Reading...
Play button
Play button
Use LEFT and RIGHT arrow keys to navigate between flashcards;
Use UP and DOWN arrow keys to flip the card;
H to show hint;
A reads text to speech;
74 Cards in this Set
- Front
- Back
|
Match the type of research with type of reasoning.
|
Qualitative is inductive.
Quantitative is deductive. |
|
|
How does qualitative research differ from quantitative research?
|
Qualitative: hositic description; quality of relationships, actions, situations; uses a naturalistic, contextual approach; emphasizes understanding.
Quantitative: Obtain numerical data; uses empirical methods, stats; emphasizes prediction, generalizability, and causality. |
|
|
Why is experimental research conducted?
|
To test hypotheses about the effects of one or more variables or dependent variables.
|
|
|
Define a variable.
|
Any characteristic, behavior, event, or other phenomenon that is capable of "varying" or existing in at least two different states, conditions, or levels.
|
|
|
What is a constant?
|
A characteristic under study that is restricted to a single state or condition.
|
|
|
Describe differences in DV and IV
|
IV: symbolized with "X"; referred to as treatment or intervention; is manipulated by researcher.
DV: symbolized by "Y"; not manipulated but observed and measured. |
|
|
IV/DV study tip
|
Each IV must have at least 2 levels and comparisons on the DV are made across different levels of the IV
|
|
|
What is the method for measuring a detailed written description or audio/video?
|
Content analysis: involves organizing data into categories to summarize and interpet the info.
|
|
|
What is a protocol analysis?
|
A type of content analysis used by psychologists interested in cognitive processes that underlie problem-solving/other complex tasks.
|
|
|
What is interval recording?
|
observing a behavior for a period of time divided into equal intervals. Interval recording especially useful for observing and recording complex interactions and behaviors (e.g., talking, playing)
|
|
|
What is "event sampling"?
|
A type of recording that entails observing a behavior each time it occurs. Especially good for studying behaviors that occur infrequently, that have a long duration, or that leave a permaent record (e.g. completed a worksheet)
|
|
|
What is situation sampling?
|
an alternative to behavioral sampling, and is used when the goal of the study is to observe a behavior in a number of settings - helps increase the generalizability of the study's findings.
|
|
|
What is "sequential analysis"?
|
Coding behavioral sequences rather isolated behavioral events and is used to study complex social behaviors.
|
|
|
What is one difference between nonexperimental and experimental research?
|
Nonexperimental research is conducted to collect data on variables while experimental research is ocnducted to test hypotheses about the relationships between variables.
|
|
|
Quasi-experimental research versus experimental research?
|
In quasi experimental reserach, an experimenter cannot control the assignment of subjects to treatment groups, must used intact (pre-existing) grups or a signle treatment group. Less control as in a true experiment; consequently less causal inference.
|
|
|
What research design characteristics distinguishes true experimental research from quasi?
|
Random assignment.
|
|
|
What is simple random sampling?
|
Every member of the population has an equal chance of being in the population. The selection of one member has no effect on the selection of another member. Reduces probability of bias, especially if sample size is large.
|
|
|
What is stratified random sampling?
|
"strata" or characteristics of interst and relevant to research hypothesis. Randomly selecting subjects from each stratum to ensure representation.
|
|
|
What is cluster sampling?
|
Selecting units of individuals rather than individuals and then randomly selecting within the unit.
|
|
|
Difference between random assignment and random selection?
|
Assignment allows an investigator to be more certain that an observed effect on the DV wa actuallycaused by the IV while "selection" enables the investigator to generalize findings from sample to population. Assigned to different treatment groups allows the experimetner to be more certain that groups are initially similar.
|
|
|
What three factors cause variability in the study's dependent variable?
|
1)experimental variance (the IV)
2) systematic error (extraneous variables) 3) random error (due to fluctuations in subjects, methods, conditions). Goal is to maximize variability due to IV, control extraneous variables, and minimize random error. |
|
|
What techniques would control the effects of extraneous variables (or one source of systematic error?
|
1) Randomization (assignment) of subjects to tx groups.
