Term
|
Definition
| Consistency or accuracy of a measurement; extent to which a measure is free of random error |
|
|
Term
| What is Internal Consistency? What is used to measure Internal Consistency? What is normal value? |
|
Definition
| See if scales are composed of items that all measure the one attribute and nothing else. Cronbach's Alpha or Coefficient Alpha is used. Normal range is 0-1.00. The higher the better |
|
|
Term
| What is Inter-rate? What percent agreement is desirable? |
|
Definition
| See if 2 independent observers agree about the scoring. Want at leasst 80% |
|
|
Term
|
Definition
| See subjects over time. USed for traits that don't change over time (ex: personality, abilities) |
|
|
Term
|
Definition
| Extent which similar results are obtaied on 2 seperate occasions |
|
|
Term
|
Definition
| Soundness of the study's evidence. Whether there is evidence to support the inference |
|
|
Term
| What is Content Validity? |
|
Definition
| Does the measure adequately represent the domain of content? |
|
|
Term
| What is used to measure validity? What kind of score do you want? |
|
Definition
| Validity Co-efficient (r). Between 0-1. Want at least a .70 |
|
|
Term
| What is Chriterion Validity? |
|
Definition
| See if scores on intrument & external criterions match... |
|
|
Term
| What is Construct Validity? What is this especially good for? |
|
Definition
| What is this instrument really measuring? Especially good for highly abstract concepts. |
|
|
Term
| What is convergent validity? |
|
Definition
| Different methods of measuring the same attribute yield the same result |
|
|
Term
| What is Discriminant validity? |
|
Definition
| To differentiate the constrct being measured from other similar construct |
|
|
Term
|
Definition
| Instrument's ability to ID a case correctly |
|
|
Term
|
Definition
| instrument's ability to ID noncases correclty |
|
|
Term
| What are the 3 types of Data Collection Instruments? |
|
Definition
| Self report, Observation, Biophysical Measurements |
|
|
Term
| What is self-reporting? What is commonly used in self-reporting? |
|
Definition
| Interview: verbal exchange between the data collector and the subject. Questionaires are normally used. |
|
|
Term
|
Definition
| Systematic observing and recording behavior events, and settings of the variables under investigation. |
|
|
Term
|
Definition
| Has objectivity & preciison. |
|
|
Term
| Data collecting methods vary in 4 dimensions, what are they? |
|
Definition
| Structure, quantifiability, researcher obstrusiveness, and objectivity |
|
|
Term
| What is the Critical Incidents Technique? |
|
Definition
| Involves probes about the circumstances surrounding an incident that is critical to an outcome of interest |
|
|
Term
| What is Think aloud method? |
|
Definition
| Involves having people talk about decisions as they are making them |
|
|
Term
| What does the Likert Scales do? |
|
Definition
| Present respondents with a series of items worded favorably or unfavorably toward a phenomenon; responses iindicating level of agreement or disagreement with each statement are scored and summed into a composite score |
|
|
Term
| What do Semantic Differential (SD) technique do? |
|
Definition
| Consists of a series of scales with bipolar adjectives (good/bad) along which respondents rate their reactions |
|
|
Term
| What is the Visual Analog Scale (VAS)? |
|
Definition
| Used to measure subjective experiences along a 100mm line designating a bipolar continuum |
|
|
Term
|
Definition
| Brief descriptions of some event, person, or situation to which respondents are asked to react |
|
|
Term
| What are Q Sorts? How are they assorted? |
|
Definition
| Respondents sort a set of statemtns on cards into piles according to specified criteria |
|
|
Term
| What are characteristics of Experimental Design? |
|
Definition
| Manipulation, control, and Randomization |
|
|
Term
| Basic Designs include what? |
|
Definition
| Posttest-Only & Pretest-Posttest Designs |
|
|
Term
| What is Posttest-Only Design? |
|
Definition
| Inovlve only collecting data once |
|
|
Term
| What is Pretest-Posttest Design? |
|
Definition
| Collect data both before and after intro of intervention |
|
|
Term
| What is Factorial Designs? |
|
Definition
| 2 or more variable are manipulated simultaneously allow researchers to test both main effects and interactions |
|
|
Term
|
Definition
| Effects from the experimentally manipulated variables |
