PSYC 220 Statistics Exam 2 SIUE

Frequency Table

A table for organizing a set of data that shows the number of times each item or number appears.

inductive reasoning

A type of logic in which generalizations are based on a large number of specific observations. E.g.: using observations of a small number of humans to make a statement about human behavior

Continuous variable

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

Data Structure II

Comparing two or more groups of scores: Experimental: to establish a cause and effect relationship, Ex: does eating breakfast have an effect on academic performance? Non-Experimental: quasi-independent variable (gender) Ex: does gender have an effect on quantitative math scores?

What are different types of surveys?

Demographics, Attitudes and beliefs, facts and knowledge, behaviors and behavior intentions

What types of research are surveys useful for?

Descriptive research - approval rates Correlational research - relationship between two variables Dependent measures for experimental research - how does manipulating mood affect well-being

How does the scientific method differ from authority and intuition?

Empirical (knowledge based on systematic observation) Public Objective

Authority

Experts say it's true Problem: establishing expertise, sometimes experts are wrong

T/F: Observing children's behavior while having them play a game in the laboratory is an example of participant observation.

False

Five Steps of the Research Process

HOMER: Hypothesize Operationalize Measure Evaluate Revise or Replicate

Key issues with contrived observation

Important to have good operational definitions and coding systems Sampling - limited to the specific behaviors being observed Interrater reliability - multiple raters should agree on what they are seeing

Key issues of Naturalistic Observation

Important to take detailed, objective notes Participant vs. non-participant Concealment vs. non-concealment

main parts of a journal article

Introduction Instruments (Materials) Procedure (Method) Results Discussion

Ordinal

Levels have quantitative distinctions, but intervals between levels are not necessarily equal (e.g.; values, place in a race) Uses Median to measure

types of response scales

Likert scale (bipolar - 7 Point or Unipolar 5 Point) Graphic (line or slider with anchors) Nonverbal (faces)

Data Structure I

Measuring two variables for each individual (as they exist naturally): correlational method Ex: Are people's salaries correlated with how much money they spend per month on clothing?

Symbol for a population

N

Skew

Negative skew: tail points to the left (easy exam) Positive skew: tail points to the right (difficult exam)

Equation for Standard Deviation

Population variance = SS/N Population SD = sqrt(SS/N) Sample variance = SS/n-1 Sample SD = sqrt(SS/n-1) How much individual scores differ from the mean

Difference between methods

Qualitative: Focuses on quality rather than quantity. Quantitative: Focuses on quantity rather then quality.

interviewer bias

A response bias that occurs because the presence of the interviewer influences respondents' answers.

Frequency Distribution

A summary chart, showing how frequently each of the various scores in a set of data occurs Proportion: f/N Percentage: F/N(100)

Equation for Variance

S^2 = SS/n-1 S^2 = Ex^2 - (Ex)^2/N all over N

what is meant by saying, "Science is empirical?"

Scientific answers are based on direct observation.

different types of descriptive methods

Systematic and objective description of variables. Examples: Behavioral Observation Archival Data Analysis Physical Trace Analysis

frequency

The ____ method for quantifying observations involves counting the number of times a behavior occurs in a specified period of time.

Variability

The extent to which the scores in a data set tend to vary from each other and from the mean.

signs of pseudoscience

Vague and imprecise language and statistics Overconfident and unrefutable claims Anecdotes and testimonials over scientific evidence Small and/or limited samples Only confirming, and no conflicting evidence is stated Example: website that is plastered with testimonials from family members that describe seemingly miraculous cures

What is the difference between reliability and validity?

Validity implies the extent to which the research instrument measures what it is intended to measure. Reliability refers to the degree to which scale produces consistent results, when repeated measurements are made.

archival reserch

When researchers apply behavioral observation techniques to historical records in order to measure behaviors that occurred in the past, the measurement process is called ____.

contrived observation

careful observation of one or more specific behaviors in a particular setting

Key issues in observation

certain behaviors are difficult to observe (memory, attitudes towards guns) defining a good coding system (try to consider all possibilities, be flexible during data collection) inter rater reliability - multiple raters shoud agree on what they are seeing Sampling - timing, people, location Reactivity and demand researcher bias and expectations

four issues to avoid with survey wording

confusing questions negative wording loaded questions double-barreled questions

reliability

consistency of measurement Example: Measurement that includes a large error component will be very low in this.

Categorical Variable

consists of separate, indivisible categories; theoretically no values can exist between two neighboring categories (e.g.; eye color, hometown, t-shirt size.)

Survey Research

gathering primary data by asking people questions about their knowledge, attitudes, preferences, and buying behavior

case studies

in depth description of individual person, organization, or event usually qualitative

Interval

intervals between levels are equal (e.g.; Likert Scale) Can use any to measure, often use Mean

Ratio

intervals between levels are equal and has rational zero (e.g.; pounds, inches, milliseconds) Can use any to measure, often use mean

Survey Formats

interviews panel studies (surveys over time ANES) paper survey online survey

Intuition

it "feels true" Problem: illusory correlation, no data, or biased data

quantitative methods

less information, but from large samples. Conclusions are drawn by statistics

Good Hypothesis is

logical testable refutable positive

an explanation is rational if it is based on _____________

logical deductions

Key issue of Participant Observation

lose some objectivity, but gain understanding (JG criticized for naming chimps, becoming part of troop)

How to deal with social desirability

manipulte or measure social desirability, social desirability scale, moral foundations questionnaire, moral sacredness scale Ex: how much money would you have to be paid to kick a puppy?

