PSYC 2005 Exam #1 Study Guide

Basic assumptions about nature

-a physical universe exists -there is rendomness and unpredictableness but it is primarily orderly and predictible system -we can discover the principles of their universe through scientific research -knowledge of the universe is always incomplete

differential research

-comparing 2 or more groups of people ( Ex: male vs female; dem vs rep; grade level) -measurements must be the exact same for each group -setting and observational procedures must be constrained -only difference between groups should be their characteristics preexisting variable

Naturalistic Observation

-observe behavior of p's in natural environment -only constraint is on the observational method -don't usually have a strong hypothesis

how to find variance

-subtract mean from score giving each score's deviation score -square each each of these deviation scores this gives you the squared deviation -add up all the squared deviations (sum of squares ss) - divide the sum of squares by the number of scores, this dives you the average of the squared deviation

safegaurds for deception and concealment

1) Researcher's judgment that the dec/con poses no serious or long term risk 2) a debriefing, which involves explaining the true nature of the dec/con as soon as possible, usually immediately after the study

Phases of research process

1. idea generating phase 2. problem defining phase 3. procedure- design phase 4; observation phase 5. data analysis phase 6. interpretation phase 7. communication phase

what are some good questions to ask about scientific claims?

1. what is the nature of the evidence for the claims? 2. In what forms is the evidence reported? 3. What are the affiliations of the supposed scientists?

multimodal distribution

2 or more high points

continuous variable

A variable (such as age, test score, or height) that can take on a wide or infinite number of values between two values.

nominal scale

Lowest level of measurement, do not match the # system naming categories qualitative differences we can assign numbers to the categories but they are arbitrary Ex: place of birth, political affiliation can't use mean or median only mode; can't be skewed

pseudoscience

a collection of beliefs or practices mistakenly regarded as being based on scientific method. astrology, creationists, etc

theory

a formalized set of concepts that summarizes and organizes observations and inference, provides tentative explanations for phenomena, and provides the bases for making predictions

bimodal distribution

a frequency distribution having two different values that are heavily populated with cases

true zero

a non-arbitrary point indicating a zero level of the variable being measured

skewed distribution

an asymmetrical but generally bell-shaped distribution (of opinions); its mode, or most frequent response, lies off to one side

scientific model

another type of theory miniature representations of reality description or analogy that helps scientists understand something unseen/complex "mini theories" models represent reality, they don't duplicate it models can be concetual or abstract verbal or mathmatical

Histograms

barlike graph of a frequency distribution; height of bar = frequency

justice (relating to ethical principles in research)

both the risks and the benefits of research should be shared equally by all members of the population

Statistics

branch of math that deals with organization, analysis,, and interpretation of a group of numbers a method of pursuing truth, predicting out comes

Nominal variables

categorical variables for which the categories do not have a natural ordering

causal relationships

changes in one variable results in a predictable change in the other

variable

characteristics that can have different values

non-manipulated IV

classification variable researchers assign participants to groups based on preexisting characteristics organismic variables (IQ, age, political affiliation) are the most common types of variables in psych studies researchers do NOT actively control but instead assigns groups

reification of a construct

confusing a construct for a fact don't do this

levels of constraint

coninuum of demands on the adequacy of information constibutes the second dimension of our model of research explanatory research is less refined, has low constraint studies don't always need to be precise and controlled

How does a research avoid measurement errors?

create a well thought out operational definition of the measurement procedure

deception/concealment

deliberately misleading ps by giving them false information or by withholding information

How to understand a group of scores

describe the scores in terms of representative (or typical) values like an average gives the central tendency main representative # used is the mean

variability

describes how spread out the numbers are variance or standard deviation

Two Branches of statistical methods

descriptive statistics and inferential statistics

data

facts about research

misleading graphs are caused by

failure to use equal intervals exaggeration of proportions (not starting scale at 0)

rectangular distribution

frequency distribution in which all values have approximately the same frequency

unimodal distribution

frequency distribution with one value clearly having a larger frequency than any other

correlation research

greater constraint on procedures used to measure behavior setting can range from naturalistic to very controlled lab quantification, so needs precise and consistent procedures

Why was B. F. Skinner against statistics?

he thought there was a lot of information lost when averaging scores

Ratio scale

highest level of measurement interval scale with a TRUE ZERO can use math operations score data, full number system meaning full to talk about the ratio of the score (ex: someone is 2x as tall as someone else)

kurtosis

how much the shape of a distribution differed from the normal curve in terms of whether the curve is more peaked or flat

What are the properties of the abstract number system?

identity magnitude equal intervals true zero

contructs

inferred events, often used by scientists as if they really exist as facts and actually have a relationship with the observable events

Case Study Research

intensive study of an individual observe p's, access records, actively intervene in the p's functioning, by interviewing and testing somewhat more constrained

ratio scale variable

interval variable with a true zero point (zero indicates complete absense of the variable), such as height in centimeters or duration of illness

autonomy (relating to ethical principles in research)

it is the right of the ps to decide whether they will participate and they must be given sufficient information on which to make that decision (informed consent)

Evaluative Bias of language

language inserts subtle judgments into the descriptions of objective behavior certain words have certain connotations

