PED 359 Test 2

Qualitative Research Procedures:

-Interviews, focus groups, observations, action research, behavior coding inventories and scenario development. - data is generally presented through words, descriptions, and images.

Non-Probability Sampling:

-Samples are not selected at random. -difficult to claim sample is representative of group. -intact groups, volunteers.

Non-probability sampling (not random):

-The probability that an element will be chosen is not known with the result being that a claim for representativeness of the population cannot be made. -the researchers ability to generalize findings beyond the actual sample is greatly limited. -less expensive and less complicated.

Quasi-Experimental Designs:

-These designs lack either random selection of participants or random assignments to groups. -They lack some of the control of true experimental designs, but are generally considered to be fine.

Purposive Sampling:

-When members of sample are purposively selected because they possess certain traits that are critical to the study. -limited generalizability -qualitative research

Experimental Design

-a relationship between the variables needs to be established -all other reasons for the variables must be able to be eliminated. -experimental and control groups -independent and dependent variables -effect of intervention by analyzing differences between groups.

Systematic Sampling

-an alternative to simple random sampling in which the sampling units are selected in a series according to some predetermined sequence. The origin of the sequence should be controlled by chance. -it is a practical and useful approximation to random sampling that is easier to perform

True Experimental Designs:

-best type of research design because of their ability to control threats to internal validity. -utilizes random selection of participants and random assignment to groups.

Experimenter Bias Effect:

-bias of a researcher can affect the outcome of the study. -single blind study and double blind study

External Validity (properties)

-generalizability of results to what population, settings, or treatment variables can the results be generalized. -concerned with real world applications -what relevance do the findings have beyond the confines of the experiment. -external validity is generally controlled by selecting subjects, treatments, etc.

Threats to Internal Validity: Experimental Mortality

-loss of participants from comparison groups due to nonrandom reasons.

Selective Manipulation:

-method of gaining control by selectively manipulating certain participants or situations. -increase the likelihood that treatment groups are similar in characteristics and or ability at the beginning of the experiment -matched paris design and blocked design and counterbalanced design are all examples.

Physical Manipulation:

-method of gaining control by the researcher physically controlling the research surroundings. -ex: amount of sleep, food, intake, drug use, stimulation, stress, exercise, practice or training is the same for all participants.)

Cluster Sampling

-or area sampling is a simple random sample in which each sampling unit is a collection or cluster of elements. (classrooms, schools, counties and city blocks) -Sampling unit is a cluster -the first task is to delineate or specify the cluster.

Placebo Effect:

-participants in an experimental treatment may believe the treatment is supposed to change them so they respond to the treatment with a change in performance.

Types of Designs:

-pre experimental -true-experimental -quasi-experimental

Constant Comparison/Content Analysis:

-preliminary analysis -selection of categories from preliminary analysis -comparison with peer debriefer -selection of final categories -Participants response by category -category descriptions -comparison of responses in each category -development of empirical assertions -discussion of assertions.

descriptive research

-present -gathering info and describing the current situation -may or may not involve hypothesis testing

"Traditional" Experimental Design:

-problem -reading relavent literature -testable hypothesis or research question -method -results -discussion

Non Probability Sampling: (example)

-purposive sampling -convenience sampling

Possible to estimate sampling error:

-simple random sample -stratified random sampling -systematic sampling -cluster sampling

Types of Descriptive Research:

-survey -developmental (longitudinal/cross sectional approach) -case study (person, event, etc) -Correlational (relationship, predictive) -Normative (norm referenced-percentiles and criterion referenced) -causal-comparative (aka ex post facto)

external validity:

-the degree to which the findings can be inferred to the population of interest or to other populations or settings; the generalizability of the results.

Internal Validity

-the validity of findings within the research study; did the experimental treatments make a difference in the study in that the treatments caused the participants in the study to chance in ability or are the changes in the ability of the participants due to other factors. -to gain internal validity, the researcher attempts to control everything and eliminate possible extraneous influences.

Overview of Experimental Research:

-traditional type of research -purpose is to investigate cause and effects relationships among variables. -each group of participants receives a different treatment. -always involves manipulation of independent variable.

What makes a qualitative study good? Credibility (internal validity)

-triangulation (data investigator, method theory) -member checks -prolonged engagement

Descriptive Statistics:

-used to organize, simplify, and summarize the collected data. -Data typically consist of a set of scores called a distribution. These scores result from the measurements taken. -The original measurements or values in a distribution are called raw scores.

What makes a qualitative study good? Transferability (external validity)

-user generalizability -rich, thick description

Computer Analysis:

-variety of computer programs for statistical computations. -SPSS -SAS -Statview -Excel *Fast, easy to use, widely available.

Pre-experimental Designs

-weak exp designs in terms of control. -no random sampling -threats to internal/external validity are significant prob. -many definite weaknesses

How do you select participants in qualitative studies?

1. Selected for certain characteristics (not looking to make generalizations) 2. Probability sampling is not used in qualitative research 3.Purposive sampling-seeks info rich cases which can be studied in depth.

Random Process-important to the quality of research for 4 reasons:

1. representativeness of sample to population. 2. will show the researcher was unbiased during selection of participants. 3. equalize characteristics among groups 4. basic requirement of inferential statistical tests.

Steps in the sampling process:

1.Identify target population 2. identify the accessible population 3. determine desired sample size 4.select specific sampling technique 5.implement the sampling plan.

Census:

A survey which obtains responses from the entire population is called a census.

Controlling threats to validity:

Campbell and Stanley present 12 factors that can threaten the validity of an experimental research study. -1-8 threaten internal validity -9-12 threaten external validity **try to control as many as possible

Measures of Central Tendency:

Mean, Median and Mode

Longitudinal Approach:

Method by which a group is measured and observed for years.