2)Holding it Constant - using homo. groups, but limits generalizability. 3) Matching subjects on status on that variable 4) Blocking - building it into the study (e.g., level of severity) 5) statistical control - ANCOVA - especially in quasi-exp. |
|
|
What are the most important things to remember about choosing a research design?
|
Choose a research desing that minimizes the effects of both systematic and random error.
|
|
|
What are sources of random error?
|
distractions or fluctuations in environment, measuring devices, fatigue during study.
|
|
|
When is matching the most useful?
|
When the number of subjects are too small to guarantee that random assignment will euqalize the groups to control the effects of an extraneous variable.
|
|
|
When is a study said to have internal validity?
|
When the investiagor can determine if there is a causal relationshiop between independent and dependent variables? Or, the three sources of variabilty have been controlled.
|
|
|
What is meant by a threat to internal validity?
|
The investigator cannot maximize the IV, or control/minimize systematic and error variance; therefore, cannot be certain that changes in the DV are attributable to the IV
|
|
|
What is maturation as a threat to internal validity?
|
any biological or psychological change that occurs within subjects during the course of a study as a function of time (not related to research hypotheses).
|
|
|
What is the best way to control maturation and history?
|
Include more than one group in the study and randomly assign subjects to groups.
|
|
|
What is "history" as a threat to internal validity?
|
An external event systematically affects the status of subjects on the DV. Most likelyl to be a problem when a study includes only one group and the event occurs at the same time the IV is applied (e.g., change in hospital staff)
|
|
|
What is "testing" as a threat to internal validity?
|
Practice effects or other exposure to a test that alters subjects test performance.
|
|
|
What is Instrumentation as a threat to internal validity?
|
Changes in the accuracy or sensitivity of measuring devices or procedures during the study. Includes improvements in a raters observations.
|
|
|
What is statistical regression as a threat to internal validity?
|
Tendency of extreme scores on a measure to regress toward the mean when the measure is readministered to the same group of people. Threatens a study when subjects selected because of their extreme status on the DV.
|
|
|
What is selection as a threat to internal validity?
|
method used to assign subjects to treatment groups results in systematic differences between groups. Often a problem when intact groups are used.
|
|
|
What is attrition as a threat to internal validity?
|
Subjects drop out. Can use pretesting can help determine if dropouts and non dropouts differ with regard to their initial status on the DV.
|
|
|
What is meant by "external validity"?
|
Findings can be generalized to other people, settings, conditions.
|
|
|
What is the difference between population validity and ecological validity?
|
Population describes the generalizability of research results to other people. Ecological refers to generalizability in other settings?
|
|
|
When is ecological validity the a bigger concern?
|
In analogue studies ( in the lab or other non-naturalistic settings).
|
|
|
What is meant by "interaction between testing and treatment" as a threat to external validity?
|
Study's results have been contaminated by pretest sensitization. Can be controlled by using the Solomon four-group design wheich enables an investigator to measure the impact of pretesting on both the external and internal validity.
|
|
|
Which type of threat to external validity is controlled with a Solomon four-group design?
|
Interaction between testing and treatment.
|
|
|
What is meant by "interaction between selection and treatment" as a threat to external validity.
|
Subjects in a study that have characteristics that make them respond to the IV in a particular way. (volunteers more motivated). Ensure sample representation.
|
|
|
What is meant by "Reactivity" as a threat to external validity?
|
Participants respond to an IV because they know their behavior is being observed.
|
|
|
What are demand characteristics?
|
Cues in the experimental setting that inform subjects of the purpose of the study or suggest what behaviors are expected of them.
|
|
|
What is experimenter expectancy?
|
Experimenter unintentionally provides subjects with cues that let them know what is expected or act in ways that bias the results (computational errors)
|
|
|
What are some ways to control reactivity?
|
Deception, unobtrusive measures, single or double-blind study.
|
|
|
What is multiple treatment interference as a threat to external validity?
|
In a within subjects design and each subject is exposed to multiple levels of the IV.
|
|
|
What can be used to control multiple treatment interference?
|
Counterbalancing - different subjects receive the levels of the IV in a different order.
|
|
|
What is the Latin square design?
|
one type of counterbalanced desing and involves administering each level of the IV so that it appears the sam number of times in each position.
|
|
|
When is a study called a "factorial design"
|
When a study includes two or more independent variables.
|
|
|
What is the major advantage of a factorial design?
|
Provides more through information about relationships among varialbes by allowing an investigator to analyse main effects as well as interaction effects.
|
|
|
What is a between-group research design?
|
Between subjects; the effects of different levels of an IV to a different group and then compare the status or performance of the groups on the DV
|
|
|
What is the difference between a main effect and an interaction effect?
