NCE Study Set - Research and Program Eval CH 9
Wilcoxon Signed Rank Test
-T test -a non-parametric test that looks for differences between two correlated samples. -It is the non-parametric equivalent of the related t-test. ** the Mann Whitney U looks at 2 UNcorrelated samples
ANCOVA (analysis of covariance)
-the ANCOVA tests a NHypothesis regarding the means of 2 or more groups AFTER the random samples are adjusted to eliminate average differences. - similar to an ANOVA, but more powerful because it can eliminate differences between groups which otehrwise could not be solely attributed to the experimental IVs. - The ANCOVA allows you to correct for the differences in the groups (possibly due to athletic training or other extraneous variables). By making the groups more alike upfront, it will enhance the possibility that the IVs(biofeedback, meditation, and self-hypnosis instruction) rather than a covariate, such as athletic training caused the differences (I.e. DVs; Anxiety) in the groups.
In the social sciences the accepted probability level is usually
.50 or less
Correlational research requires _____ subjects per variable while a survey should include at least ______.
30; 100.
The WAIS-IV IQ test is given to 100 adults picked randomly. How many of the adults most likely would receive an IQ score between 85 and 115?
68%
Hawthorne effect
A change in a subject's behavior caused simply by the awareness of being studied - Study that work production tended to increase with better lighting or worse lighting conditions. * If subjects knew they were a part of a study, or given attention because of the experiment, their performance sometimes improves.
quasi-experiment
A comparison that relies on already-existing groups (i.e., groups the experimenter did not create). -the IV cannot be altered. - you cannot state with any degree of statistical confidence that IV caused the DV. -EX: Ex post facto study- "after the fact" The IV was adminnnistered before the research began. When conducting a research study, a counselor is concerned with internal/external validity.
Quartile
A division of the total into four intervals, each one representing one-fourth of the total. - 25th percentile is in the firsts quartile - second quartile is the median -third quartile lies at the 75ths percentile **the score distance between the 25th percentile and the 75 percentile is called the interquartile range.
Variable
A factor that can change in an experiment - a behavior or a circumstance that can exist on at least 2 levels or conditions. -a factor that "varies" or is capable of change.
Non-parametric tests
A family of statistical tests that do not rely on the restrictive assumptions of parametric tests. In particular they do not assume sampling distribution is normal. -Normally considered less powerful. -The non-parametric test is one of the methods of statistical analysis, which does not require any distribution to meet the required assumptions, that has to be analyzed. Hence, the non-parametric test is called a distribution-free test. *** List of Non parametric tests: Kruskal Wallis Test Sign Test Mann Whitney U test Wilcoxon signed-rank test
null hypothesis
A prediction that there is no difference between groups or conditions, or a statement or an idea that can be falsified, or proved wrong.
the X axis
AKA abscissa - used to plot the IV
Exam hint: When a research study uses different subjects for EACH condition, some exams refer to this study as a __________ __________ _________.
Between subjects design.
Correlation does not mean
Causation!
ANOVA
Compares mean values of a contributes variable for multiple categories/groups - if you were using a 'parametric' test to examine a NH for 2 means, you could rely on the t test. However if you were using a 'parametric' test to examine NH for 3 means, you use ANOVA
A statistic that indicates the degree or magnitude of relationship between 2 variables is known as
Correlation coefficient. r test - A coefficient of correlation makes a statement regarding the association of 2 variables and how change in one is realted to the change in the other. Correlations range from 0.00 (no relationship) to 1.0 or -1.0 (perfect relationship) ** IMPORTANT: a positive correlation is not a stronger relationship than a negative one of the same numerical value. A correlation of -.70 is still indicative of a stronger relationship than a positive correlation of .60. - negative sign describes that as one variable goes up, the other goes down.
Kruskall-Wallis (one way -ANOVA)
H test A non-parametric method to compare three or more groups -Corresponds to one way ANOVA
In experimental terminology IV stands for _________ and DV stands for __________.
Independent variable; dependent variable. -IV: the researcher manipulates, controls, alters or wishes to experiment with. -DV: the outcome or data of the research.
Regardless of the shape, the ____ will always be the high point when a distribution is displayed graphically.
Mode
Interval scale of measurement
Numerical distances between intervals -Absence of a zero point -distances between each number are equal, yet it is unclear how far each number is from zero. The interval scale is a quantitative measurement scale where there is order, the difference between the two variables is meaningful and equal, and the presence of zero is arbitrary. It measures variables that exist along a common scale at equal intervals. The measures used to calculate the distance between the variables are highly reliable. - Can have negative numbers -Division is not permissible b/c division assumes an absolute zero -Likert scale scores(1 = Strongly disagree; 2 = Disagree; 3 = Neutral; 4 = Agree; 5 = Strongly agree)
Horizontal Sampling
Occurs when a researcher selects subjects from a single socioeconomic group.
halo effect
Occurs when a trait which is not being evaluated (e.g., attractiveness or how well he/she is liked) influences a researcher's rating on another trait (e.g., counseling skill).
Leptykurtic
Peak that is high and thin. Lept = to LEEP tall buildings
Exam hint: if the exam asks a question regarding the type of data which must be used with Pearson r versus the Spearman rho.. remember
Pearson R (IR data) Spearman (Ordinal data)
EXAM Hint: When you see the "Hawthorne effect" question on your exam, you can bet
Rosenthal effect question is within shouting distance. - Hawthorne: Being study improves performance -Rosenthal: Experimenter's beliefs changes treatment of individual and that improves performance. * individual does not know about study*
***Remember: Z scores are the __________ as Standard Deviations
SAME!
The most common measures of central tendency are the mean, the median, and the mode. The mode is
The most frequently occuring score and the least-important -the French phrase, a la mode means "in style" the mode is the score that is most "in style" or occurs the most. ***The modal score is the highest point on the curve.
interquartile range
The score distance between the 25th and 75th percentile.
