kin 250 final
Talk through the parts of a frequency distribution
A frequency distribution has three major columns: the individual scores, the frequency at which each score appeared, and the cumulative frequency of all scores added together progressively.
What makes a likert scale different from a semantic differential scale?
A likert scale assesses a thought, opinion, belief, or attitude by assigning a number, usually on a scale of 1-5 or 1-9, etc. There are no opposite meanings included in these questions Semantic differential scales assess a specific concept, feeling, thought, or attitude with bipolar adjectives that have opposite meanings. There are always 7 response options, with a neutral option in the middle. We also have three options when working with these scales, evaluation, potency, and activity.
Define evaluation
A statement of the quality, goodness, merit, value, or worthiness about what has been assessed
What is a test?
A tool used by kinesiologists to measure or assess a quality of interest
What are advantages and disadvantages of objective questions?
Advantages: cover a wide range of material, easy ish to write (not multiple choice), easy to grade, can be written to many taxonomic levels Disadvantages: multiple choice are time consuming and difficult to write well, matching only tests recognition, T/F encourages guessing and tests for isolated facts, T/F can be read into too much
What are advantages and disadvantages of semi-objective questions
Advantages: easy to write, requires recall of information, simple and easy to scores, reduces guessing Disadvantages: more than one answer may apply, some subjectivity involved in grading, can take time to grade (short answer), limits the answer length
List some advantages and disadvantages of essay questions
Advantages: quickest to write, larger units of information must be studies, eliminates guessing, assesses higher taxonomic levels. Disadvantages: very subjective when grading, quality of writing can influence grading, subject to bias, sampling all areas of instruction is difficult
How should we report results back to athletes?
Anonymously, and with information on where they fall compared to people who take the test (normative data). We should also give them information on how they can improve on certain areas, and help them understand exactly what their results mean.
Give an example of quantitative methodology
Any test or measurement that attaches a number to an observation or response. This is the more traditional, and objective approach, and is often found in most research studies. Some examples might be likert scales, semantic differential scales, metabolic carts, goniometers, scores on push up or sit up tests, etc.
What does a two-way ANOVA allow us to do?
Assess a relationship between the nominally scaled independent variables, and one continuously scaled dependent variables, we can also assess an interaction between the two independent variables on the dependent variables
What is one major reason that we tell athletes why the test is being given
Because they might lie or give socially desirable answers (what they think we want to hear) to stay on the team or not be singled out as an "outsider" Athletes may assume our reason for being there and giving tests is because their coach wants to weed out players, so we need to assure them this is not the case Informed consent is a great practice
What does the interactionist perspective say about human behavior
Behavior comes from an interaction between the traits of the person and the state they are in. Depending on the situation and the person, trait and state may have a greater influence from situation to situation and behavior to behavior
Define muscular actions
Concentric contraction: muscle generates force as it shortens Eccentric contraction: muscle generates force as it lengthens Isometric contraction: muscle generates force but does not change length (no movement) Isotonic Contraction: generates enough force to move a constant load at variable speeds through a range of motion Isokinetic Contraction: muscle generates force at a constant speed through a full range of motion
List and define the different types of validity:
Content validity: professional judgement or logic to determine that the survey items are representative of the content Concurrent validity: extent to which scores on a new measure relate to scores from a criterion measure administered in the same testing session Predictive validity: extent to which scores on a new measure predict performance on a criterion measure given at a later time Construct validity: the degree that results of a test accurately measures an attribute or trait that can't be directly assessed
Give an example of each type of validity
Content: me looking at a measure of team norms on a volleyball team and assessing if it actually appears to ask about team norms Concurrent: a new athlete burnout questionnaire given to a team, then the ABQ given to the same team. Their scores are correlated to see how well the new scores relate to the old scores Predictive: a new motivation survey given to an exercise class, those scores are then used to predict scores on the BREQ-3. The BREQ-3 is actually given to the class a week later, and their actual scores are compared to their predicted scores. Construct: assessing if items on the sport friendship quality scale actually measure the 6 constructs that make up adolescent sport friendships
What is the difference between inferential and descriptive statistics?