Cross-Sectional Approach:

Method for testing many groups and assuming each group is representative of all other groups when they are at the point in time.

Statistical Techniques:

Method of gaining control uses if other control techniques are not possible. -applied when physical and selective manipulation of variables is not possible. -ANCOVA (analysis of covariance)

Causal-Comparative Research:

Research that seeks to investigate cause and effect relationships that explain differences that already exist in groups or individuals.

Measures of Variability:

Spread or Heterogeneity: -Range: highest to lowest score -standard deviation: measure of variability used with the mean and also the amount that all scores differ from the mean.

Sample

a small subgroup of a population of interest thought to be representative of that population.

Threats to Internal Validity: Maturation

biological or psychological processes within participants that may change due to passing of time.

Quantitative Definition:

causal determination, prediction, generalization of findings.

Threats to Internal Validity: Instrumentation

changes in testing instruments, raters, or interviewers, including lack of agreement within and between observers.

objectivity (convention term)- what is the qualitative term?

conformability

Correlational Statistics:

correlation is a family of statistical techniques that is used to determine the relationship between 2 or more variables. -correlation coefficient ranges from -1 to +1. -scatterplot is a graphic illustration of the relationship between 2 variables. -no manipulation of variables.

Internal validity (convention term)- what is the qualitative term?

credibility

Mixed Method- Concurrent

data collected at the same time and then integrated for interpretation of the overall results.

Reliability (convention term)- what is the qualitative term?

dependability

Threats to Internal Validity: Testing

effects of one test upon subsequent administrations of the same test. (practice effects, fatigue effects, catching on effects)

Threats to Internal Validity: History

events occurring during the exp. that are not part of the treatment.

Simple Random Sampling

every member of the population has an equal probability of being selected for the sample. Also the selection of one member of the population does not affect the chances of any other member being chosen (equal and independent) Usual Procedure: -fishbowl technique -table of random numbers -computer generated sampling

Mixed Method-Sequential

expands on findings of one method with another.

block design:

extension of matched pairs design for 3 or more groups.

Threats to Internal Validity: Interaction Among Factors

factors can operate together to influence experimental results.

matched pairs design:

form of selective manipulation by which participants are matched to gain control.

experimental research:

future

Threats to Internal Validity: Selection Bias

identification of comparison groups in other than a random manner.

John Henry Effect:

in studies with an experimental group and control group, the control group knows it is not supposed to be better than the exp so it tries harder and out performs the exp. group. -aka "avis effect"

counterbalanced design:

method of gaining control by all participants receiving all treatments but in different orders.

Stratified Random Sampling:

obtained by separating the population elements into non-overlapping sub-groups, called strata, and then selecting a simple random sample from each strata. -no sampling unit can appear in more than one strata. -a stratified sample will assure representation from each strata.

Hawthorne Effect:

participants should be unaware that they are participating in an experiment and also unaware of the hypothesized outcome of the study.

sampling

process of selecting a subgroup or sample of the population.

Random Assignment:

purpose is to enable the researcher to assume that groups are "equivalent" at the beginning of the study. This adds control to the study; it has nothing to do with the selection of the sample.

Random Selection:

purpose is to enable the researcher to generalize the results to a larger population thus, researcher is concerned about the representativeness of subjects in the sample.

Population

refers to an entire group or aggregate of people or elements having one or more common characteristics.

Qualitative Research:

sample size: purposive, small Info per respondent: substantial administration reqs: special skills Type of Analysis: descriptive, interceptive Hardware: tape recorder, video, pics. Ability to replicate setting: low Design: natural, real world, flexible, may change

Quantitative

sample size:random, large Info per respondent: varies administration reqs: fewer special skills Type of Analysis: statistical, Hardware: questionnaires, computer printouts Ability to replicate setting: High Design: lab, pre-determined

Probability Sampling:

sampling technique in which the probability of selecting each participant is known. -utilizes random processes but does not guarantee the sample is representative of population.

rating effect:

several kind of rating errors can occur: 1.halo effect: tendency to let initial impressions influence future ratings or scores of participants. 2.central tendency error: tendency to rate most participants in the middle of the rating scale.

ANCOVA (analysis of covariance):

statistical technique to gain control by adjusting for initial differences among groups.

double blind study:

study in which participants and those conducting the study are unaware of the purpose of the study and group membership of participants.

single blind study:

study in which participants are unaware of the purpose of the research study and their role in the study.

Survey Research methodology:

survey research is the most common of descriptive research. -involved questions techniques for data collection -consists of asking questions of a supposedly representative sample of the desired population at a single point in time. The person of whom the questions are asked are called survey respondents. -most difficult part of conducting a survey is writing the questions.

Threats to Internal Validity: Statistical Regression

the fact that groups selected on the basis of extreme scores are not as extreme on subsequent testing.

Research Design:

the framework which guides the collection of data; blueprint of the study -determined by the research question-which design is the most appropriate? -also specifies: variables to be measured, population and sampling method, method of observation.

External Validity(convention term)- what is the qualitative term?

transferability

Qualitative Definition:

understanding, illumination, extrapolation. -Qualitative uses the natural setting as the source of data. The researcher attempts to observe, describe, and interpret settings as they are, maintaing what Patton calls an "emphatic neutrality." -Researcher acts as the human instrument of data collection. -Qual. reports are descriptive, incorporating expressive language and the "presence of voice in the text." -Qual. research has an interpretive character, aimed at discovering the meaning events have for individuals who experience them, and the interpretations of those meanings by the researcher. -Qual res has an emergent design, and researchers focus on the emerging process as well as the outcomes or product of the research. -Qual research is judged using special criteria for trustworthiness