MFT study ch.1: Research Methods

Define a Case Study

a researcher studies a subject in depth. the researcher collects data about the subject through interviews, direct observation, psychological testing, or examination of documents records about the subject.

Validity

a test is valid if it actually measures the quality it claims to measure. two types: content and criterion

Content validity

a test's ability to measure all the important aspects of the characteristic being measured. EX: an intelligence test wouldn't have good content validity if it measured only verbal intelligence.

Hypothesis

a testable prediction of what will happen given a certain set of conditions.

Reliability

a tets has good reliability if it produces the same result when researchers administer it to the same group of people at different times.

subject or participant

an individual person or animal a researcher studies

Bias and the three main kinds

bias is the distortion of results by a variable. (sampling bias, subject bias, and experimenter bias)

Test-retest reliability

by giving the test to a group of people and then giving the test again to the same group of people at a different time.

Purpose of using descriptive or correlational research methods

can describe different events, experiences, or behaviors and look for links between them. However, these methods do not enable researchers to determine cause of behavior. Correlation is not same as causation.

common correlational research methods (4)

case studies, naturalistic observations, surveys, laboratory observations

meta analysis

comprises statistical methods for contrasting and combining results from different studies in the hope of identifying patterns among study results, sources of disagreement among those results, or other interesting relationships that may come to light in the context of multiple studies.[1] Meta-analysis can be thought of as "conducting research about previous research." In its simplest form, meta-analysis is done by identifying a common statistical measure that is shared between studies, such as effect size or p-value, and calculating a weighted average of that common measure. This weighting is usually related to the sample sizes of the individual studies, although it can also include other factors, such as study quality.

dependent variable

depends or is affected by the independent variable

Negatively skewed distribution

distribution with a few very low scores

Statistically significant

if it is unlikely that the difference was due to chance, then the observed difference can be considered statistically significant. A result is considered statistically significant if such a result occurs just by chance 5 or fewer times out of every 100 times a study is done. They call this statistical significance at the p<.05 (p less than or equal to .05). Statistical significance simply means that a result is probably not due to chance.

Criterion validity

is fulfilled when a test not only measures a trait, but also predicts another criterion of that trait. EX: one criterion of scholastic aptitude is academic performance in college. a scholastic aptitude test would have good criterion validity if it could predict college GPA.

Confirmation bias

look for and accept evidence that supports what they want to believe and ignore or reject evidence that refutes their beliefs. (which is why theory must be falsifiable)

principle of parsimony or Occam's razor

maintains that research should apply the simplest explanation possible to any set of observations

Positive correlation (+)

means that as one variable increases, the other does too. EX: the more years of education a person receives, the higher his or her yearly incomes is.

Negative correlation (-)

means that one variable increases, the other one decreases. EX: the more hours a high school student works during the week, the fewer A's he or she gets.

Measuring variation and two main forms

measures of variation tell researchers how much the scores in a distribution differ. the range and standard deviation.

correlation coefficient

measures the strength of the relationship between two variables. it is always a number between -1 and +1. The sign (+or-) of a correlation coefficient indicates the nature of the relationship between those variables.

experimenter bias and way to control for it

occurs when researchers ' preferences or expectations influence the outcome of their research. researchers see what they want to see rather than what is actually there. Double blind method is when neither the experimenter nor the subject knows which subjects come from the experimental group and which come from the control group.

random assignment

one way to control for extraneous variables. researchers place subjects in either exp or control group at random.

Standard

provides more information about the amount of variation in scores. it tells researchers the degree to which scores vary around the mean of the data.

Research must have what 4 components

research must be: replicable, falsifiable, precise, and parsimonious

subject bias

research subjects expectations can affect and change the subjects' behavior, resulting in subject bias.

Naturalistic observations

researchers collect info about subjects by observing them unobtrusively, without interfering with them in any way.

Laboratory observation

researchers perform lab observation rather than in a natural setting. give researchers some degree of control over the environment

Measures of central tendency

researchers summarize their data by calculating measures of central tendency, such as the mean(average), median(middle score when arranged in numerical order), and mode(most frequently occurring score). Most commonly used one is the mean, which is the average of the scores.

Inferential statistics

researches use them to figure out the likelihood that an observed difference was just due to chance.

operational definitions

state exactly how a variable will be measured

population

the collection of people or animals from which the researchers draw a sample.