|
Main is the effect of one IV on the DV, regardless of all other variables. Interaction occurs when the effects of an IV differ at different levels of another IV. Interaction effects invalidate conclusions drawn on main effects alone.
|
|
|
What is a within-subjects research design?
|
All levels of the IV are administered sequentiall to all subjects.
|
|
|
What is a single-group time-series design.
|
One type of within-subjects design where the effects of the IV are measured at regular intervals befor and after treatment is applied. This procedure allows subjects to act as their own no-treatment control.
|
|
|
What is the greatest therat to internal validity in the single-group time-series design?
|
History - exposure to an external event could occur at the same time the IV is applied. Maturation is not a threat because these effects can usually be detected.
|
|
|
In a repeated measures design, what is meant by carryover effects and what method can be used to control for it?
|
Multiple treatment interference where one level of the IV carries over and influences the next level. Counterbalancing controls for this.
|
|
|
What is autocorrelation?
|
A disadvantage of time-series/within subjects designs. Pre-test and post-tests are correlated and inflate type I error.
|
|
|
What is meant by a mixed design?
|
Combined between-group and within-group.
|
|
|
What are the two characteristics of a single-subject desing
|
Derived from behavioral psychologists. 1st, each subject has a baseline or no-treatment phase and then a treatment phase. 2nd, dependent variables are measured repeatedly at regular internvals throughout the baseline and treatment phases. Controls maturation effects.
|
|
|
What is the most common single-subject design?
|
AB Design. includes a single baseline (A) phase and a single treatment (B) phase.
|
|
|
What is a Reversal Design?
|
The AB design expanded to ABAB. Withdrawal desing where the treatment is withdrawn and a new baseline is measured and then treatment re-established. Provide additional control over threats to validity.
|
|
|
What is a multiple baseline design?
|
When reversal desing is inappropriate or not ehtical (e.g., withdrawing an anger management technique), instead, sequentially applying the treatment to different behaviors, or settings.
|
|
|
What are some examples of nominal scales of measurement?
|
Sex of salespeople, religion, political affilation, place of birth, DSM diagnosis.
Primary limitation - the only mathematical operation is to count frequency of cases. |
|
|
What are some examples of ordinal scale of measurement?
|
Ranks and LIdert-scale where one has more or less of a characteristic being measured than another person. Freshman versus sophmore.
Primary limitation - Do not lend to determining just how much difference there is between scores. |
|
|
What are some examples of interval scale of measurement?
|
Equal intervals between successive points on a scale. Standarized IQ test. Allows for mathematical operations of addition and subtrations so that data is interpretable. Zero is arbitrary, not absolute.
|
|
|
What are some examples of ratio scale of measurement?
|
True zero - most mathemtaically complex. Allows for multiplaication and division for ratio scores. So, can conlude that if someone selling $1000 of goods, they have sold twice as much as the person selling $500.
|
|
|
Types of Scales - study tip
|
The word frequency does not immediately imply nominal scaling. It is only nominal when the frequency or number of individuals in each category is compared. Calculating the frequency of aggressive acts and number of hours studied is on a ratio scale.
|
|
|
Types of Frequency polygons
|
Leptokurtic Distribution: more Peaked than normal.
Platykurtic: more flatter than normal. Mesokurtic: normal distribution. POsitive versus negative skew: where is the tail? |
|
|
What is the mode?
|
the score or category that occurs most frequently in a set of data. Primary advantage: easy to identify
Disadvantage: susceptible to smaple fluctuations and not useful for stats and serves only as a descriptive technique. |
|
|
What is the median?
|
score that divides a distribution in half when the data have been ordered from low to high.
Advantage: distribution is not affected by extreme scores. Disadvantage: affected by the magnitude of every score in the distribution..can be misleading. |
|
|
Choosing a measure of central tendency
|
Nominal: mode
Ordinal: mode or median Interval: mean, mode, or median Ratio:mean, mode, or median |
|
|
What happens to measures of central tendency in skewed distributions?
|
Positively skewed: mean is greater than the median, than the mode.
Negatively skewed: mean is Less than the median, than the mode. |
|
|
Range as a measure of variability
|
Subtracting the lowest score in the distribution from the highest score. Based on two most extreme scores - misleading when a distribution contains atypical scores.
|
|
|
Variance (Mean Square)
|
provides a measure of the average amount of variability in a distrubiton by indicating a degree to which the scores are dispersed around the distribution's mean. Sum (X-M)2/N-1
|
