click below
click below
Normal Size Small Size show me how
PSY 220 Ch 5
Measuring Variables and Sampling
Question | Answer |
---|---|
A condition or characteristic that can take on different values or categories. | Variable |
The assignment of symbols or numbers to something according to a set of rules. | Measurment |
The use of symbols, such as words or numbers to classify or categorize measurement objects into groups or types. | Nomial scale |
A rank order measurement scale. | Ordinal scale |
A scale of measurement with equal intervals of distance between adjacet numbers. | Interval scale |
A scale of measurement with rank ordering, equal intervals, and an absolute zero point. | Ratio scale |
The consistency or stability of scores. | Reliability |
The type of correation coefficient used as an infex of reliability. | Reliability coefficient |
Consistency of a group of individuals' scores on a test over time. | Test-retest reliability |
Consistency of a group of individuals' scores on two verios of the same test. | Equivalent-forms reliability |
Consistency with which items on a test measure a single construct. | Internal consistency reliability |
The most frequently used index of internal consistency. | Coefficient alpha |
Another name for coefficient alpha. | Cronbach's alpha |
The degree of consistency or agreement between two or more scores, judges, observers, or raters. | Interrater reliability |
The percentage of time that different observers' ratings are in agreement. | Interobserver agreement |
Accuracy of inferences, interpretations, or actions made on the basis of test scores. | Validity |
The way a construct is represented and measured in a particular research study. | Operationalization |
Gathering of evidence regarding the soundness of inferences made from test scores | Validation |
Judgement by experts of the degree to which items, tastks, or questions on a test adequately represent the construct. | Content-related evicence or content validity |
Prima facie judgement of whether the items appear to represent the construct and whether the test or instrument looks valid | Face validity |
Construct consisting of two or more dimensions; contrasted with a unidimensional construct. | Multidimensional construct |
A statistical analysis procedure used to determine the number of dimensions present in a set of items | Factor analysis |
The degree to which a set of items measures a single construct. | Homogeneity |
The type of correlation coefficient used in validation research | Validity coefficient |
Degree to which scores predict or relate to a known criterion such as a future performance or an already-established test. | Criterion-related validity |
Degree to which scores obtained at one time correctly predict the scores on a criterion at a later time. | Predictive validity |
Degree to which test scores obtained at one time correctly relate to the scores on a known criterion obtained at approximately the same time | Concurrent validity |
Validity evidence based on the defree to which the focal test scores correlate with independent measures of the same construct. | Convergent validity evidence |
Validity evidene based on the degree to which the focal test scores do not correlate with measures of different groups. | Discriminant validity evidence |
Degree to which groups that are known to differ on a construct actually differ according to the test used to measure the construct. | Known groups validity |
The reference group upon which reported reliability and validity evidence is based. | Norming group |
The set of elements selected from a population. | Sample |
The basic unit selected. | Element |
The full set of elements from which the sample is selected. | Population |
The process of drawing a sample from a population. | Sampling |
Sample that resemble the population | Representative sample |
Sampling method in which each indicidual element has an equal probability of selection into the sample. | Equal probability of selection method |
Numerical characteristic of sample data. | Statistic |
Numerical characteristic of a population. | Parameter |
Differences between sample values and the true population parameter. | Sampling error |
Collection of data from everyone in the population. | Census |
A list of all the elements in a population. | Sampling frame |
The percentage of people selected and who participated in the study. | Response rate |
A nonrepresentational sample. | Biases sample |
Generalizaation to people, places, settings, and contexts that are similar to those described in the research study. | Proximal Similarity |
A popular and basic equal probability selection methods. | Simple Random Sampling |
Division of population elements into mutually exclusive groups and then seletion of a random sample from each group. | Stratified random sampling |
The population elements are divided for the purpose of stratified sampling. | Stratification variable |
Stratified sampling where the sample proportions are made to be the same as the population proportions on the stratifcation variable. | Proportional stratifed sampling |
Sample proportions are made to be differnt from the population proportions on the stratification variable. | Disproportional stratified sampling |
Cluster is randomly selected. | Cluster random sampling |
A collective type of unit that includes multipe elements. | Cluster |
Clusters are randomlly selected and all the elements in the selected clusters constitute the sample. | One-stage Cluster sampling |
Clusters are randomlly selected and a random sample of elements is drawn from each of the selected clusters. | Two-stage Cluster Sampling |