Range

the difference between the highest and lowest scores in the distribution. calculated by subtracting the lowest score from highest score

placebo effect and way to control for it

the effect on a subject receiving a fake drug or treatment and subject believes they are getting the real drug or treatment. Single blind experiment is an experiment in which the subjects don't know whether they are receiving the real or fake drug in the experiment and reduces placebo effect

Variables

the events, characteristics, behaviors, or conditions that researches measure and study

interpreting correlation coefficients

the higher the correlation coefficient, the stronger the correlation. A +0.9 or a -0.9 indicates a very strong correlation; a +0.1 or -0.1 indicates a very weak correlation. A correlation of 0 means that no relationship exists between the two variables.

experimental vs control groups

the researcher manipulates one part of the treatment in the experimental group, but does not manipulate it in the control group. the variable that is manipulated is the independent variable.

Independent variable

the variable being manipulated by the researcher. thought to have some effect on the dependent variable

Alternate forms reliability

they measure this by giving one version of a test to a group of people and then giving another version of the same test to the same group of people

descriptive statistics

to organize and summarize their data, researchers need numbers to describe what happened. these numbers are called descriptive statistics and are typical presented in the form of histograms or bar graphs to show the way data are distributed.

scientific method

1. form hypothesis 2.make observations 3. refine theory 4. develop theory

demand characteristic

A demand characteristic is a subtle cue that makes participants aware of what the experimenter expects to find or how participants are expected to behave. Demand characteristics can change the outcome of an experiment because participants will often alter their behavior to conform to the experimenters expectations. Researchers typically rely on a number of different strategies to minimize the impact of demand characteristics. Deception is a very common approach. This involves telling participants that the study is looking at one thing when it is really looking at something else altogether.

frequency distribution

A frequency distribution is obtained by taking the score and splitting them into subgroups. The subgroups are then put on either a histogram (bar graph) or a frequency polygram (line graph). When a frequency distribution has most of the scores on one side of the graph it is considered skewed. If it has most of the scores in the middle with equal amounts on both sides it is considered symmetrical.

quasi experiment

A quasi-experiment is an empirical study used to estimate the causal impact of an intervention on its target population. Quasi-experimental research shares similarities with the traditional experimental design or randomized controlled trial, but they specifically lack the element of random assignment to treatment or control. Instead, quasi-experimental designs typically allow the researcher to control the assignment to the treatment condition, but using some criterion other than random assignment (e.g., an eligibility cutoff mark).[1] In some cases, the researcher may have control over assignment to treatment condition. Quasi-experiments are subject to concerns regarding internal validity, because the treatment and control groups may not be comparable at baseline.

applied research

Applied research refers to scientific study and research that seeks to solve practical problems. Applied research is used to find solutions to everyday problems, cure illness, and develop innovative technologies.

content analysis

Content analysis is a research tool used to indirectly observe the presence of certain words, images or concepts within the media (e.g. advertisements, books films etc.). For example, content analysis could be used to study sex-role stereotyping.

correlational research

Correlational studies are used to look for relationships between variables. There are three possible results of a correlational study: a positive correlation, a negative correlation, and no correlation. The correlation coefficient is a measure of correlation strength and can range from -1.00 to +1.00.

Cross sectional research

Cross-sectional research is a research method often used in developmental psychology, but also utilized in many other areas including social science and education. This type of study utilizes different groups of people who differ in the variable of interest, but share other characteristics such as socioeconomic status, educational background, and ethnicity. Takes place at a single point in time Does not involve manipulating variables Allows researchers to look at numerous things at once (age, income, gender) Often used to look at the prevalence of something in a given population

measures of central tendency

In measures of central tendency there is one number that is used to represent a group of numbers. This number is either the mean, median, or the mode.

selective attrition

In psychology experiments, selective attrition describes the tendency of some people to be more likely to drop out of a study than others. This tendency can threaten the validity of a psychological experiment.

type I and type II error

In statistical hypothesis testing, a type I error is the incorrect rejection of a true null hypothesis (a "false positive"), while a type II error is the failure to reject a false null hypothesis (a "false negative"). More simply stated, a type I error is detecting an effect that is not present, while a type II error is failing to detect an effect that is present.