Example for probability problem/answer
There is only a 5% chance that the difference between the control group and the experimental group is due to chance factors.
Mann-Whitney U test
U test -Determines whether two UNCORRELATED means differ significantly when data are nonparametric - Remember the 'U" looks at UNcorrelated -It is an alternative to the t test when parametric precepts cannot be accepted. - The Wilcoxon Signed looks at 2 Correlated samples
ratio scale
a quantitative scale of measurement in which the numerals have equal intervals and the value of zero truly means "nothing" -Examples: Time, height, weight, temperature on the Kelvin scale, volume, and distance.
cluster sampling
a sampling technique in which clusters of participants that represent the population are used -Uses an existing sample or cluster of people or selects a portion of the overall sample.
ordinal scale
a scale of measurement in which the measurement categories form a rank order along a continuum -ordinal data is quantitative data which have naturally occurring orders and the difference between is unknown. It can be named, grouped and also ranked -worthless to add, subtract, multiply, or divide.
Causal Comparative Design
a true experiment WITHOUT random assignment (Data from the causal comparative ex post factor [after the fact] design can be analyzed with a test of significance [t test or ANOVA] just like any true experiment.)
Parameter
a value obtained from a population while a statistic is a value drawn from a sample. - A parameter summarizes a characteristic of a population (ex: the average male's height is 5'9.
The standard deviation (SD) is the square root of the variance. A Z-score of + 1 would be the same as a. 1 SD above the mean b. 1 SD below the mean c. The same as a so called t score d. the median score if the population is normal.
a. 1 SD above the mean ** Z scores are the SAME as STANDARD DEVIATIONS
Z-scores (also called standard scores) are the same as standard deviations, thus a z-score of -2.5 means a. 2.5 SD below the mean b. 2.5 SD above the mean c. a CEEB score of 500 d. -.05% of the pouplation falls within this area of the curve.
a. 2.5 SD below the mean - This would be a T score of 25. (Remember T scores have mean of 50 and SD of 10. So 2.5 x10 (sd) = 25 AWAY from 50= 25) **CEEB = College Entrance Examination Board score
The range is a measure of variance and usually is calculated by determining the difference between the highest and the lowest score. Thus, on a test where the top score was a 93 and the lowest score was a 33 out of 100, the range would be a. 61 b. 77 c. 59 d. more information is necessary
a. 61 - 93-33 = 60 +1 - Some tests and statistics define range as the highest score, minus lowest score plus 1 - If the test specifies "inclusive range" then use the formula with PLUS 1. If not, go with the "exclusive range" formual which DOES NOT include plus 1.
All of the following describe the analysis of covariance technique except a. It is a correlation coefficient b. it controls for sample differences which exist. c. it helps remove confounding extraneous variables d. it statistically eliminates differences in average values influenced by covariates
a. It is a correlation coefficient
The ordinal scale rank orders variables, though the relative distance between the elements is not always equal. An example of this would be a. a horse categorized as a second- place winner in a race b. an IQ score of 111 c. the weight of an Olympic barbell set. d. a temperature of 78 degrees farenheit
a. a horse categorized as a second-place winner in a race - The ordinal data scale provides relative placement or standing, but does NOT delinate absolute differences. **nomal data do NOT rank like ordinal (you cant place first, second and third place)
In a normal curve the mean, the median, and the mode all fall precisely in the middle of the curve. From a graphical standpoint the so-called normal or Gaussian curve (named after the astronomer/mathematician K. F. Gauss) looks like a. a symmetrical bell b. the top half of a bowling ball c. the top half of a hot dog d. a mountain which is leaning toward the left
a. a symmetrical bell -normal distribution: 68--95--99.7 68% fall within 1 +/- SD; 95% fall within 2 +/- SD; 99.7% fall within 3 +/- SD
The interval scale has numbers scaled at equal distances but has no absolute zero point. Most tests used in school fall into this category. You can add and subtract using interval scales, but you cannot multiply or divide. An example of this would be that: a. an IQ of 70 is 70 points below an IQ of 140 yet a counselor could not assert that a client with an IQ of 140 is twice as intelligent as a client wiht an IQ of 70. b. a 20 lb weight is half as heavy as a 40 lb weight c. a first place runner is 3 times as fast as the third place finisher d. a baseball player with number 9 on his uniform can get 9 times more hits than player number 1.
a. an IQ of 70 is 70 points below an IQ of 140 yet a counselor could not assert that a client with an IQ of 140 is twice as intelligent as a client wiht an IQ of 70 -Division is not permissible b/c division assumes an absolute zero - if there was an absolute zero, then you could in fact assert that a person with an IQ iof 140 is twice as smart as someone with an IQ of 70. You know the starting point would be 0. But, a 0 on an IQ test does not equal zero knowledge, hence IQ tests provide interval measurements.
A good guess would be that if you would correlate the length of CACREP graduates' baby toes with their NCE scores the result would a. close to 0.00 b. close to a perfect 1.00 c. close to a perfect negative correlation of -1.00 d. be about = +.70
a. close to 0.00 - there is NO relationship
A client goes to a string of 14 chemical dependency centers that operate on the 12 step model. When his current therapist suggests a new impatient program the client responds with, "What for, I already know the 12 steps?" This client is using: a. deductive logic b. inductive logic c. an empathic assertion d. an I statement
a. deductive logic - He is taking the general (string of 14 centers on the 12 step) to the specific (he knows the 12 steps) - He assumes that his experience in 14 treatment faclities can be reduced to the specific new treatment.
P = .05 really means that a. differences truly exist; the experimenter will obtain the same results 95 out of 100 times. b. differences truly exist; the experimenter will obtain the same results 99 out of 100 times. c. there is a 95% error factor. d. there is a 10% error factor.
a. differences truly exist; the experimenter will obtain the same results 95 out of 100 times.
