlled conditions to study psychological forces effectively
Measure and Obtain Experiment Results
Quantitative research methods use numerical data to represent degrees of a variable ( ., Likert scale, where questionnaire responses fall on a continuum like “strongly disagree”) (surveys)
Qualitative research methods rely on in-depth, narrative data (naturalistic observation)
Psychological science focuses less on specific behaviors than on revealing general principles that help explain many behaviors
Ethically Research and hold experiments
Informed consent gives potential participants enough information about a study to enable them to choose whether they wish to participate
Need to debrief participants and any temporary deception
Gathering Data
Descriptive Statistics – numerical data used to measure and describe characteristics of groups; include measures of central tendency and measures of variation
Histogram – a bar graph depicting a frequency distribution.
Reading a Histogram
Mode is the most highest score (the most frequently occurring score in a set of given numbers)
Mean is the average (add and divide)
Median is the middle number
Determines percentile rank
Range is the difference between the highest and lowest scores in a distribution.
Standard Deviation is a computed measure of how much scores vary around the mean score
Normal Curve is a symmetrical, bell-shaped curve that describes the distribution of many types of data; most scores fall near the mean
Skewed is a representation of scores that lack symmetry around their average value.
Inferential Statistics: numerical data that allow one to generalize — to infer from sample data the probability of something being true of a population.
Which measure of central tendency is most influenced by skewed data or extreme scores in a distribution: mean
Determines whether data can be generalized to other populations, which inferential statistics summarizes data
68-95-97 rule in normal distribution
Whether it is safe to infer a population difference from a sample difference it should follow:
Representative samples are better than biased (unrepresentative) samples. The best basis for generalizing is from a representative sample of cases, not from the exceptional and memorable cases one finds at the extremes
Bigger samples are better than smaller ones. Averages based on many cases are more precise than averages based on a few. More (randomly sampled) cases make the sample’s estimate more precise. Larger samples also make for a more replicable study — one that will find a similar estimate the next time.
More estimates are better than fewer estimates. A study gives one brief peek at what’s going on in the population. But the best thing to do is conduct multiple studies and combine all the estimates, using meta-analysis. Better to consider an entire forest of findings rather than focusing on a single study.
Point to remember: Statistical significance indicates the likelihood that the result would have happened by chance if the null hypothesis (of no difference) were true. But statistically significant is not the same as important or strong.
Effect size: the strength of the relationship between two variables. The larger the effect size, the more one variable can be explained by the other.