|
|
Term
| What are Interaction Effects? |
|
Definition
| Effects resulting from combining the treatments |
|
|
Term
| What is Crossover Design? What is a major problem with this? It is good for what kind of subjects? |
|
Definition
| Exposing participants to more than one treatment. Carryover effects is a problem. If treatment effects are immediate and short lived. |
|
|
Term
| What is the Hawthorne Effect? |
|
Definition
| Knowledge of being in a study may change one's behavior |
|
|
Term
| What are Quasi-Experiments? What is 2 major type? |
|
Definition
| Controlled trials without randomization. Involves manipulation but NO COMPARISON group or RANDOMIZATION. Main Type: Non-equivalent Group Design & Time Series Design |
|
|
Term
| What is the Non-equivalent Group Design? |
|
Definition
| Before-after design: involves 2 or more groups of subjects observed before and after intervention. Similar to before-after designs but no randomization. |
|
|
Term
| What is Time-Series Design? |
|
Definition
| Collecting data over a period of time and introducing the treatment during that period |
|
|
Term
| What is Non-Experiemental Studies? How many variables does it focus on? |
|
Definition
| Summarizes the status of a phenomena. Observe, describe, and document aspects of a situation. Focuses on ONE variable. |
|
|
Term
| What is Prevalence Studies? |
|
Definition
| Examine prevalence of a condition or behavior at a particular point in time. |
|
|
Term
| What is Incidence Studies? What kind of study is necessary for this? |
|
Definition
| Used to measure the frequency of developing new cases. Longitudional design is required to determine how many new cases occurred over the period of study. |
|
|
Term
| What is Analytic Studies? What kind of studies fall under Analytic Studies? |
|
Definition
| Comparison between groups to determine the role of various risk factors in causing the problem. Include: Cross-sectional, correlational, cohort, case-control, Quasi-experimental, experimental |
|
|
Term
| What is Correlational Studies? |
|
Definition
| Examine the relationship among variable but involve NO MANIPULATION of the independent varialbe. It is interrelationship or association between 2 variables where a tendency for variation in one variable can relate to teh variation of another. |
|
|
Term
| What is Retrospective Design? |
|
Definition
| Phenomenon is observed in the present is linked to a phenomena occuring in the past |
|
|
Term
| What is Cohort Studies? or Prospective Studies? |
|
Definition
| A Nonexperimental design in which a defined group of people is followed over time to study outcomes for subsets of cohorts |
|
|
Term
| What is Case Control Design? |
|
Definition
| NOn-experimental research design involving the comparison of "cases" and matched controls. Usually retrospective: begin with disease and look backward in time for exposure) |
|
|
Term
| What is Cross-sectional Designs? |
|
Definition
| Involve the collection of data at one point in time (or multiple times in a short period of time) |
|
|
Term
| What is Longitudinal Designs? What 3 kinds of studies does this include? |
|
Definition
| Collection of data at more than one point in time over an extended period. Includes: Trend study, Panel Studies, and Follow-up Studies |
|
|
Term
| What does Trend Study do? |
|
Definition
| Collection of data from different people to examine trends |
|
|
Term
| What do Panel Studies do? |
|
Definition
| Collection of data from the same people to examine changes over time |
|
|
Term
| What does Follow Up Study Do? |
|
Definition
| Determine subsequent status of subjects |
|
|
Term
| What is Intervention Fidelity? |
|
Definition
| Whether the intervention was properly implemented and actually received |
|
|
Term
|
Definition
| Restricting the selection of subjects to elimnate variability on the confounding variables. |
|
|
Term
| What are validity concerne with? |
|
Definition
| The extent to which appropriate inferences can be made |
|
|
Term
| What does Statistical Conclusion Validity concern with? |
|
Definition
| The strength of evidence that a relationship exists between 2 variables |
|
|
Term
| What does Internal Validity Concern? |
|
Definition
| Concerns inferences that the outcomes of interest were cuased by the independent variable, rather than by other factors extraneous to the research. |
|
|
Term
| What is External Validity? |
|
Definition
| Concerns inferences about generalizability |