A large study at a major university gave an experimental group of clients a new type of therapy that was intended to ameliorate test anxiety. The control group did not receive the new therapy. Neither the clients nor the researchers knew which students received the new treatment. This was a a. double blind study b. single blind study c. typical AB design d. case of correlational research.
a. double blind study -this procedure helps eliminates cofounding caused by "experimenter's effects". - Experimenters effects can flaw an experiment becasue the experimenter might unconsciously communicate his or her intent or expectations of the subjects. -AB or ABA time series is the simplest type of single subject (N=1) research. - some exams will call ABA a "withdrawl design"
Test scores on an exam that fell below 3 SD of the mean or above 3 SD of the mean could be described as: a. extreme b. very typical or within range c. close to the mean d. very low scores
a. extreme
Standardized tests always have a. formal procedures for test administration and scoring b. a mean of 100 and an SD of 15. c. the mean of 100 and a standard errof of measurment of 3 d. a reliability coefficient of +90 or above.
a. formal procedures for test administration and scoring b. is IQ tests
A counselor educator is teaching two separate classes in individual inventory. In the morning class the counselor educator has 53 students and in the afternoon class she has 177 students. A statistician would expect that the range of scores on a test would be a. greater in the afternoon class than morning class b. smaller in the afternoon class c. impossible to speculate without more data d. nearly the same in either class
a. greater in the afternoon class than morning class - Range increases with sample size
A distribution with class intervals can be graphically displayed via a bar graph also called a a. histogram b. sociogram c. genogram d. genus
a. histogram
Occam's Razor suggests that experimenters a. interpret the results in the simplest manner b. interpret the results in the most complex manner c. interpret the results using a correlation coefficient d. interpret the results using a clinical interview
a. interpret the results in the simplest manner - AKA parsimony
Experiments emphasize parsimony, which means a. interpreting results in the simplest way b. interpreting the results in the most complex manner c. interpreting the results using a correlation coefficient d. interpreting the results using a clinical interview
a. interpreting results in the simplest way -Parsimonious means a tendency to be miserly and not overspend. Stingy
An operational definition a. outlines a procedure b. is theoretical c. outlines a construct d. is synonymous with the word "axom"
a. outlines a procedure - its important that researchers "operationally define" procedures so that other researchers can attempt to replicate the experimental procedure. - "axom" is auniversally accepted idea needing no addtional proof (EX: hence REBT is a theory; gravity exists on the planet earth is an axom).
If data indicate that students who study a lot get very high scores on state counselor licensing exams, then the correlation between study time and LPC exam scores would be a. positive b. negative c. 0.00 d. impossible to ascertain
a. positive. - a positive correlation is evident when both variables change in the SAME direction. A negative correlation is evident when the variables are inversely associated; 1 goes up, the other goes down.
A researcher notes that a group of clients who are not receiving counseling, but are observed in a research study group are improving. Her hypothesis is that the attention she has given them has been curative. the best explanation of their improvement would be. a. the Hawthorne effect b. the Halo effect c. the Rosenthal effect d. A type II error
a. the Hawthorne effect
The hunch is known as the experimental or alternative hypothesis. The experimental hypothesis suggests that a difference willb e evident between the control gorup and the experimental group (group receiving IV). Thus if the experiment in question 708 were conducted the experimental hypothesis would suggest:
a. the biofeedback will raise scores. - alternate hypothesis = AKA affirmative hypothesis
The median is a. the middle score when the data are arranged from highest to lowest b. the arithmetic average c. the most frequent value obtained d. never more useful than the mean.
a. the middle score when the data are arranged from highest to lowest ** when deciding the median, line numbers up low to high. - ex: 1,6,7,8,12,90,90 (there are 7 scores and "8" is the middle) -If there are and EVEN amount of numbers, for example 1,6,7,8,10,12,90,90 (there are 8 scores) **You take the arithmetic mean of the 2 middle scores and use as median: 8+10 = 18/2 =9
When a researcher uses correlation, then there is no direct manipulation of the IV. A researcher might ask, for example, how IQ correlates with the incidence of panic disorder. Again nothing is manipulated; just measured In cases such as this a correlation coefficient will reveal a. the relationship between IQ and panic disorder b. the probability that a significant difference exists c. an F test d. percentile Rank
a. the relationship between IQ and panic disorder -Relationship = Correlation coRELATION -r test
A counselor believes that clients who receive assertiveness training will ask more questions in counseling classes. An experimental group receives assertiveness training while a control group does not. In order to test for significant differences between the groups the counselor should utilize a. the student's t test b. a correlation coefficient c. a survey d. an analysis of variance (ANOVA)
a. the student's t test - test of significance (z or t) -the t test is used to ascertain whether 1 sample means are significantly different -student gets t value, turns to back of book to the t table and discover if the t value obtained statistically lower than the t value, in the table, then you accept the hypothesis. ** your computation must exceed the number cited in the table in order to reject the null. ***** if there is an analysis of more than 2 groups you use an ANOVA!
Assume the experiment in question 708 is conducted. The results indicate that the biofeedback helped raise written board exam scores but in reality this is not the case. The researcher has made a a. Type I error b. Type II error c. beta error d. b and c.
a. type I error - this experimenter rejected the notion (NH) that biofeedback wouldn't have any affect on scores. AKA: there would be no chance.
