Experimental Final

  1. 1. What is external validity? 
    How well do the findings apply to the real world
  2. 2. What amount of control is associated with experimental study?
    It is a high degree of control but the external validity will be sacrificed 
  3. 3. What did Aronson and Carlsmith do? 
    Took a stand in favor of the experimental studies and they argued that in no way do lab experiments have to be low in external validity and they made some practical suggestions, and these suggestions are ways to increase external validity in experimental studies. 
  4. 4. What are 2 ways to increase external validity in experimental studies?
    • 1. Physical Realism – You create a physical setting that is very similar to the kind of setting that you care about in the real world. 
    • An example of this is, if you are looking at aggression in 1st and 2nd graders then you should do your study in the classroom or on the playground. 
    • 2. Experimental Realism- Refers to the degree to which a study is realistic  or psychological meaningful to the research participants
    • (The participants should truly experience the psychological states that the researchers are interested) an example is to study people who have fear of being around others. It would be easier to do that in a real setting but if you did it in the lab you would want to make sure that you introduce stimulus that would cause the real psychological fear) 
  5. 5. What are validity of tests or inventories?
    The extent to which a test or inventory measures what it is supposed to measure, therefor an intelligence test should measure intelligence
  6. 6. What is content validity of tests?
    The extent to which test items actually represent the type of material they are supposed to represent, so a careful item analysis is important to ensure content validity on standardized tests and inventories, This process of item analysis has been completed for us in regard to standardized test.
  7. 7. What does a test has been vetted mean?
    • It means the test has had an item analysis done and it is valid
    • ****Researchers have to be aware of validity concerns of test used
  8. 8. What is concurrent validity?
    • The degree in which the score on a test or inventory corresponds with another measure of the designed trait
    • Example- We have a test that measures spacial intelligence and we get a score. We can take 2 other tests and compare the scores and if they come up close then we can say the test has concurrent validity
  9. 9. What is Criterion Validity?
    • Established by comparing a score on a test or inventory with a future score on another test or inventory, How well does it predict. 
    • Example GRE, MAT- These scores show how well a student will do well in grad school. You look at the people who took the test and if all do well then you have criterion validity but if they all do poorly then you have to back up.
  10. 10. What is reliability?
    • The Extent in which a test or inventory is consistent in its evaluation of the same individuals or
    • The consistency or repeatability of a measure or observation
  11. 11. What is the one idea that is common to all forms of reliability?
    The reliability of most measures is likely to increase as we increase the number of observations or observations are occasions that go into the measure
  12. 12. What is Inter-rater reliability?
    The degree of agreement among observeors
  13. 13. What is internal consistency?
    Degree in which all of the specific items or observations in multi item measure behave in the same way
  14. 14. What is temporal consistency?
    Test retest reliability—The degree in which a item, scale or instrument correlates in a positive way with itself over time or it measures consistently over time
  15. 15. What 2 techniques do we have determine reliability?
    • 1. The Test retest procedure -- the determination of reliability by repeatedly administrating a test to the same participants 
    • 2. The Split-Half technique—determination of reliability by dividing the test or inventory into two subtests then comparing the two scores made on the two halves.
  16. Ch 7
    • 16. What is the interface between research and culture?
    • The world has become more interconnected – e-mail allows for instance communication around the globe has changed how we think about research, it sometimes helps research and sometimes can impede research. 
  17. ****It is important to note that most psychology journals and text books are published in the U.S. under the influence of American psychologists****
  18. 17. What is Cross Cultural psychology?
    A branch of psychology with a goal to determine whether research results are universal or specific to the culture in which they were reported
  19. 18. What happens if we ignore culture?
    • 1. Ignoring culture impedes Our understanding of a behavior of a group or groups 
    • 2. Impedes our understanding of what might be the universal truths about human behavior that cut across cultural, ethnic and racial groups
  20. ****Because culture is closely tied to concepts such as race, ethnicticy and social class there often is confusion of these terms and this confusion can serve as an obstacle in research involving culture
  21. 19. What is one problem with cross cultural psychology or psychological research?
    A lack of a clear definition of terms
  22. Don’t have to know this for the exam. ☺ 
    • 20. What are the definitions of culture?
    • 1. Lasting values, attitudes and behaviors that are shared by a group that are past down to subsequent generations
    • 2. The human made part of the environment
    • 3. Social Norms, roles, beliefs, values, attitudes, family roles, communication patterns, spirituality and religiosity
    • 4. Highly variable systems of meaning which are learned or shared by a people or an identifiable segment of the population
  23. Do have to know this for the exam. ☺ 
    • 21. What do Scholars and Pollsters of use the concept of culture interchangeably with?