|
|
Term
|
Definition
| The process of selecting a portion of the population, which is an entire aggregate of cases |
|
|
Term
| What is one of the main challenges of sampling? |
|
Definition
|
|
Term
|
Definition
| Systemic overrepresentation or underrepresentaiton of some segment of the population |
|
|
Term
| What is non-probability sampoing? |
|
Definition
| Where elements are selected by nonrandom methods |
|
|
Term
| What is convenience sampling? |
|
Definition
| Uses the most readily available or most convenient gorup of people for the sample. Volunteer sample |
|
|
Term
| How strong is convenience sampling and how common is it used? |
|
Definition
| Weakest sampling that contains bias but most commonly used |
|
|
Term
| What is snowball sampling? When is this used? |
|
Definition
| A type of conveninece sampling which refferals for potential particpants are made by those already in the sample. Used when population is difficult to identify with |
|
|
Term
|
Definition
| Divides the population into homogenous strata (subpopulations) to ensure representation of the subgroups in the sample; within each stratum, subjects are sampled by convenience. |
|
|
Term
| What is Consecutive Sampling? |
|
Definition
| Involves taking all of the people from an accessible population who meet the eligibilty criteria over a specific time interval, or for a specified sample size. |
|
|
Term
| What is Purposive Sampling/Judgemental? |
|
Definition
| Participants are hand-picked to be included in the sample, based on the researcher's knowledge about the population. Ex: A sample of experts |
|
|
Term
| What is Probability Sampling? |
|
Definition
| Involve the random selection of elements from the population, yield more representative sample than nonprobability designs and permit estimates of teh magnitude of sampling error. |
|
|
Term
| What is Simple Random Sampling? |
|
Definition
| Involves the random selection of elements from a sampling frame that enumerates all the elements |
|
|
Term
| If nursing students at UCONN were the accessible population, then what would be the samplying frame? |
|
Definition
| Roster of the students or telephone book |
|
|
Term
| In simple random sampling, what is the main problem? |
|
Definition
| No guarantee that the sample will be representative of the population. |
|
|
Term
| Is simple Random sampling used a lot? |
|
Definition
| No. Rarely used and time consuming |
|
|
Term
| What is Stratified Random Sampling? Give example |
|
Definition
| Divides the population into homogenous subgroups from which elements are selected at random. Ex: Having a population of different ethnicities and varying amounts of people in each ethnic group; pick a certain amount of people from each group to have a "good representation" from teh minority group |
|
|
Term
| What is Cluster Sampling (multistage sampling)? Give example. What is good for? |
|
Definition
| Involves the successive selection of random samples from larger to smaller units. EX: State-->Census Tract-->Households. Good for when the population is large and widely dispersed |
|
|
Term
| What is Systematic Sampling? |
|
Definition
| The selection of every kth case from a list. |
|
|
Term
| IF you want a sample of 50 from a population of 5000, what will be the sampling interval for Systematic Sampling? |
|
Definition
| Sampling Interval will be 100; every 100th case on the sampling frame would be sampled. |
|
|
Term
| For qualitative sampling, what methods are usually used? |
|
Definition
| Convenience & snowball sampling, Purposive sampling, Maximum Variation Sampling, Extreme Case Sampling, Typical Case Sampling, Criterion Sampling, Theoretical Sampling |
|
|
Term
| What is Maximum Variation Sampling? |
|
Definition
| Deliberately selecting cases with a wide range of variation on dimensions of interest |
|
|
Term
| What is Extreme (deviant) case Sampling? |
|
Definition
| Provides opportunities for learning from the most unusual and extreme informatns (outstanding successes and notable failures) |
|
|
Term
|
Definition
| Selection of participants who illustrate or highlight what is typical or average |
|
|
Term
|
Definition
| Involves studying cases who meet a predetermined criterion of importance |
|
|
Term
| What is Theoretical Sampling? |
|
Definition
| MEthod of sampling that is most often grounded in theory; involves decisions about what data to collect next and where to find those data to develop an emerging theory optimally. "What group should the researcher turn to next?" |