An experiment is said to be confounded when a. undesirable variables are not kept out of the experiment. c. undesirable variables are kept out of the experiment d. basic research is used in place of applied research d. the sample is random.
a. undesirable variables are not kept out of the experiment. "contaminating variable" aka confound
the x axis is used to plot the IV scores. Th x axis could also be called the _________ on your exam.
abscissa
the Y axis
aka ordinate - is used to scale the DV
Basic research is conducted to advance our understanding of theory, while _________ _______ (also called action research or experience near research) is conducted to advance our knowledge of how theories, skills, and techniques can be used in terms of practical application.
applied research
A t-score is different from a z-score. A z-score is the same as the SD. A t-Score however, has a mean of 50, with every 10 points landing at a SD above or below the mean. Thus a t-score of 60 would equal +1 SD while a t Score of 40 would be: a. -2 SD b. -1 SD c. a z-score of +2 d. a z-score of +1
b. -1 SD
A doctoral student who begins working on his bibliography for his thesis would most likely utilize a. SPSS b. ERIC for primary and secondary resources c. O*Net d. a random number table or random number generation computer program.
b. Eric for primary and secondary resources -ERIC.gov is a for scholarly articles. -SPSS is a popular computer softward program to help you do statistics.
There are four basic measurement scales ; the nominal, the ordinal, the interval, and the ratio. The nominal scale is strictly a qualitative scale. It is the simplest type of scale. It is used to distinguish logically separated groups. Which of the following illustrates the function of the nominal scale. a. a horse categorized as a second place winner in a show b. a DSM or ICD diagnostic category c. an IQ score of 111 d. The weight of an Olympic Barbell set.
b. a DSM or ICD diagnostic category - "Noir" Black is Nominal, Ordinal, Interval, Ratio
A bimodal distribution has two modes (ex: most frequently occuring scores). Graphically this looks roughly like: a. a symmetrical bell-shaped curve b. a camel's back with 2 humps c. the top half of a bowling ball d. a mountain which is leaning toward the left.
b. a camel's back with 2 humps When more than 2 peaks it is known as a "multimodal" distrubtion.
A group of first-semester graduate students in counseling took an experimental counseling exam that was much more difficult than the NCE. All of the students scored very low. A distribution of their scores would: a. Always be a bimodal distribution b. be positively skewed c. be negatively skewed. d. produce a curve with a long tail to the left side of the graph.
b. be positively skewed - Most scores would fall on the left side of the distribution. - the tail of the distribution would point to the right or the positive side. - Consider these test scores: 0----------|---------100 Low scores like 47, 62, 38, will all be toward the left side (closer to 0). -There may be a couple of 82, 74, 91 on the right side (closer to 100) -Positively skewed: \
Switching the order in which stimuli are presented to a subject in a study is known as a. the pygmalion effect b. counterbalancing c. ahistoric therapy d. mutiple treatment interference
b. counterbalancing
A researcher studies a single session of counseling in which a counselor treats a client's phobia using a paradoical strategy. He then writes in his research report that paradox is the treatment of choice for phobics. This is an example of: a. deductive logic or reasoning b. inductive logic or reasoning c. attrition or so called experimental mortality d. construct validity
b. inductive logic or reasoning - This is inductive since the research goes from the specific (paradoxical; one session) to generalization (treatment of choice for all phobics)
In a new study the clients do not know whether they are receiving an experimental treatment for depression or whether they are simply part of the control group. This is, nevertheless, known to the researcher. Thus, this is a a. double blind study b. single blind study c. baseline for an intensive N= 1 design d. participant observer model.
b. single blind study -groups don't know, but the researcher knows - if both the group and the researcher doesn't know it is called a double blind. -blind study helps eliminate "Demand Characteristics" which are cues or features of a study which suggest a desired outcome.
A panel of investigators discovered that a researcher who completed a major study had unconsciously rated attractive females as better counselors. This is an example of a. the Hawthorne effect b. the Halo effect c. the Rosenthal effect d. trend analysis
b. the Halo effect
There are 2 distinct types of developmental studies. In a cross-sectional study, clients are assessed at one point in time. In a longitudinal study, however. a. the researcher has an accomplice pose as a client and act in a certain manner. b. the same people are studied over a period of time. c. the researcher relies on a single observation of a variable being investigated. d. all of the above.
b. the same people are studied over a period of time.
Exam Hint: When correlational data describe the nature of 2 variables, the term _________ is utilized. If more than 2 variables are under scrutiny, the term _______ is used to ddscribe the correlational paradigm
bivariate; multivariate
A study that would best rule out chance factors would have a significance level of P=___. a. .05 b. .01 c. .001 d. .08
c. .001 - the smaller the value for P the more stringent the level of significance. AKA there is only 1 chance in 1000 that the results are due to chance. 999 times out of 1000 the experimenter will obtain the same results.
In World War II the Air Force used stanine scores as a measurement. Stanine scores divide the distribution into nine equal intervals with stanine 1 as the lowest ninth and 9 as the highest ninth. In this system 5 is the mean. thus a Binet score of 101 would fall in stanine a. 1 b. 9 c. 5 d. 7
c. 5 - the mean on the Binet is 100, so a Binet score of 101 would fall in stanine 5 -Stanine scores, imagine a normal curve ^. It looks like this below the curve 1 2 3 4 5 (at the Y axis or 0) 6 7 8 9
If an ANOVA yields a significant F value, you could rely on _______ to test significant differences between group means. a. one and two tailed t tests b. percentile rank c. Duncan's multiple range, Tukey's or Scheffe's test. d. Summative or formative evaluation
c. Duncan's multiple range, Tukey's or Scheffe's test. - After running an ANOVA; next step is post hoc Tukey's
An elementary school counselor tells the third grade teacher that a test revealed certain children will excel during the school year. In reality, no such test was administered. moreover, the children were unaware of the experiment. By the end of the year, all of the children who were supposed to excel, did excel! This would be best explained via: a. the Hawthorne effect b. the Halo effect c. the Rosenthal effect d. observer bias
c. Rosenthal effect -" experimenter expectancy effect" - Named for Robert Rosenthal (psychologist)
A researcher creates a new motoric test in which clients throw a baseball at a target 40 feet away. Each client is given 100 throws and the mean on the test is 50. (In other words, out of 100 throws the mean number of times the client will hit the target is 50 times.) Sam took the test and hit the target just 2 times out of 100 throws allowed. Jeff on the other hand, hit the target an amazing 92 times out of 100 trials. Using the concept of satistical regression toward the mean, the researcher would predict that a. Sam's and Jeff's scores will stay about the same if they take the test again. b. Sam and Jeff will both score over 95 next time. c. Sam's score will increase while Jeff's will go down. d. Sam will beat Jeff if they both are tested again.
c. Sam's score will increase while Jeff's will go down. -Statistical regression is a threat to internal validity - Statistical regresssion predicts that very high and very low scores will move toward the mean if a test is adminstered again.