    • Race, ethnicity and nationality. 
    • For example some surveys or questionnaires may ask race - choose from one of the following categories; Black, white, Asian, Latino (This is flawed when doing research) 
  24. 22. What should race technically refer to?
    • Physical characteristics that might be reflective of a particular group of people ex skin tone, facial features and hair type which are common to a group. 
    • But non of this is proof positive of ethnicity 
    • Classification of people into groups based on race is not good because it is not very specific and it revels very little about people and race as a variable has the least value of anything
  25. 23. What does ethnicity mean?
    Where the person is from, the person country of origin or their heritage
  26. 24. What does research tell us very consistently about racial groups?
    That there are more differences within racial groups than between racial groups
  27. 25. What is the definition of Ethnicity?
    • Often used interchangeably with culture, Ethnicity refers to groups that are characterized in terms of a common nationality, culture or language
    • Ethnicity is related to the Greek concept Ethos which means refers to a people of a nation or tribe
  28. 1. How is race defined?
    In terms of physical characteristics such as skin color, hair type, and facial features and things like this, that are common to a group. It is not good to do research using race
  29. 2. What is Ethnicity?
    Is used to reference groups that are characterized in terms of a common nationality, culture and language. This is the best way to do research using ethnicity
  30. Pg 142
    • 3. What is the Ultimate goal of cross cultural research?
    • Is to discover etics and emics.
  31. 4. What is etics?
    A finding that is the same in different cultures. These are behaviors that are common to most or all societies. May also be referred to as universals
  32. 5. What is an emic?
    Is a cultural specific finding, behaviors that are found only in one or a few societies.
  33. 6. When looking at etics and emics what is the way to do research on them?
  34. 7. What Must exists in order for there to be human life that has some sort of order.
    Certain Universals or etics
  35. 8. What are the 3 Universal behaviors or dynamics that seem to exist across all cultures?
    • 1. Norm of trust – There has to be some level of trust that exists in all cultures so that there is not complete chaos
    • 2. Norm of Truth – People are expected to be truthful but there has to be some truth in order for there to be some order
    • 3. Norm of Turn taking in dialogue
  36. 9. What is a Norm?
    Is a prescription for social behavior or a guide to appropriate behavior in any given setting
  37. 10. What are the effects of Culture on the research process?
    • 1. The choice of the research problems – simply put some problems are important in some cultures than in others
    • 2. Nature of the experimental hypothesis – you need to have some sort of understanding of the culture you are evaluating before you state your hypothesis
    • 3. Selection of the independent variable and recording of the dependent variable – Might have to do with what technology you have available to you. The variables might change if you are in the mountains or if you are in a city
  38. 11. Methods and analysis issues associated with cultural concerns.
    • 1. Participants and sampling procedures – you have to make sure the process that you are going to sample, make sure that the individuals are truly representative of the culture of interest
    • 2. The type of survey or questionnaire used – offer alternative surveys (that may be in another language if need be)
    • 3. Language and translation becomes a problem – you must determine the trait or concept is valued in other cultures
  39. 12. What is Cultural response set?
    The tendency of a particular culture to respond in a certain manner – we know that some cultures are more passive or more agreeable than others, we know that some cultures are more nay sayers and some are more yay sayers. There may be differences in how people in different cultures respond to likert scales
  40. What is Internal and External validity in regard to experimental study.
  41. Pg 147
  42. 1. When you consider Internal validity, it is asked that weather the independent is the only possible explanation of the results shown for the what?
    Dependent variable
  43. 2. When a study is high is Internal validity what can we confidently say about the independent variable?
    We can confidently conclude that variations in the Independent variable that caused any of the observable changes in the dependent variable, but you can not conclude without absolute confidence because there will always be some issues of validity and you hope that you will be high in Internal validity
  44. 3. What is Internal Validity?
    The extent in which a set of research findings provides compelling information about causality or cause and effect
  45. 4. Why is Experimental Studies Usually High in Internal Validity?
    • 1. Because you are controlling for the extraneous variables
    • 2. Control of individual differences through random assignment to groups
  46. Pg 157
    ***5. When you consider External validity in terms of experimental studies it is asked that do the research results apply to populations and situations that are different from the specific study therefore when a study is high in External we can conclude that the findings will apply to other people and other environments***
  47. 6. What is External validity?
    The extent in which set of research findings provides an accurate description of what happens in the real world
  48. 7. What are specific threats to external and internal validity?