null hypothesis

In statistical inference on observational data, the null hypothesis refers to a general statement or default position that there is no relationship between two measured phenomena.[1] Rejecting or disproving the null hypothesis—and thus concluding that there are grounds for believing that there is a relationship between two phenomena (e.g. that a potential treatment has a measurable effect)—is a central task in the modern practice of science, and gives a precise sense in which a claim is capable of being proven false.[2] The null hypothesis is generally assumed to be true until evidence indicates otherwise. In statistics, it is often denoted H0 (read "H-nought", "H-null", or "H-zero").

p-value

In statistics, the p-value is a function of the observed sample results (a statistic) that is used for testing a statistical hypothesis. Before performing the test a threshold value is chosen, called the significance level of the test, traditionally 5% or 1% [1] and denoted as α. If the p-value is equal to or smaller than the significance level (α), it suggests that the observed data are inconsistent with the assumption that the null hypothesis is true, and thus that hypothesis must be rejected and the alternative hypothesis is accepted as true. When the p-value is calculated correctly, such a test is guaranteed to control the Type I error rate to be no greater than α. The p-value is calculated as the lowest α for which we can still reject the null hypothesis for a given set of observations. An equivalent interpretation is that p-value is the probability of finding the observed sample results, or "more extreme" results, when the null hypothesis is actually true (where "more extreme" is dependent on the way the hypothesis is tested).[2] Since p-value is used in Frequentist inference (and not Bayesian inference), it does not in itself support reasoning about the probabilities of hypotheses, but only as a tool for deciding whether to reject the null hypothesis in favour of the alternative hypothesis.

Longitudinal research

Longitudinal research is a type of research method used to discover relationships between variables that are not related to various background variables. This observational research technique involves studying the same group of individuals over an extended period of time. Data is first collected at the outset of the study, and may then be gathered repeatedly throughout the length of the study. In some cases, longitudinal studies can last several decades.

statistical symbols

N = number of scores X = score (or scores) M = mean d = difference of a score from the mean Σ = sum of D = difference in rank r or ρ = correlation SD = standard deviatio

Naturalistic observation

Naturalistic observation is a research method commonly used by psychologists and other social scientists. This technique involves observing subjects in their natural environment. This type of research is often utilized in situations where conducting lab research is unrealistic, cost prohibitive, or would unduly affect the subject's behavior.

Hawthorne effect

The Hawthorne effect is a term referring to the tendency of some people to work harder and perform better when they are participants in an experiment. Individuals may change their behavior due to the attention they are receiving from researchers rather than because of any manipulation of independent variables.

descriptive statistics

The term descriptive statistics refers to statistics that are used to describe. When using descriptive statistics, every member of a group or population is measured. A good example of descriptive statistics is the U.S. Census, in which all members of a population are counted.

Positively skewed distribution

a distribution with a few very high scores

Nomothetic (quantitative approach)

This approach basically used inferential and descriptive statistics as both mediums of scientific method of investigation in analyzing, presenting, and interpretation of data gathered by the researcher through standardized or objective instruments (e.g. psychological Tests).

Idiographic (qualitative approach)

This approach tends not to use inferential or descriptive statistics, but rather uses qualitative methods of data gathering such as interviews, diaries, and other written materials, obtained from or provided by the expected or anticipated respondents of a particular research.

measures of variability

Variability is concerned with the dispersement of the scores, called variability i.e. are the scores clustered together or spread out. Range and standard deviation are the measures most commonly used. To find the range just subtract the number of the lowest score from the number of the highest score. This can be deceiving if most of the scores are bunched together and one of the scores is very far away from it. In this case standard deviation must be used. A formula commonly used for standard deviation is SD = the square root of Σd²/N.

sample

a collection of subjects researchers study. researchers use samples because they cannot study the entire population

Experiments

unlike correlational research or psychological tests, experiments can provide info about cause and effect relationships between variables. In an experiment, a researcher manipulates or changes a particular variable under controlled conditions while observing resulting changes in another variable(s)

Psychological tests

used to collect info about personality traits, emotional states, aptitudes, interests, abilities, values, or behaviors.

extraneous variables

variables other than the independent variable that could affect the dependent variable

Surveys

way of getting info about a specific type of behavior, experience or event. researchers give people questionnaires or interview them to obtain info. when subjects fill out surveys themselves, the data is called self report data.

sampling bias

when the sample studied in an experiment does not correctly represent the population the researcher wants to draw conclusions about.