Descriptive statistics describe, organize, summarize, and present data. Inferential statistics make inferences about our population and sample, they test hypotheses, determine relationships between independent variables, dependent variables, and make predictions
Calculate the index of difficulty
Diff= (Uc+Lc)/(Un+Ln) X100 Upper group total: 20 Lower group total: 25 Upper correct: 19 Lower correct: 7 Answer: 57.78% (0.5778)
If you had your choice of physical activity assessment tools, would you choose a direct monitoring method, or a self-report method, why?
Direct monitoring methods, like accelerometers or pedometers, because they are often more reliable and valid than self-report alone. Given my absolute best choice, no limits to what I could buy or use, I would go with direct monitoring methods
What were the two exercise motivation scales developed with the exercise context in mind?
Exercise Motivation Inventory Behavioral Regulation in Exercise Questionnaire-3
What is the difference between formative and summative evaluations?
Formative evaluations are initial or immediate assessments. They may also be used throughout the research or teaching process to track change and progress. Summative evaluations are at the end of a training or program. They give us a more formal summary of the participants progress through the program.
What is the difference between the general scales, the sport general measures, and the sport specific measures?
General scales were developed in other research domains not sport related, but they can be used in the sport domain, usually with good psychometric properties. Sport general scales can also be used in sport situations, but they were developed specifically with the sport realm in mind. They would not perform well in other life domains. Sport specific scales were developed for that sport type and only that sport type.
What happens to the standard deviation when there is kurtosis present
In a leptokurtic distribution, there will be a very small standard deviation In a platykurtic distribution, there will be a large standard devliation
When our data is skewed, what does this do to the relationship between the mean, median, and mode
In a normal distribution, these three are generally equal or very close to it. When there is a negative skew the mean is less than the median, which is less than the mode. When there is a positive skew, the mean is greater than the median which is greater than the mode.
What are interval data? Give an example
Interval data are continuous, and they use a common or equal form of measurement. We can tank items and compare the sizes or differences between them. They have a zero point that does not actually mean zero, or absence of a quality.
List and describe the four ways to develop criterion-referenced tests
Judgmental: based on the experience or belief of experts Normative: using norm-referenced data to set standards; theoretically accepted criterion is chosen Empirical: relying on an external measure of a criterion attribute; cutoff scores are developed from the data available Combination: a combo of all three methods
Define muscular endurance, relative endurance, absolute endurance, and repetition maximum
Muscular endurance: physical ability of the muscle to perform work over an extended period Relative endurance: repetitive performance compared to maximum strength Absolute endurance: repetitive performance at a fixed resistance Repetition maximum (RM): how many repetitions you can do before failure at a certain weight
Calculate the index of discrimination
Net D = (Uc-Lc)/Un X 100 Upper correct: 25 Lower correct: 14 Students in the upper group: 25 Answer: 44% (0.44)
Should we use tests for recruitment or draft purposes
No! Why? because they are not designed for this purpose. To use them this way is a gross misconduct, and won't actually asses a real phenomenon anyways
What are nominal data? Give an example
Nominal data name or classify into mutually exclusive categories. This allows us to see the frequency at which each observation occurs. An example of nominal data would be a type of car, or eye color.
What are norm and criterion referenced standards
Norm-referenced: an evaluation based on a comparison with other similar individuals Criterion-referenced: an evaluation based on a comparison with a standard or criterion
What do we measure in the psychomotor domain
Objectives concerned with different aspects of physical health and fitness. Reflex movements, fundamental movements, perceptual abilities, physical abilities, skilled movements, non discursive movements
What is simple regression?
One continuous independent variable predicting (or relating to) one continuous dependent variable
What are ordinal data. Give an example
Ordinal data rank observations in terms of a quality or quantity being assessed, or in order of importance. Order of marathoners crossing the finish line; order of college rankings on academic achievement.