The sampling method where one determines the sampling interval (k), randomly selects an element between 1 and k, and then selets every kth element. | Systematic Sampling |
The population size divided by the desired sample size; it's symbolized by the letter (k). | Sampling Interval |
Problematic situation in systematic sampling that can occur if there is a cyclical pattern in the sampling frame. | Periodicity |
Use of people who are readily avaliable, volunteer, or are easily recruited for inclusion in a sample. | Convienience sampling |
A researcher decides on the desired sample sizes or quotas for groups identified for inclusions in the sample, followed by convenience sampling from the groups. | Quota sampling |
A researcher specifies the characteristics of the population of interest and then locates individuals who have those characteristics. | Purpose sampling |
Each sampled person is asked to identify other potential participants with the inclusion characteristics. | Snowball sampling |
Selection of participants using a random sampling method. | Random selection |
Placement of participants into experimental conditoins on the basis of a chance proces. | Random assignment |
To obtain a representative sample. | Purpose of random selection |
To produce two or more equivalent groups for use in an experiment. | Purpose of random assignment |
A statistical program used to provide a recommended sample size. | Sample size calculator |
Use of a combination of quantitative and qualitative sampling methods. | Mixed sampling |
What are the four scales of measurement, describe? Least quantitative to most quantitative. | 1. Nominal - names 2. Ordinal - grades, [low, med, high) 3. Interval - the year 4. Ratio - from 0 to highest number. i.e weight |
What are the two psychometric properties, describe? | Reliability - consistency or stability of the score of your measurment instrument Validity - extent to which your measurement procedure is measuring what you're actually measuring and how you interpret the scores. |
What are all the types of reliability? (4) | 1.Test-retest reliability:consistency of scores 2.Equivalent-forms reliability:consistency of scores on 2 versions of the same test 3.Internal Consistency Reliability:consistency of each item on test 4.Interrater Reliability:consistency b/t two testrat |
What are the types of validity? (3) Describe the procedures. | 1.Content:Content must adequately represent construct 2.Internal structure:factor analysis for # of constructs. Homogeneity of items, calc. item-to-total correlation and coefficiet a 3.Relations to other variables:concurrent & predictive validity eviden |
What is considered in validity based on content? | 1. Do items appear to represent the thing measured? Face validity. 2. Does the set of items underrepresent content? Exclude any areas or topics? 3. Do the items represent anything other than what is being measured? Any irrelevant items? |
What is considered in validiity based on internal structure? | Multidimensional constructs? This can be determined by factor anaysis (a statistics program) which calculate number of subsets = dimensions = factors. Homogenity of each item is considered which means how each items are related to one another. |
What is homogenity and what two ways can it be indicated? What happens if this value is large? | *Homogenity shows how much a set of items relates what what it is measuing (the construct). *Item-to-total correlation and coefficient alpha. *The larger the homogenity=more strongly items are related |
What is considered in validity based on relations to other variables? | If what is predicitive and concurrent valid and able to be used in tests with the same results that should correlate strongly. This is convergent validity evidence, if it does not, it will be discriminant validity. |
What are the two types of criterion-related validity, describe? | 1. Predictive validity: Using what you believe are true valid constructs to predict it will occur again in a future test. 2. Concurrent validity: Using what you believe are valid constructs to observe if it is happening in the current test. |
What are the four types of random sampling? | 1. Simple Random 2. Stratified Random 3. Cluster Random 4. Systematic Sampling |
What is used to compare reliability and validity for evidence? | Norming group |
What are the two most important sources of information in standardized tests? | Mental Measurements Yearbook (MMY), and Tests in Print (TIP) |
Know the 12 terminology used in sampling. | 1. sample 2. element 3. population 4. sampling 5. representative sample 6. equal probablility of selection method 7. statistic 8. parameter 9. sampling error 10. census 11. sampling frame 12. response rate |
What are the four types of nonrandom sampling, and when is it used? | 1. Convinence 2. Quota 3. Purposive 4. Snowball When a specific group is needed to be tested on. |
Which method of random sampling is not an EPSEM? | Disproportional random sampling |
What is the difference between a random selection and random assignment? | Random selection is for obtaining a sample. Random assignment is for placing people in either control or treatment group randomly. |
What are the five things to consider when determining sample size? | 1. 100 or fewer, use entire pop. 2. Larger sample = better 3. See how many other experiment's sample size 4. Use a table for determining sample size 5. Use sample size calculator |
What are seven ways of sampling for qualitative research? | 1. Maxium variation sampling 2. Extreme case sampling 3. Homogeneous sampling 4. Typical-case sampling 5. Critical-case sampling (important) 6. Negative case sampling 7. Opportunistic sampling (useful or one that sprung up) |