In order for the professor of counselor education to conduct the experiment suggested in question 708, the experimental group would need to receive: a. the manipulated IV b. the biofeedback training c. a and b. d. organismic IV.
c. a and b.
When a distribution of scores is not distributed normally statisticians call it a. Guass Curve b. a symmetrical bell-shaped curve c. a skewed distribution d. an invalid distribution
c. a skewed distribution -in a skewed distribution, the left and right side of the curve are not mirror images. - in a skewed distribution, the mean, meadian, and the mode fall at different points. ( in a normal curve, they will fall at the SAME point)
To complete a t test you would consult a tabled value of t. In order to see if significant differences exist in an ANOVA you would consult a. the mode b. a table for t values c. a table for F values d. the chi-square
c. a table for F values * remember this is a F test for anova.
If a researcher changes the significance level from .05 to .001, then a. alpha and beta errors will increase b. alpha errors increase but beta errors increase c. alpha errors decrease; however beta errors increase d. this will have no impact on Type I and Type II errors.
c. alpha errors decrease; however beta errors increase - remember when you make it so stringent, you may end up accepting the NH when it is actually false.
the null hypothesis suggest that there will not be a significant difference betwen the experimental group which received the IV and the control group which did not. Thus, if the experiment in question 708 was conducted the null hypothesis would be: a. all students receiving biofeedback training would score equally well on the board exam. b. systematic desensitization might work better than biofeedback. c. biofeedback will not improve the board exam scores d. meta- analysis is required
c. biofeedback will not improve the board exam scores - Null = NO change - the null hypothesis is simply that the IV does not affect the DV.
A professor of counseling education hypothesized that biofeedback training could reduce anxiety and improve the average score on written board exams. If this professor decides to conduct a formal experiment the IV will be the ______, and the DV will be the ______. a. professor; anxiety level b. anxiety level; board exam score c. biofeedback; board exam score d. board exam score; biofeedback.
c. biofeedback; board exam score
In order for the professor of counselor education (see question 708) to conduct an experiment regarding his hypothesis he will need a(n) ________ and a(n) ________. a. biofeedback group; systematic desensitization group b. control group; systematic desensitization group c. control group; experimental group d. control group with at least 60 subjects; experimental group with at least 60 subjects.
c. control group; experimental group -the control group does NOT receive the IV; -the experimental group receives the IV.
Sociogram is to a counseling group as a scattergram is to _____. a. the normal curve b. the range c. a correlation coefficient d. the John Henry effect
c. correlation coefficient ** A scattergram (AKA scatterplot) is a pictoral diagngram or graphn of 2 variables being correlated. - John Henry Effect (AKA compensatory rivalry of a comparison group) is a threat to internal validity of an experiment that occurs when subjects strive to prove that an experiment treatment that could threaten their lievelihood really isn't all that effective.
A counselor educator is running an experiment to test a new form of counseling. Unbeknownst to the experimenter one of the clients in the study is secretly seeing a gestalt therapist. This experiment a. is parsimonous b. is an example of Occam's Razor c. is confounded/flaw d. is valid and will most likely help the field of counseling.
c. is confounded/flaw
Which of the following would most likely yield a perfect correlation of 1.00 a. IQ and salary b. ICD diagnosis and salary c. length in inches and length in centimeters d. Height and weight
c. length in inches and length in centimeters -AKA Coveration (when 2 variables vary together staticians say the variables "covary positively" when 1 goes up and other goes down its "covary negatively"
In a basic curve or so-called frequency polygon, the point of maximum concentration is the: a. mean b. median c. mode d. range
c. mode _-remember the modal score is the highest point in a curve
Nine of the world's finest counselor educators are given an elementary exam on counseling theory. The distribution of scores would most likely be a. bell-shaped curve b. positively skewed c. negatively skewed d. indicate that more information would be necessary.
c. negatively skewed - since high scores pack the RIGHT side of the distrubtion, this give you a long TAIL that points to the left. - Picture a cat + tail. -recall previous problem. 0---------|---------100 - if all scores are around 88, 94, 99, 92 it will be closer to 100 - there may be couple of scores near 0 like a 45, but most (where you find the median/mode) will be close to 100. -Negative skewed: /
When you see the letter P in relation to a test of significance it means a. portion b. population c. probability d. the researcher is using an ethnographic qualitative approach.
c. probability - Traditionally, probability in social science research (often indicated by P) has been set to a .05 or lower (.01 or .001). - the .05 level indicates that differences would occur via chance only 5 times out of 100. -this significance level must be set the experiment begins!
A researcher wants to run a true experiment but insists she will not use a random sample. You could safely say that a. she absolutely, positively cannot run a true experiment b. her researcher will absolutely positively be causal comparative research. c. she could accomplish this using systmatic sampling. d. Her research will be correlational.
c. she could accomplish this using systmatic sampling.
In a random sample each individual in the popularion has an equal chance of being selected. Selection is by chance. In a new study, however, it will be important to include 20% African Americans. What type of sampling procedure will be necessary? a. Standard (i.e., simple) random sampling is adequate b. Cluster sampling is called for. c. stratified sampling would be best d. Horizontal sampling is required.
c. stratified sampling would be best -Stratum or a special characteristic needs to be represented. In this case it is race.
