Designing and Planning Phase

designing and planning phase

constructing of research methodology

research design selection, categories and characteristics of research designs, validity of experimental designs

what do you determine in the designing and planning phase

research design selection

• blue print or roadmap of the research study

research design selection

• the framework or guide used for the planning, implementation, and analyzing of data

quantitative data (obj data); qualitative data (subj data)

what are the major approach of research design selection

casuality

• many research questions are about causes and effects

temporal, relationship. confounders, biological plausibility

what are the criteria for establishing casual relationships

temporal

a cause must precede an effect in time

relationship

there must be an association between the rpesumed cause and effect

confounders

the relationship cannot be explained as being caused by a third variable

biological plausibility

it is the criterion in health research; evidence from basic pathological studies that a casual pathway is credible

counterfactual

is what would hapen to people if they were expected to casual influence and were simultaneously not expected to it.

counterfactual

an effect represents the difference between what actually did happen with the exposure and what would have happened without it

experimental designs

researcher describes the intervention in formal protocols that stipulate exactly what the treatment is

experimental designs

researchers have choices about what to use as the control condition

usual care; an alternative treatment; a placebo or pseudo intervention; an attention control condition; delayed treatment

types of control conditions

usual care

it is a control condition using standard or normal procedure

an alternative treatment

it is a control procedure using for example music vs massage

a placebo or pseudo intervention

control condition that is presumed to not have therapeutic values

an attention control condition

control condition where the control group gets attention but not the intervention’s active ingredients

delayed treatment

control condition wherein control group members are wait-listed and exposed to the intervention after outcomes are assessed

random assignment; control over extraneous variables; manipulation of the treatment conditions; outcome measure; group comparison; threats to validity

what are the characteristics of experiment

random assignment

process of assigning individuals at random to groups, or to different groups in an experiment

random assignment

any bias in th eprsonal charcteristic of individuals in the experiment is distrubuted equally among the group

random assignment

provide control of the extraneous characteristicsof the participants that might inlfuence the outcome

random assignment

e.g. student ability, attention span, motivation

equating the group

experimental term for random assignment

control over extrabeous variables

any influence in the selection of participants, the rpocedures, the statistics, or the design liekly to affect the outcome.

control over extraneous variables

provide an alternative explanation for our results than what we expected.

control over extraneous variables

random assignment is a decision made by the investigators before the experiment begins.

pretest and post test; covariates, matching of articipants; homogenous samples; blocking variables

control over extraneous varibales: control procedures

pre test

this is to equate the characteristics of the groups, experimental researchers may use a what?

pretest and post test

this is to equate the characteristics of the groups, experimental researchers may use a what?

covariates

variables that the researchers controls for using statistics (ANCOVA) n that elate to the dependent variale but that do not relate to the indipendent variable

covariates

in this control procedure, the researcher needs to control for these variables, which have the potentila to covary with the deoendent variable

matching of participants

the process of identifying one or more personal characteristics that influence the outcomes and assigning individuls with that charcteristics equally ti the experimentak and control group

homogenous samples

selecting people who vary little in their personal characteristics

blocking variables

a variable the researcher controls before the experiment starts by dividing (blocking) the participants into sub groups (or categpries) and analyzing the impact of each subgroups on the outcome.

manipulation of the treatment conditions

researcher physically intervenes to alter the conditions experienced by the experimental unit.

outcome measures

dependent variables that us the presumed effect of the treatment variable

outcome measures

the effect predicted in a hypothesis in the cause-and-effect equation

outcome measures

aka response, criterion, or post-test

group comparisons

process of researcher obtaining scores for individuals or groups onthe dependent variable and comparing the ens and variance both within the group and between the groups.

threats to validity

specific reasons for why we can be wrong when we make an inference in an experiment

validity of experimental design

researcher is interested in controlling or removing extraeous variables that may create spurious results or inaccurate findings

internal validity; external validity; statistical conclusion validity; construct validity

types of validity of experimentak design

internal validty

relates to the validity of inferences drawn about the cause and effect relationship of IDV and DV

internal validity

extent to which it can be inferred that the IDV is casuing the outcome (DV)

threats to internal validity

exoerimental procedures, treatments, or experinces of the particoiants that threaten the researchers ability to draw correct inferences from the data baout the population in an experiment

threats to internal validity

most severe because they can compromise an otherwise good experiment

related to participants (history, maturation, regression, selecting or self selecting, morbidity or attrition); related to treatments (diffusion of treatments, compensatory / resentful demoralization, compensatory rivalry); related to procedures (testing, instrumentation)

types of threats to internal validity:

history

because of time passes during an exprimentation, events can occur that unduly influence the outcome beyond the experimental treatment

maturation

participants in an experiment may mature or change (become older or getting tired, wiser, stronger, and more experience) during the experiment thus influencing the results

regression

participants with extreme scores are selected for the experiment

selection (self-selection)

participants can be selected who have certain characteristics the predispose them to have ceratin outcomes (e.g., they are brighter)

mortality (attrition)

particpants drop out during an experiment due to many possible reasons

diffusion of treatments

participants in the EG and CG communicate with each other. this communication can influence how both groups score on the outcomes.

compensatory / resentful demoralization

the benefits of an experiment may be unequal or resented when only the EG receives the treatment.

compensatory rivalry

particopants in the CG feel that they are being devalued as compared to the EG because they do not experince the treatment

testing

participants become familiar with the outcome measures and remember responses for later testing

instrumenttaion

the instruke nt change between a pretest and post test thuc impacting the scores on the outcome

external validity

refers to the validity of the cause and effct realtionshio being GENERALIZEDA TO OTHER PERSONS, SETTINGS TREATMENT, VARIBALES AND MEASURES

threats to external validty

problems that threaten our ability to draw correct inferences from the sample data to other persons, settings, treatment varuables, and\ measures

interaction of selection and treatments; interaction of setting and treatments; interaction of history and treatments; hawthorne effect, halo effect, experimental effect (rosenthal effect)

types of threat to exterbal validity

interaction of selection treatment

because of narrow characteristics of particiants in the experiment, the researcher cannot gneralize to individuals who do not have the characteristics of participants

interaction of setting and treatment

because of the characteristics of the setting of participants in an experiment, a researcher cannot generalize to individuals in other settings

interaction of history and treatment

because results of an experiemnt are time-bound, a rsearher cannot generalize the results to post our future situations

hawthorne effect

occurs whe study participants respond in particular manner, or there s abvious change of behaviours because they are aware that they are being observed

halo effect

the tendency of the researcher to rate the subject high or low becaus eof the impression he has on the subjetc

experimental effect (rosenthal effect)

refers to a threat to the stdy whicb results when the researchers behaviour influences the behaviour of the paraticipants such as the reseearch facial expression, gender, and clothing among others

statistical conclsuion validty

refers to the appripriate use of statistics to infer whether the presumed independent and dependent variabe covary in th expeirment

construct validity

menas the validity of inferences abou the constrcts or (varibales) in the study.

constrct validity

degree to which evidence about a measures scores in reltion to other variables suppoert the inference that the contstructs has been respresented

construct validity

if study contain construct errosrr, the study could be misleading