|
|
Term
| What is used to estimate sample size in quantitative studies? |
|
Definition
|
|
Term
| What kind of study do qualitative researchers most often use? |
|
Definition
| Purposive Sampling- to select data sources that maximize information richness. |
|
|
Term
| What are sampling confirming and disconfirming cases? |
|
Definition
| Selecting cases that enrich and challenge the researcher's conceptualization |
|
|
Term
| What is a guiding principle in qualitative studies? |
|
Definition
| Data Saturation-sampling to the point at which no new information is obtained and redundancey is achieved |
|
|
Term
| Ethnogrpahers use who to serve as guides and interpreters of the culture? |
|
Definition
|
|
Term
| Grounded theory researchers typically use what kind of sampling? |
|
Definition
|
|
Term
| What are the 2 criteria for qualitative sampling? |
|
Definition
| Informational adequacy and appropriateness |
|
|
Term
| What is Frequency Distribution? |
|
Definition
| Systematic arrangement of numeric values from the lowest to highest, together with a count of the number of times each value was obtained |
|
|
Term
| What is a symmetric Distribution? |
|
Definition
| When folded over, the two halves of a frequency polygon would be superimposed |
|
|
Term
| What is a Positive and Negative Skew? |
|
Definition
| Positive Skew: Tail to the right. Negative Sckew: Tail points to the left |
|
|
Term
| For interval-level or ratio level measurements, what is usually reported? |
|
Definition
|
|
Term
| When the data is highlly skewed, what characterizes the center of distribution? |
|
Definition
|
|
Term
| What is Inferential Statistics? |
|
Definition
| Use samples to make inferences about a population; based on incomplete info therefore there is always a risk of making an error |
|
|
Term
| What does it mean when a distribution is more heterogeneous? Vs. Homogeneous? |
|
Definition
| More variables. Ex: Wide range of scores. homogeneous means less range. |
|
|
Term
| What percentage fall within 1 SD above and below the mean? |
|
Definition
|
|
Term
| What percentage fall 2 SDs from the mean? |
|
Definition
|
|
Term
| What percentage fall 3 SDs? |
|
Definition
|
|
Term
| What is Contingency Table or Crosstab? |
|
Definition
| 2 dimensional frequency distribution in which the frequencies of two variables are crosstabulated. Ex; Had data on pateint's sex and whether they were nonsmokers, light smokers, or heavy smokers. |
|
|
Term
|
Definition
| Concluding that a relationship exists when it does not=Rejecting the null hypothesis that is true |
|
|
Term
|
Definition
| Concluding that a relationship doe snot exist when it does= Accepting the null hypothesis when it is false |
|
|
Term
| What does the Alpha Level of Significance indicate? What is the minimum Alpha Level for scientific research? What does this mean? |
|
Definition
| Indicates the probability of making a type I error. Minimal acceptable level is .05. Means out of 100 samples, a true null hypthothesis would be wrongly rejected 5 times. |
|
|
Term
| Lowering Type I error will do what to Type II Error? How do you reduce risk of Type II error then? |
|
Definition
| Lowering Type I will increase chances of Type II errors. Reduce risk of Type II by increasing the sample size |
|
|
Term
| What is BETA Level of Significance? How is this estimated? |
|
Definition
| The probability of committing a type II error. Estimated through Power of Analysis. |
|
|
Term
| For BETA Level of Significance, what does Power mean? Power = ? |
|
Definition
| Power refers to the ability of a statistical test to detect true relationships. power = (1-Beta) |
|
|
Term
| What is the criterion for an acceptable risk for Type II error? |
|
Definition
|
|
Term
| What is Confidence Intervals? What percentage is usually used? |
|
Definition
| Indicate the upper and lower confidence limits and the probability that the population value is between those limits. Usually use either 95% or 99% Confidence Interval |
|
|
Term
| What does the P-Value tell you? What does the numerical value mean? |
|
Definition
| Probability level that determines if something is caused by change fluctuations. Probability of rejecting the Null Hypothesis of a study questions when that hypothesis is ture. Any computed probability GREATER than .05 indicates a NONSIGNIFICANT RELATIONSHIP. |
|
|