The simplest form of descriptive research is the ___________, which requires a questionnaire return or completion rate of _____________ to be accurate. a. survey; 5% b. survey; 10-25% c. survey: 50-75% d. survey; 95%
c. survey: 50-75% *** most surveys have a return rate of about 40%. - Ideal sample size will be at least 100. - Gallup poll is an example of a surey -survey problems include: poor construction of the instrument, a low return rate, and the fact that often subjectss are not picked at random and thus are not representative of the problem.
Behaviorists often utilize N=1, which is called intensive experimental design. The first step in this approach would be to a. consult random number table b. decide on a nonparametric statistical test c. take a baseline measure d. compute the range.
c. take a baseline measure -When there is only 1 person being study, you must start with a baseline to see what IV's do to the person over time. -Case study aka idographic studies; single subject designs -AB design; ABAB; ABC; ABC - popularized by Freud
A researcher gives a depressed patient a sugar pill and the individual's depression begins to lift. This is known as: a. the Hawthorne effect b. the Halo effect c. the Placebo effect d. the learned helplessness syndrome.
c. the Placebo effect - a Nocebo has a negative effect on a person
The most valuable type of research is a. always conducted using a factor analysis b. conducted using the chi-square c. the experiment, used to discover cause-and-effect relationships d. the quasi-experiment
c. the experiment, used to discover cause-and-effect relationships
Researchers often utilize naturalistic observation when doing ethological investigations or studying children's behavior. In this approach a. the researcher mainpulates the IV b. the researcher manipulates the IV and the DV c. the researcher does not manipulate or control variables d. the researcher will rely on a 2x3 factorial design.
c. the researcher does not manipulate or control variables ** Naturalistic means its natural, no manipulation occurs.
If a distribution is bioldal, then there is a good chance that: a. the curve will be normal b. the curve will be shaped like a symmetrical bell c. the researcher is working with 2 distinct populations d. the researcher is useless in the field of counseling.
c. the researcher is working with 2 distinct populations - Normal curve has ONE peak - Symmetrical bell has ONE peak -researcher useless (doesnt make sense)
Mike takes a math achievement test. In order to predict his score if he takes the test again the counselor must know a. the range of scores in his class b. the standard deviation c. the standard error of measurement d. the mode for the test.
c. the standard error of measurement - the SEM tells the counselor what would most likely occur if the same individual took the same test again.
a Platykurtic distribution would look approximately like: a. the upper half of a bowling ball b. the normal distribution c. the upper half of a hot dog, lying on it's side over the abscissa d. a camel's back.
c. the upper half of a hot dog, lying on it's side over the abscissa ** Kurtosis refers to peakedness of a frequency distribution. - Platykurtic is flatter and more spread out. - Plat = FLAT
A Type I error occurs when a. you have a beta error b. you accept null when it is false c. you reject null when it is true d. you fail to use a test of significance.
c. you reject null when it is true
Exam Hint: if your exam describes a true experiment (such as biofeedback research), except for the fact that the groups were NOT randomly assigned, then the new exams are calling this a
causal comparative design
Using the data in question 764 one could say that a person with an IQ score of 122 would fall within a. + or -1 SD of the mean b. the average IQ range c. an IQ score which is more than 2 SD above the mean d. + or - 2 SD of the mean.
d. + or - 2SD of the mean. - 2 SD would be 70-130; since 2 SD is 30 pts. *** the greater the SD, the greater the spread
Which level of significance would best rule out chance factors? a. .05 b. .01 c. .2 d. .001
d. .001
The variance is a measure of dispersion of scores around some measure of central tendency. The variance is the standard deviation squared. A popular IQ test has a SD of 15. A counselor would expect that if the mean IQ score is 100 then, a. the average score on the test would be 122 b. 95% of the people who take the test will score between 85 and 115. c. 99% of people who take the test will score betwen 85 and 115. d. 68% of the people who take the test will score between 85 and 115.
d. 68% of the people who take the test will score between 85 and 115. - Remember: if an IQ test has a mean of 100 and SD of 15, then 68% fall within 1 SD; 95% fall within 2 SD; 99% fall within 3 SD. - 95% between 85-115 wont work. The IQ test 1 SD = 15. AKA 68% - 99% between 85-115 wont work. The IQ test is 1 SD= 15. AKA 68%. To work with b. and c.; the numbers would need to be 70-130 & 50-145.
The researcher in question 727 now attempts a more complex experiment. One group receives no assertiveness training and second group receives 4 assertive training sessions and a third group receives 6 assertiveness training sessions. That statistic choice would be the a. mean b. t test c. two way ANOVA d. ANOVA
d. ANOVA ** if you had 2 IV's you would use a two way ANOVA. This would mean if you tested say Assertiveness training group and drinking tea.
In a parametric test, the assumption is that the scores are normally distributed. In nonparametric testing, the curve is not a normal distribution. Which of these tests are nonparametric statistical measures? a. Mann-Witney U test, often called the U test b. Wilcoxon signed-rank test for matched pairs c. Solomon and the Krukal- Wallis H test d. All of the above are nonparametric measures.
d. All of the above are nonparametric measures. -aka "distribution-free tests"
Experimenters should always abide by a code of ethics. The variable you manipulate/control in an experiment is the a DV b. Dependent variable c. the variable you will measure to determine the outcome d. IV or independent Variable
d. IV or independent Variable - "I am the researcher so I manipulate or experiment with the IV"
Hypothesis testing is most closely related to the work of: a. Robert Hoppock b. Sigmund Freud c. Lloyd Morgan d. R. A. Fischer
d. R. A. Fisher - A hypothesis is a statement which can be tested regarding the relationship of the IV and DV.