    • 1. People are different but we try to counter this through random assignment to groups
    • 1a. How are people different?
    • Individual differences – the type of research finding that are most susceptible to this threat is where people are exposed to Independent variable and behave as expected. This is referred to as a false experiment or false conclusion.
  49. 1b. Selection Bias and Non Response Bias – This can be a threat to both External and Internal validity – If people are different and they are, and a sampling technique somehow favors one particular kind of person we might come to the general conclusion about people that only apply to a particular type of person. A flaw in your sampling procedures could only favor one particular kind of person and it might not be applicable to the broader population
  50. 1c. What is Selection Bias?
    Results in an unrepresented sample. This is a flaw or a mistake made by the researcher. Although it is a threat to internal validity that it is more of a threat to external validity
  51. 1d. What is Non-Response Bias?
    Has to do with surveys with low response rates are most vulnerable to non response bias
  52. 2. People change – People differ not only from one another but they also differ from themselves. Because people change that can be a threat to internal validity and external validity
  53. 2a. History and Maturation – This mostly has to do with a threat with internal validity, most likely to be a problem when a researcher conducts a Pre test - Post test study in which all participants receive some degree of the independent variable. Particularly highly vulnerable would be a repeated measures study in which there is no control group
  54. *** What is History?
    Refers to changes are occurring more or less across the board in a very large group of people, such as a nation or culture.
  55. *** What is Maturation?
    Refers to specific development changes that are occurring in a particular person or a particular cohort over time. Also can refer to short term changes, does not have to be a permanent change
  56. Pg 148
    2b. Testing and Practice effect – This is a threat to internal validity that occurs because measuring the dependent variable causes a change in the dependent variable, just because you are going through the measuring process. Or The score does not change because of anything other than repeating the test. Or a beneficial effect on a dependent variable measurement caused by previous experience with the dependent variable or the tool, instrument or inventory used to measure the dependent variable

    2c. What is Statistical regression? – A threat to internal validity that occurs when lower scores improve or higher scores fall on a second administration of a test solely as a result of statistical reasons this is called regression toward the mean
  57. ** What is Regression toward the mean?
    • The tendency for people who score high or low scores on a particular
    • measure to score close to the mean on a subsequent testing. Sometimes High scores and low scores can be off that is why it is a threat to internal validity
  58. 2d. Mortality – a threat to internal validity that can occur if research
    participants from different groups drop out at different rates
  59. 2e. Diffusion or imitation of treatment – this is a threat to internal
    • validity – this can occur if participants in one research group becomes
    • familiar with a treatment of another group, and they copy that treatment. This can occur easily if the treatment provides some information to one group but not to participants to the other group.
  60. 2f. Process of studying people changes people – The Hawthorne effect – It is a threat to external and internal validity
  61. 2g. Observer or researcher bias – you are recording in a biased manner because you are looking for certain results – this can be a threat to internal and external validity
  62. 3. Instrumentation – Is a threat of internal validity – Refers to changes in measurement of the dependent variable that is due to the measuring device whether it is a piece of equipment or human. Sometimes called instrumental decay. Examples – faulty equipment and human error in recording and observing.
  63. 4. What are the two approaches to Protecting Internal validity?
    • 1. Controlled procedures – these are across the board in experimental
    • 2. Standard procedures – these are the procedures that you use specifically to implement your study.
  64. 5. What is descriptive statistics?
    Are procedures used to summarize a set of data example measures of central tendency – for instance the mean
  65. 6. What is Inferential statistics?
    Are procedures used to analyze data after an experiment is completed in order to determine whether the independent variable has a significant effect, Only when you are talking about experimental study.
  66. 1. When are descriptive statistics used?
    Are used when we want to summarize a set or a distribution of numbers in order to communicate their essential characteristics
  67. 2. What are the 4 scales of measurement?
    • 1. Nominal scale – A simple classification system – events are simply assigned to categories – you would have categories and a number of responses
    • 2. Ordinal scale – A scale of measurement that permits events or data to be ranked ordered – example is like a race you have 1st place, 2nd place and 3rd place you know how they are ordered but you don’t know how far ahead the 1st place is from 2nd or 3rd place.
    • 3. Interval Scale – The scale of measurement that permits rank ordering with the assumption of equal intervals of adjacent events. Example – ACT scores are ranked – The problem with this is there is no absolute 0 point.
    • 4. Ratio scale – Has an absolute 0 point – The presents of a true 0 is only characteristic of this scale – Which allows for ranked ordering with assumptions of equal intervals, with this data when you say 0 it means 0. It allows you to make statements like twice as much or half as much.