List the 6 purposes of measurement, testing, and evaluation
Placement, diagnosis, prediction, motivation, achievement, and program evaluation.
Define population and sample
Population: set of all participants possessing common characteristics that we are interested in. Sample: a subset of a larger population of interest that we are gathering data from
What is the purpose of motivation in measurement and evaluation? Example?
Purpose: evaluation of achievement or effort can be motivating for some people. ex. giving fitness related awards to elementary students based on their performance on the fitnessgram (i.e. achieving the healthy fitness zone)
Describe the purpose of placement, and an example
Purpose: group people of similar ability levels together so they progress at a certain rate. ex. grouping runners together by mile pace in a marathon.
What is the purpose of diagnosis? Give me an example of how we would use diagnosis in measurement and evaluation
Purpose: identify weaknesses and deficiencies in our clients, identify the presence/absence/status of a disease, and identify areas for improvement ex. drawing a blood sample for cholesterol testing, and identifying cholesterol levels as too high, and dangerous for one's health
Why do we predict in measurement and evaluation? Give me an example
Purpose: predict future events from the past and present data. Ex. predicting our risk of developing heart disease from our current lifestyle habits and family history.
Define achievement. Give an example of this purpose of measurement and evaluation
Purpose: sets of objectives to assess achievement levels ex. a series of reading quizzes and tests that build up to the final exam in a class
Why do we do program evaluations? Give an example
Purpose: to justify your treatment or program; to demonstrate successful achievement of objectives. ex. a study as part of a physical activity intervention that is designed to evaluate the effectiveness of the PA intervention for its intended community.
Give an example of qualitative methodology
Qualitative methods are mostly text based, and are a less traditional approach to research. These are often used to provide rich depth and detail, and to explain a complex or new phenomenon. We might also use these to describe, understand, and provide meaning to an experience, or build a foundation for future research efforts. Some examples are interviews, and field observations
What are ratio data? Give an example
Ratio data have an absolute zero point that actually means zero or absence of a quality. These are the most precise and useful of all measurement levels. Can compare quantities or amount of a quality. Ex. height, weight, feet or inches, VO2max (ml/kg/min)
Define reliability and validity
Reliability: consistency or repeatability of an observation Validity: the degree of truthfulness to our scores
Which are the general scales used in exercise psychology?
Self-Motivation Inventory Profile of Mood States Test of Attentional and Interpersonal Style
What are mixed methods
Some combination of quantitative and qualitative methods. It can be an even split, mostly quantitative, or mostly qualitative
What is standard deviation
Standard deviation is the positive square root of the variance. A small SD indicates that observations are clustered tighter to the mean A large SD indicates that observations are spread out about the mean
What are the three main descriptors of a correlation
Strength: how closely related are these two? (weak vs. strong) ±.80 - 1.00 Strong ±.60 - .79 Moderately strong ±.40 - .59 Moderate ±.20 - .39 Weak ±.00 - .19 Very weak (no relationship) Direction: is it direct (positive) or indirect (negative)? Shape: is it linear or curvilinear
List and define the types of reliability, both regression based and ANOVA based
Test-retest: assesses the consistency of a score across time Equivalence: assesses two equivalent forms of the same test when they are given to the same group Split halves: test is split in half, or divided by odd and even items, and scores are correlated to estimate reliability of the test Cronbach's Alpha: correlation between three or more sets of data
Example of each type of reliability
Test-retest: the ABQ given to a sport team at time 1 and time 2 Equivalence: survey form A and survey form B given to athletes on a single team Split-halves: a test is given to the class, and then scores are separated by odd and even numbers, then correlated together to give reliability Cronbach's alpha: multiple (3+) study data sets for the BREQ-3 correlated together
What does the null hypothesis always state?
That there is no relationship between two or more variables of interest
What is measurement?