Ordinal scales

magnitude and identity order ranking interval unclear Ex: social class, school rank

interval scales

magnitude, id, and interval scaling close to matching # system but still does not have a true zero Temperature (C & F) Used a lot in psychology (IQ scale)

kinds of independent variabl

manipulated and non manipulated

ceiling effect

many scores pike up at the high end of a distribution because it is not possible to have any higher score

floor effect

many scores pile up at the low end of a distribution because it is not possible to have any lower score

which events are not considered facts?

memory, emotion, intelligence, attitudes, creativity, etc. anything NOT directly observable

nominal fallacy

mistake the naming of phenomenon for an explanation

mode

most common value peak of histogram the mode will match the median if the data set is unimodal and symmetrical poor representation of control, but good for nominal scores

standard deviation

most widely used square root of variance the average amount that the scores deviate from the mean

scientific theories

must be testable and must be falsifiable solid empirical base and carefully developed constructs parsimonious

Why are all scientific assumptions, knowledge, and their theories tentative?

new knowledge will alter current ideas and theories

magnitude

number has an inherent order

equal interval variable

numbers stand for approximately equal amounts of what is being measured Ex: GPA, 0-10 scale

rank order variable (ordinal)

numeric variable in which the values are ranks such as class rank or finishing a race (1st, 2nd place)

score

particular person's value on a variable

Experimental Research

performance of p's under certain conditions research randomly assigns p's to condition or groups unlike differential research high constraint

values

possible number or category that a score can have

controls

procedures used to reduce extraneous influences important for validity

Ethical principles 2 basic categories

protect those who participate in research conduct and report research accurately and honestly

inductive reasoning

reason from particular to general (observations --> constructs)

central tendency

refers to the middle of the distribution 3 measures: mean, medium, and mode

validity

refers to the quality or precausion of a study, procedure, measure to how well it does what it is supposed to do Ex: does the study answer the question it posed? Does the test measure what we want it to measure? WHat does this lab study reveal about the real world?

parsimonious theory

relatively simple and straightforward and is preferred over a complex theory if the theories provide a complex theory of the theories provide equivalent predictive ability

availabilty heuristic

relies on the info that is most readily available, rather than the total body of info on a subject in order to make a decision

Frequency table

shows how frequently a score was used and mkes it easy to see the pattern in a large group of numbers -make a list of the values from lowest to highest -make tallies -make table with scores and # of times -find percentages

negative skewed distribution

skewed left

positive skewed distribution

skewed right

normal curve

specific bell shaped frequency distribution that is symmetrical and unimodal

Barnum statements

statements, such as those used in astrological forecasts, that are so general that they can be true of almost anyone

all-or-none bias

tendency to see a statements as either true or false, when most cases in science the statement is probabbilistic

similarity-uniqueness paradox

tendency to view two things as either similar or different from one another when they arae likely both

median

the middle score good representation when there are a few outliers that could affect the mean

Who holds personal responsibility for participants in research?

the researcher any ethical issues should be corrected before contacting any participants

what happens in the in the debriefing

the researcher informs the ps about the procedures and explains the rational for their use resolves misconceptions and discomfort Following ps sign a form either permitting or denying the use of their data

stereotype threat

the risk ofconfirming as a self characteristic, a negative stereotype about a group you happen to belong to certain situations create this threat like taking a challenging math test

beneficence (relating to ethical principles in research)

the risk to ps should be minimized and the benefit to ps and society must be weighed against the possible benefits

response-set bias

the tendency to respond in specific ways regardless of the situation or your experiences Ex: social desirability= the tendency to respond in a socially acceptable manner (inaccurate self reports to make yourself look better)

validity

theory makes specific testable predictions that further observation can confirm

constants

things that researchers avoid varying

facts

those events that we can observe directly and repeatedly

shapes of frequency distributions

unimodal bimodal multimodal rectangular symmetrical skewed

extraneous variables

unplanned and uncontrolled factors that can arise in a study and affect the outcome researchers must control these to avoid their potential effects

deductive reasoning

use general or abstract ideas to return to specifics, used to make predictions

Inferential Statistic

used to draw conclusions and to make inferences that are based on numbers from a research study but go beyond numbers, allows people to make inferences about large groups of people

Descriptive statistics

used to summarize and describe a group of numbers from a study

mean

usually the best measurement of central tendency

discrete variable

variable that has a specific value and that cannot have values between these specific values (rank order)

list the 5 research methods from lowest to highest level of constraint.

Naturalistic observation Case study Correlation research Differential Research Experimental Research

Scales of measurement

Nominal Scale Ordinal Scale Interval Scale Ratio Scale

equal interval

difference between units is the same anywhere on the scale

Measurement Error

distorts the scores so that the observations do not accurately reflect reality

symmetrical distribution

distribution in which the pattern of frequencies on the left and right side are mirror images of each other

identity (property of abstract # system)

each # has a particular meaning

functional theory

equal emphasis on deduction and induction most theories

Kinds of quantitative variables

equal interval variables Ratio scale variables rank order variables

manipulated iv

experimenter actively controls