A measurement procedure is valid if it

measures what you intend it to measure

tenacity

method of acquiring knowledge that is being used when people accept information as true because it had been believed for a long time

qualitative methods

methods in which researchers study naturally occurring communication rather than assembling data and converting it to numbers (i.e., focus groups)

Mode

most frequently occurring score

Symbol for a sample

n

degrees of freedom

n-1 The number of individual scores that can vary without changing the sample mean. Statistically written as 'N-1' where N represents the number of subjects.

Types of observational methods

naturalistic observation participant observation contrived observation

Nominal

no numerical quantitative properties (e.g., Gender, SES) Uses Mode to measure

Scales Of Measurment

nominal, ordinal, interval, ratio

inferential statistics

numerical data that allow one to generalize- to infer from sample data the probability of something being true of a population Examples: t-tests, R^2 Statistical significance is determined by statistical analyses performed on the data (represented with a p value)

What type of question allows participants the greatest flexibility in deciding how to answer?

open-ended

In a race, runners come in first, second, or third place. This type of measurement would be on a _____________ scale of measurement

ordinal

The three measures of variability

range, standard deviation, variance

Determining a person's reaction time (in milliseconds) would involve measurement on a(n) ____ scale of measurement.

ratio

descriptive research

research methods that involve observing behavior to describe that behavior objectively and systematically example: A study examining the percentage of college-age students who are in committed relationships

Considerations for survey research

respondent carelessness (ex: entering letters when asked for zip code) social desirability (responding in a socially acceptable way) Agreement bias - people have a tendency to agree with terms regardless of their content People don't always know their own minds

The multiple-choice questions on this exam are examples of ____ items.

restricted

method

section of research article that can help you develop ideas for studies by changing characteristics of the participants or modifying the procedures for your own study

discussion

the section of a research article that is most likely to provide suggestions for additional research

Variance

the square of the standard deviation

sum of squares

the sum of each score's squared deviation from the mean ∑(x- xbar)^2

∑ (Sigma)

the sum of everything behind it

Use Median

there are extreme scores or skewed distributions There is a missing score A distribution is open-ended

T/F: The purpose of the correlational research strategy is to describe the relationship between two variables and measure its strength.

true

test-retest reliability

using the same test on two occasions to measure consistency

extraneous variable

variable in a study that is not being directly studied

independent variable

variable that is manipulated

Equation for Range

xmax-xmin difference between the lowest and highest score

content analysis

analyzing content of existing documents

archival research

analyzing previously compiled information

Median

(n+1)/2 the middle score in a distribution; half the scores are above it and half are below it

Why does correlation not equal causation?

-You do not know the direction of the effect. -It could be due to chance. - There could be a third variable that is responsible for the relationship.

What is a limitation of survey research?

The results are limited by the truthfulness of the participants.

T/F: A limitation of descriptive studies is that they cannot assess the causal relationship between variables.

True

T/F: One advantage of Likert-type rating scale questions is that they produce numerical scores that can be evaluated with standard statistical methods such as computing means.

True

T/F: The descriptive research strategy is the only strategy that is not concerned with relationships between variables.

True

scientific method

a circular process that leads to a tentative answer

Standard Deviation

a measure of variability that describes an average distance of every score from the mean

If people score high on one measure and score low on another measure, there is _______________

a negative relationship between two measures

The method of authority

a person relies on information or answers from an expert in the subject area, (e.g.; google the phone number for a restaurant.)

If people score high on one measure and also score high on another measure, there is ___________

a positive relationship between the two measures

participant observation

a research method in which investigators systematically observe people while joining them in their routine activities

construct

a variable that cannot be observed or measured directly, but is useful for describing and explaining behavior

Equation for Mean

add up all the numbers, then divide by how many numbers there are

Sampling error

an error that occurs when a sample somehow does not represent the target population Bigger Sample = Smaller Margin of Error Example: Politico, National sample of 2488 registered voters, approval rating 21 with a MoE of 2.0% which means it's really + or - 2%, or 39-43%.

Measures of Variability

describe the spread of the data (i.e., the shape of the distribution) Range & Standard Deviation

Measures of central tendency

describing data with a single score Mean, Median, and Mode

face validity

extent to which respondents can tell what the items are measuring example: A Self-Esteem Scale contains the item "I have high self-esteem."

internal validity

extent to which we can draw cause-and-effect inferences from a study example: research study finds that a group of participants who received relaxation training had lower exam anxiety scores than a group who did not receive training. However, the researcher suspects that the difference between groups may be caused by the fact that the participants in one group are generally smarter than those in the other.

external validity

extent to which we can generalize findings to real-world settings example: A researcher is concerned that experimental results obtained with college students may not apply to adults in the general population, which concerns external validity.

T/F: Basic research is intended to answer practical problems

false

descriptive statistics

statistics that summarize the data collected in a study Example: Exam 1 M = 38.19, SD = 6.29

Range

the difference between the highest and lowest scores in a distribution

concurrent validity

the extent to which two measures of the same trait or ability agree Example: You develop a new measure of self-efficacy and you find that people who score high on your measure also score high on a standardized measure of self-efficacy.