  68. 3. The scale of measurement that is used is one factor that goes into determining what?
    What measure of central tendency that is going to be used
  69. 4. What is the measure of central tendency?
    The mean, median and mode
  70. 5. What does the measure of central tendency tell us?
    About the typical score in a distribution
  71. 6. What is the mean?
    Simply put the mathematical average of a set of numbers. We know this is found by adding all the numbers and dividing by n (the amount of numbers in a distribution) In APA we express the mean with an m. You can calculate the mean for Interval and Ratio but not for Nominal and Ordinal
  72. 7. What is the median?
    The number that divides a distribution at the midpoint. To find this you must numerically order the numbers. The median can be a number that is not an actual number in the combination. It can be calculated for Ordinal, Ratio and Interval data
  73. 8. What is the mode?
    Is the score in a distribution that occurs most often, you can have a bi-modal distribution, which means has 2 mode. The mode is the ONLY measure of central tendency that can be used for Nominal data.
  74. 9. What are the four guidelines in choosing your measure of central tendency?
    • 1. The scale of measurement
    • 2. The type of information that you are wanting to communicate
    • 3. Nature of the distribution
    • 4. The Mean (more times and not you are not going to look at the first 3) The problem with the mean and the mode as well they are very susceptible to outliers or extreme scores. The more numbers that you have in a distribution the less influence an outlier has
  75. Graphing the results
  76. 10. What are your choices of graphs determined by?
    The type of graph that depicts your results most effectively and the by the scale of measurement used
  77. 11. What are the different type of graphs?
    • 1. Pie Chart – Graphical representation of the percentage of each alternative.
    • 2. Histogram – A graph in which the frequency for each category of a quantitative variable is represented by a vertical column that touches the adjacent column
    • 3. Bar Graph – A graph in which the frequency for each category of a qualitative variable is represented by a vertical column but the columns do not touch. Categories that cannot be numbered, For example marital status
    • 4. Frequency Polygon – A graph that is made by placing dots in the center of each bar of a Histogram then connecting the dots and then removing the bars
    • 5. Line Graph – In constructing a line graph you start with 2 dimensions, you have your vertical or y-axis known as the ordinate and you have the horizontal or x-axis know as the abscissa. It is for an Independent variable and the dependent variable – The Dependent variable is plotted on the ordinate or the y-axis and the Independent variable data is plotted on the abscissa or x-axis
  78. 12. What is a general rule in constructing a line graph?
    That the Y-axis or ordinate should be 2/3’s as tall as the x-axis
  79. 13. What is variability?
    The extent to which the scores in a distribution are spread out
  80. 14. What is the Range?
    Subtract the smallest from the Largest
  81. 15. What is the variance?
    Is a single number that represents the total amount of variation in a distribution, it is the square of the standard deviation
  82. 16. What is the Standard Deviation?
    Square Root of the variance
  83. 17. What is important about the standard deviation in terms of research?
    It is the relation to the bell curve as with the variance the larger the standard deviation the greater the spread
  84. 18. What is a bell curve normal distribution?
    It is a symmetrical bell shaped distribution, having half the scores above the mean and half below the mean. All measures of central tendency on the bell curve is the same
  85. 19. What is Correlation?
    Is Not cause and effect!!!! You are looking at a relationship, not whether one causes the other.
  86. 20. What is the Person product correlation coefficient?
    The most common measure. It is utilized when both variable are both interval or ratio
  87. 21. If it is not interval or ratio data what scale do you use?
    Spearman Row
  88. 22. How do you know what statistics to you if it is a One tail or two tail?
    • Your hypothesis -- If it is a directional it is a One tail T
    • If it in Non directional it is a 2 tail T
  89. 23. When an experiment is conducted must be used to determine what?
    • What statistics do you use to find out whether the Independent variable had a significant effect on the dependent variable or if the change in the dependent variable just happened by chance?
    • Inferential Statistics
  90. 24. What does inferential statistic with a small value mean?
    Implies that the results occurs frequently by chance
  91. 25. What does an inferential statistic with a large value mean?
    That the results would occur rarely by chance
  92. 26. What is the goal of an experiment?
    To reject the NULL
  93. 27. What is the Null hypothesis for an experimental study?
    The hypothesis that says that all differences between groups specifically is there a significant difference between the control group and the experimental group. With regard to the Dependent variable and with inferential statistics you are hoping to answer that question. The difference that exists between the control group and the experimental group, did it just happen by chance or did it occur because of the Independent variable.
Card Set
Experimental Final
Final Notes