Question | Answer |
Concept | an abstraction based on observations of certain behaviors or characteristics. For example, stress, pain etc. |
Construct | an abstraction or concept that is deliberately invented (constructed) by researchers for a scientific purpose. Often used interchangeably with concept however construct is usually a more complex abstract- for example self-care. |
Theory | Systematic, abstract explanation of some aspect of reality. Building blocks of theory. |
Experimental studies | The research often starts with a theory or conceptual model and predicts how the phenomena will behave in the real world. |
Deductive reasoning | Used to describe test or predict the application of a theory to a particular phenomenon. |
Inductive reasoning | Used in qualitative research to develop theories about phenomenon. |
How are boundaries set in experimental research? | By sampling identify inclusion and exclusion criteria. |
What are the four major categories of quantitative research? | Nonexperimental, pre-experimental, quasi-experimental, true experimental |
Nonexperimental | Studies in which the researcher collects data without introducing any treatment or change. |
Pre-experimental | Research design that does not include mechanisms to compensate for the absence of either randomization or a control group. |
Quasi-experimental | A study in which the subjects are not randomly assigned to treatment conditions, but the researcher does manipulate the independent variable and exercises certain controls to enhance the internal validity. |
True experimental | A study in which the investigator manipulates the independent variable and randomly assigns subjects to different conditions. |
What is the purpose of experimental research? | describe, explain, predict |
What are some of the research designs used for experimental studies? | Pretest-post-test, post-test only, Solomon Four Group, Factorial, Repeated Measures |
Pretest-post-test | Data are collected from research subjects both before and after introduction of the experimental intervention (also referred to as before-after design). |
Posttest Only | Data is collected from research subjects only after the introduction of the experimental intervention. (also referred to as after-only design). |
Solomon Four Group | Uses before-after design for one pair of experimental and control groups and after-only for second pair. |
Factorial | Two or more independent variables are simultaneously manipulated. Allows researcher to perform a separate analysis of the main effects of the independent variables plus interaction effects of those variables. |
Repeated Measures | one group of subjects is exposed to more than one condition or treatment in random order; also referred to as cross-over design |
What are some of the research designs used for quasi-experimental studies? | Non-equivalent control group; Time series |
Non-equivalent control group | Involves a comparison group that was not developed on the basis of random assignment, however pre-intervention data is obtained to assess the initial equivalence of the groups. |
Time series | Collection of information over an extended period of time, with multiple data collection points both before and after introduction of the treatment. |
What are some of the research designs used for nonexperimental studies? | Ex Post Facto-correlation; Descriptive |
Ex Post Facto-correlation | Research is conducted after the variations in the independent variable have occurred in the natural course of events. Causal explanations are inferred after the fact. |
Descriptive | Accurate portrayal of the characteristics of persons, situations, or groups and/or the frequency with which certain phenomenon occur. |
What is purpose of literature review? | To determine previous research on the topic.
To determine the relationship between current knowledge and identified problem.
To provide rationale for a design. |
Read literature critically to: | Understand level of knowledge of a particular problem area. Identify gaps in knowledge development. Determine next logical research step. Identify potential measures for a particular study. Must set boundaries in literature review |
When must research questions be posed in experimental research? | Before research begins. |
What is a research question called in qualitative research? | Query- a broad statement that identifies both a particular phenomenon and a context for a study. |
Variable | A concept or construct to which numerical values are assigned |
Types of variables | Dependent, independent, extraneous or confounding variable |
Validity | The extent to which what is being measured is a reflection of the underlying concept |
Internal validity | ability of research design to answer accurately the research question |
History threat to internal validity | effect of external events on study outcomes |
Testing threat to internal validity | effect of being observed or tested on study outcome |
Instrumentation threat to internal validity | extent to which the instrument is accurate in its measurement and extent instrument may effect outcome |
Maturation threat to internal validity | effect of passage of time |
Regression threat to internal validity | effect of cluster around mean |
Mortality threat to internal validity | effect on outcome caused by dropping out of study |
Interactive threat to internal validity | extent to which each of the threats interacts with the others |
External Validity | Capacity to generalize findings and develop inferences from the sample to the study population |
Construct Validity | Fit between constructs that are the focus of the study and the way in which the constructs are operationalized |
Content Validity | Degree to which an indicator seems to agree with a validated instrument measuring the sample construct |
Face Validity | Extent to which a measuring instrument looks as though it is measuring what it purports to measure. |
Reliability | Obtaining stable measurement from a single instrument or stability of research design |
Measuring reliability: test-retest | Same test is given twice to same subject, under same conditions. |
Measuring reliability: Split-half technique | Instrument items are split in half and correlational procedure is performed between two halves |
Measuring reliability: Cronbach’s alpha | Statistical procedure used to examine the extent to which all items in the instrument measure the same construct. |