When a horizontal line is drawn under a frequency distribution it is known as a. mesokurtic b. the y axis c. the ordinate d. the x axis
d. The X axis --|-- x y
A researcher performs a study that has excellent external or so-called population validity, meaning that the results have generalizability. To collect his data the researcher gave clients a rating scale in which they were to respond with strongly agree, somewhat agree, neutral, somewhat disagree, or strongly disagree. This is _________________________. a. a projective measure b. unacceptable for use in standardized testing c. a speed test d. a Likert Scale.
d. a Likert Scale.
A Type II error a. is also called a beta error b. means you reject the null when it is applicable c. means you accept the null when it is false d. a and c.
d. a and c.
From a mathematical standpoint, the mean is merely the sum of the scores divided by the number of scores. The mean is misleading when a. the distribution is skewed b. the distribution has no extreme scores c. there are extreme scores d. a and c.
d. a and c. - remember the median is the best for skewed distributions.
From a purely statistical standpoint, in order to compare a control group (which does NOT receive IV or exp manipulation) to the experimental group, the researcher will need: a. a correlation coefficient b. only descriptive statistics c. percentile rank d. a test of significance
d. a test of significance test of significance tests are used to determine whether a difference in the groups scores is significant or just due to chance factors. In this case a t test would be used to determine differencde betwen 2 means. -descriptive statistics only DESCRIBES data - Percentile rank- a descriptive statistic that tells the counselor what percentage of the cases fell below a certain level. ** do not confuse percentile ranks with percentages. A percentage score is just another way of stating a raw score.
Type I and Type II errors are called __________ and ________. a. beta; alpha b. .01; .05 c. a and b d. alpha; beta.
d. alpha; beta **Type 1 (Alpha): rejects the NH when it's true. (Says there is no difference, when there really is) ** Type 2 (Beta): accepts the NH when its false (Says there is a difference when there really isn't) - the probability of committing a Type 1 error equals the level of the significance mentioned earlier. - 1 minus Beta is called "the power of a statistical test" (power means a statistical tests ability to reject correctly a false null hypothesis).
Three years ago an inpatient addiction treatment center in a hospital asked their clients if they would like to undergo an archaic form of therapy created by Wilhelm Reich known as "vegotherapy". Approximately half of the clients stated they would like to try the treatment while the other 50% said they would stick with the tried and true program of the center. Outcome data on their drinking was complied at the end of the seven weeks. Today --- thee years later--- a statistician compared the two groups based on their drinking behavior at the endof the seven weeks using a t test. The study could be described as: a. correlation research b. a true experiment c. a cohort study d. causal comparative research.
d. causal comparative research.
Dr. X discovered that the correlation between therapists who hold NCC status and therapists who practice systematic desensitization is .90. A student who perused Dr. X's research told his fellow students that Dr. X had discovered that attaining NCC status causes therapists to become behaviorally oriented. The student is incorrect because a. Systematic desensitization is clearly not a behavioral strategy b. this can only be determined via a histogram c. the study suffers from longitudinal and maturational effects d. correlation does not imply causal.
d. correlation does not imply causal.
Experimental is to cause and effect as correlational is to _____ of _______. a. blind study b. double blind study c. N = 1 design d. degree of relationship
d. degree of relationship -In correlation coefficient- the Pearson Product Moment Correlation r is used for interval or ration data and the Spearman rho correlation is used for ordinal data.
A counselor educator Dr. Y, is doing research on his classes. He hypothesizes that if he reinforces students in his morning class by smiling each time a student asks a relevant question, then more students will ask questions and exam grades will go up. Betty and Linda accidently overhear Dr. Y discussing the eperiment with the department chair. Betty is a real people pleaser and decides that she will asks a lot of questions and try to help Dr. Y confirm his hypothesis. Linda, nevertheless, is angry that she is being exepriumented on and promises Betty that Dr. Y could smile until the cows came in but she still wouldn't ask a question. Both Linda and Betty exemplify a. internal versus external validity b. ipsative versus normative interpretation of test scores c. the use of the nonparametric chi-square test. d. demand characteristics of experiements.
d. demand characteristics of experiements.
Billy received an 82 on his college math final. This is Billy's raw score on the test. A raw score simply refers to the number of items correctly answered. A raw score is expressed in the units by which it was originally obtained. The raw score is not altered mathematically. Billy's raw score indicates that a. he is roughly a B student b. he answered 82% correctly c. his percentile rank is 82. d. more information is obviously necessary.
d. more information is obviously necessary. - His score tells you nothing. - How many questions were there? If there were only 90 questions he scored VERY high. What if there were 160 questions? He scored really low.
A ratio scale is an interval scale with a true zero point. Ratio measurements are possible using this scale. Addition, subtraction, multiplication, and division can be utilized on a ratio scale. In terms of counseling research: a. the ratio is the most practical b. all true studies utilize the ratio scale c. a and b. d. most psychological attributes cannot be measured on a ratio scale
d. most psychological attributes cannot be measured on a ratio scale
Nondirective is to person-centered as a. psychological testing is to counseling b. confounding is to experimenting c. appraisal is to research d. parsimony is to Occam's Razor
d. parsimony is to Occam's Razor -nondirective and person centered is synonymous; both refer to names given to Rogerian Counseling.
A counselor educator decides to increase the sample size in her experiment. This will a. Confound the experiment in nearly every case. b. raise the probability of Type I and Type II errors c. Have virtually no impact on Type I and type II errors. d. reduce type I and type II errors.
d. reduce type I and type II errors. ** Increasing sample size helps lower risks of chance error factors
If an experiment can be replicated by others with almost identical findings, then the experiment is a. impacted by the observe effect b. said to be naturalistic observation c. the result of ethological observation d. said to be reliable
d. said to be reliable
In a career counseling session, an electrical engineer mentions 3 jobs he has held. the first paid $10 per hour, second paid $30 an hour, and third paid higher rate of $50 an hour. The counselor responds that the client is averaging $30 an hour. The counselor is using a. A Pearson Product- Moment Correlation coefficient b. a factorial design c. the harmonic mean d. the mean
d. the mean - the mean is the sum of scores divided by the number of scores.