The act of assessing ex. using the metabolic cart to collect expired gases and measure someone's VO2 max on a maximal exercise test
What is variance
The average deduction of individuals values with respect to the mean
What is the mean, and why do we use it? When would we not use it?
The mean is the average of the sum of all scores in our data set. We use it to describe the "average" observation or people in our data set. We also use it when our data distribution is approximately normally distributed. We might not use the mean as our typical central tendency estimate when the data are abnormal (skewed, have outliers, clusters, gaps, or have two or more modes)
What is the median and why do we use it?
The median is our middle score from our data set when they have been ordered. This is very resistant to the presence of outliers, and is used in place of the mean, usually
What is the mode, and why would we use it?
The most frequent value in the data set. We use it when we are working with nominal data, to determine which observation was the most common.
What is R squared?
The proportion of shared variance between two variables. How much of the variance in Y can be explained by, or associated with x
Which exercise motivation scale had high discriminant validity?
The self-motivation inventory; it could distinguish vey well between those who would stick with their exercise program past 6 months and those who would not
Explain why we create visual displays for conveying information
There are a few reasons: first, we are trying to convey a point or argument in an easily digestible way that does not take much cognitive processing of information on the participants part. We are also trying to convey a lot of information in a smaller space.
Why do we use standard scores
To compare different variables on different scales to each other To see how many standard deviations an observation is away from the mean
What is the purpose of the chi-square analysis?
To determine if there is an associated between two nominally scaled variables
What are the purposes of regression
To model a relationship, to predict a future event likelihood, to control for variance when analyzing data
What are the trait and state perspectives respectively?
Trait: variable comes from the person, traits are inherent and very stable unlikely to change (consistent attribute), the environment doesn't have influence over the person State: influence comes from the situation, traits don't have much influence, and once the situation changes, the behavior will too
What is multiple regresion?
Two or more continuous independent variables predicting (or relating to) one continuous dependent variable
What are type 1 and type 2 errors respectively?
Type 1: false positive, reject the null when it is true Type 2: false negative, retain the null when it is false
What are the 6 criteria for giving psychological tests
Understanding of testing principles and measurement error Ability to analyze test reliability and validity for its intended purposes Self-awareness of qualification and limitations Practice ethical use of tests Know what types of test apply where, and how to give the test, plus give feedback on the results Give information on why the testing is being done
Why do we not assess or treat any other psychological phenomenon outside of the sport realm if we are not trained to do so
We are simply not qualified to handle these situations. We have not gone through the appropriate training to be able to assist our clients in ways that they deserve for these types of issues. When in doubt of our ability to handle a situation, refer out.
When there are two modes in a data set, what does this mean for the mean and median?
When there are two or more modes, the mean and median will either be equal or close to it. But, there is also no true mean in the data set.
When would a researcher use a one-way ANOVA to analyze their data?
When there is one nominally scaled independent variable, and one continuously scaled dependent variable, and the independent variable either has more than three levels, or when there are more than two groups for the independent variable
Define work, power, muscular strength, and torguq
Work: result of physical effort Power: amount of work performed in a certain time frame Muscular strength: force generated while a muscle is contracting Torque: effectiveness of a force to produce rotation around an axis
What are some cautions we need to be considering when giving psychological tests to athletes or clients
You don't have to be a licensed psychologist, but you do have to be trained in how to use and analyze these tests, as well as knowledgeable about what the test is designed to measure, and how to interpret the results of the test
Which type of hypothesis is the below statement? "Participant's self-determined motivation for exercise will increase as their basic psychological needs satisfaction increases"
a research (alternative) hypothesis
What do we measure in the cognitive domain of human performance
knowledge, comprehension, application, analysis, synthesis, and evaluation
What do we measure in the affective domain?
psychological, emotional, and mood based activities
What characteristics do we look for in data distributions?
shape, skewness, multimodality, clustering, outliers, gaps, kurtosis