What is sampling? | The process of selecting a portion of the population to represent the entire population. In experimental studies, sampling is used to set the boundaries of the study. |
What is probability sampling? | Sampling plans based on probability theory all in population have equal chance of being in sample. |
Simple Random sampling | Sample frame is created by enumerating all members of a population of interest, and then selecting a sample through completely random procedures such as drawing names from hat or having computer select random numbers |
Stratified sampling | (population is divided into smaller groups or strata) participants are selected from strata independently |
Systematic sampling | sampling interval with width (k) is determined based on the needed sample size and every kth element is selected from the sampling frame |
Cluster sampling | Large groupings (clusters) are selected first (e.g., nursing schools) with successive sub-sampling of smaller units (e.g., nursing students). |
What is Nonprobability sampling? | Nonrandom methods used. Examples: convenience, purposive, snowball and quota. |
Convenience Sample | selection of the most readily available persons (or units) as participants in a study; also known as accidental sampling |
Purposive Sample | researcher selects participants for the study on the basis of personal judgment about which ones will be most representative or production |
Snowball Sampling | sampling of participants based on referrals from others already in the sample, also known as network sampling |
Quota sampling | researcher prespecifies characteristics of the sample to increase its representativeness. |
What are inferential statistics? | Type of statistics used to draw conclusions about population parameters based on findings from a sample. |
What is saturation? | Point at which an investigator has obtained sufficient information from which to obtain an understanding of the phenomena. |
What is crystallization or triangulation? | Use of multiple strategies or methods as a means to strengthen the credibility of the researchers’ findings. |
What are characteristics of true experimental design? | Randomization, manipulation and control |
What do the following Campbell and Stanley Symbols mean? | R = random sample selection.
r = random group assignment.
X = independent variable.
O = dependent variable. |
What is an operational definition? | Definition that reduces the abstraction of a concept to a concrete observable form by specifying the exact procedures for measuring or observing the phenomenon. |
What is an IRB? | Institutional Review Board-group of individuals from an institution who meet to review the ethical considerations of proposed and ongoing studies. |
What is informed consent? | Ethical principle that requires researchers to obtain the voluntary participation of subjects after informing them of the possible risks and benefits. |
What is full disclosure? | Adequacy of information provided to research participants necessary for them to make an informed decision about participating in the study. |
What are mean, median and mode? | Measures of central tendency |
What statistical test compares means if you have 2 groups? | T-test |
What statistical test compares variance when you have two or more groups? | Analysis of Variance (ANOVA) |
What is effect size? | Strength of differences in the sample values that the investigator expects to find. |
What is response rate? | Rate of participation in a study, calculated by dividing the number of persons participating n the study by the number of persons sampled. |
What is the Hawthorne effect or Halo effect? | Attention factor-phenomenon in which research subjects may experience change simply from the act of participating in a research project. |
What is Pearson's Chi-square? | Used to test the hypothesis of no association of columns and rows in tabular data. Probability of <0.05 = justify rejecting null hypothesis. Calculation: (sum of observed - expected count squared)/divided by the expected. |
What is Pearson’s correlational coefficient (r2)? | A bivariate measure of association (strength) of the relationship between two variables.Varies from 0 (random relationship) to 1 (perfect linear relationship) or -1 (perfect negative linear relationship). |
Hypothesis | Statement predicting the relationship between variables. |
Null Hypothesis | States that there is no relationship between variables under study; used primarily in connection with tests of statistical significance as the hypothesis to be rejected. |
p value | In statistical testing, the probability that the obtained results are due to chance alone; the probability of committing a type I error. |
Alpha | The probability of a type I error. Represents the researcher’s risk of incorrectly rejecting the null hypothesis (saying there is a difference when in fact there is not). Also referred to as probability p. |
Alpha halves | The risk of a Type I error when a test of equality is performed. Alpha is divided in half. Two-tailed tests. |
Type I Error | error created by rejecting the null hypothesis when it is true (the researcher concludes that relationship exists when in fact it does not |
Type II Error | error created by accepting the null hypothesis when it is false (the researcher concludes that no relationship exists when in fact it does. |
Prevalence vs. Incidence | Prevalence is the proportion of the population with a given disease at a single point in time whereas incidence is the number of new cases of disease or condition during a specified time frame. |
Positive Predictive Value (PPV) | the likelihood someone with a positive test result will actually have the disease. It is expressed as a proportion. Percentage of those with a positive test who actually that the disease. a/ a+b |
Negative Predictive Value (NPV) | likelihood someone with a negative test result will actually not have the disease. Expressed as a proportion it is the percentage of those with a negative test who actually do not have the disease. d/c+d |
Sensitivity | ability of the test to be positive given the person tested has the disease/problem Expressed as a proportion. It is the percentage of those who are known to have the disease/problem who test positive. Proportion of true positives a/a+c |
Specificity | ability of the test to be negative given the person does not have the disease/problem. Expressed as a proportion. It is the percentage of those who are known not to have the disease or problem who test negative. The proportion of true negative d/(d+b) |