An IQ score on an IQ test which has 3 SDs above the mean would be near the ____ level. a. about average b. slightly below the norm for adults c. approximately 110 d. very superior
d. very superior
Solomon four-group design
experimental design in which the researcher uses 2 control groups. Only 1 experimental group and 1 control group are pretested. The other control group and expermental group are mearly post-tested 2 different treatment groups, 2 control groups
Rosenthal effect
experimenter belief about the individual may cause the individual to be treated in a special way so the individual begins to fulfill the expectancy -AKA Pygmalion effect
external validity
extent to which we can generalize findings to real-world settings
In a new experiment, a counselor educator wants to ferret out the effects of more than one IV. She will use a _______ design. a. Pearson Product- Moment r b. Spearman rank order rho c. factorial d. Solomon Four group
factorial - In a factorial design, several variables are investigated and interactions noted. - they include 2 more more IVs
nocebo effect
harm resulting from the expectation of harm - When a doctor comments that a person with such and such condition has only 6 weeks to live.
Pygmalion effect
higher expectations lead to an increase in performance AKA Roesenthal effect
standard error of measurement
hypothetical estimate of variation in scores if testing were repeated
Ipsative
implies a within person analysis rather than a normative analysis between individuals. -was your jog today faster than yesterday? Rather than a normative analysis between individuals: did you run as much as her?
*** Remember: Range ______________ with sample size
increases
Exam Hint: Although lowering the significance level (ex: .01 to .001) lowers Type I errors it
increases the risk of ocmmitting a type II error or beta error - you are making it so stringent to eliminate any possiblity that you would reject it when it is true, but you run the risk of accepting it when it really isn't true.
IV does the action; DV
is measured
Nominal Data
level of measurement - NOMINAL is most elementary as it does NOT provide ANY "quantitative" (measurable) information. It merely classifies names, labels, or identifies by group. Nominal has NO true Zero and does NOT indicate order. -examples: street address, telephone number, political party affiliation, brand of therapy, number on players uniform. - adding, subtracting, mutliplying or dividing nominal would be meaningless
CEEB scores (College Entrance Examination Board Score)
mean of 500 and SD of 100 - The scale ranges from 200-800 with a mean of 500. - a score of 200 corresponds to 3 SD from the CEEB mean of 500. *** it is possible that your exam could refer to a CEEB score as an ETS score and the scale was created to eliminate negative scores
The most useful measure of central tendency is the
mean often abbreviated by an X with a bar over it aka average
Exam Hint: The APA's Journal of Counseling Research publishes
more research articles than any other periodical in the field.
Mesokurtic
normal distribution
the y axis is used to plot the frequency of the DVs. The y axis could also be called the ________ on your exam.
ordinate the Y axis is VERTICAL like the letter Y (stands up and down)
***Remember that if you cannot randomly assign the 2 groups (in an experiment) then your exam will consider the research a
quasi-experiment.
Spearman correlation (also known as Kendall's tau)
r test used in place of the Pearson r when parametric assumptions cannot be utilized
snowball sampling
recruitment of participants based on word of mouth or referrals from other participants
parametric tests
rely on assumptions regarding distribution of population and are specific to population parameters. ** List of parametric tests: Two-sample t-test. Paired t-test. Analysis of variance (ANOVA) Pearson coefficient of correlation.
Exam Hint: have you ever placed a sticker on your car and tried to smooth it out? No matter how many times you attempt to do this, the sticker usually retains a few trapped air bubbles. This analogy has often been used in conjuction with
research, in the sense that flaws in research are often called "bubbles".
T-score
standard score with a mean of 50 and a standard deviation of 10 - hence a Z score of -1.0 would be a T score of 40.
MEMORIZE this: The benfit of standard scores such as: Percentiles, T scores, Z scores, Stanines, or Standard Deviations over a raw score is that:
standard scores allow you to analyze the data in relationship to the properties of the normal bell shaped curve. - you are provided with more information if you have a standard score - Raw scores turned to standard scores give more information, without it, you know nothing.
Trend in Counseling research. Meta studies are being used to summarize findings related to a given topic or theme. Cohen's d effect size (ES)
statistic is used to guage how strong a relationship exists (ex: small .2; medium .5; large .8
factor analysis
statistical procedure that use the important or underlying "factors" in an attempt to summarize a lot of variables.
Exam Hint for statistics: The basic rule is to use a parametric t-test for normally distributed data and a non-parametric test for skewed data.
test for skewed data.
range
the difference between the highest and lowest scores in a distribution - EX 1, 4, 19, 3, 8, 26, 5, 8. Range is 26-1 = 25
sampling error
the difference between the results of random samples taken at the same time - Small samples intended to mimic the population sometimes do not! -The average or mean IQ is 100; this is known as the pouplation parameter. -But say you took the mean IQ in a counseling class with 20 students. It could turn out to be 100, but there also is a good chance it might not. (counselor students often have a higher iQ). The margin of errror stated in political poll results is based on this concept.
The median is the best measure of central tendency when
the distribution is skewed
Exam Hint: To reduce Type I and Type II errors, increase
the sample size.
P = .05 really means that
there is only a 5% chance that the difference between the control group and the experimental groups is due to chance factors. - May be referred to as the "95% confidence interval" that means the results would be due to chance only 5x out of 100.
If the researcher in the previous question utilized two IVs then the statistic of choice would be
two way ANOVA aka MANOVA - if 3 IVs its a 3 way ANOVA
internal valdity
were results caused by what you say they were caused by? were alternative explanations ruled out?
Exam Hint: If the same subjects are employed (ex: such as in repeated measures) your exam could refer to it as a _______ ________ ________.
within subjects design.
