KIN 4310: Statistics
108 Cards in this Set
| Front | Back |
|---|---|
|
if null is true then is the skeptic right or wrong?
|
right
|
|
in a left-tailed test the test statistic must be greater than the critical value in order to reject the null hypothesis
|
false
|
|
If the p-value is greater than the level of significance, we fail to reject the null hypothesis.
|
true
|
|
type I error
|
Null is true but we reject it anyways
|
|
type II error
|
research hypothesis is correct but we fail to reject the null.
|
|
What is a p-value?
|
probability of getting a value more extreme than the test statistic by CHANCE, assuming that the null hypothesis is actually true.
|
|
If the p-value is less than the level of significance,
|
reject null hypothesis
|
|
The probability of making a Type II error when the null hypothesis is false is:
|
β if sample size goes up β comes down
|
|
what do you need about the population be fore you can perform a one sample z-test?
|
mean and SD which can be found within census data
|
|
Type I and II errors
|
|
|
Know which test is appropriate for which statistic
|
|
|
T-test distribution?
|
bell curve is dictated by degrees of freedom; the smaller the sample the narrower the bell curve become. (symetrical)
|
|
does z-test have degrees of freedom?
|
No
|
|
F
|
Msb/Msw
positively skewed
|
|
which of the 5 research hypothesis can never have 2 tails?
|
ANOVA (F)
|
|
One sample z-test
|
Determine if one group of data is from a given population
H₁: X(bar)≠µ
H₀: X(bar)=µ
|
|
Independent t-Test
|
Two groups of data
H₁: X(bar)1 ≠ X(bar)2
H₀: µ₁=µ₂
|
|
Dependent t-Test
|
Two groups of data (paired)
H₁: X(bar)1 ≠ X(bar)2
H₀: µ₁=µ₂
|
|
Correlation (r) research hypothesis
|
Paired data for n subjects
H1: r≠0
H0: p=0
|
|
A hypothesis is:
|
An educated guess
|
|
Statistics (plural)
|
collection of methods for planning experiments, obtaining data, and then organizing, summarizing, presenting, analyzing, interpreting, and drawing conclusions based on the data
|
|
Population
|
the complete collection of all elements (scores, people, measurements, and so on) to be studied. The collection is complete in the sense that it includes all subjects to be studied. (content specific)
|
|
census
|
collection of data from every member of the ppopulation
|
|
sample
|
a sub-collection of elements drawn from a population
|
|
Statistic (singular)
|
a numerical measurement describing some characteristic of a sample
(Standard deviation, mean, Z- score, etc)
|
|
parameter
|
a numerical measurement describing some characteristic of a population.
|
|
descriptive statistics
|
summarize or describe characteristics of a known set of data.
|
|
inferential statistics
|
uses sample data to make inferences (or conclusions and predictions) about a population.
(correlational or experimental designs)
|
|
central tendency
|
a value at the center or middle of a data set. (mean, median, and mode)
|
|
when is mode used?
|
when data is categorical
|
|
when is median used
|
when data contains extreme values that would distort an average
|
|
when is mean used
|
anytime if mode and median can't be used first.
|
|
3 measures of variability?
|
Range, Standard Deviation, Variance (these examine the amount of spread or dispersion in a group of scores)
|
|
Systematic sampling
|
selects a start point and then select every Nth element in the population
|
|
stratified sampling
|
subdivide the population into at least 2 different subgroups, then draw a sample from each subgroup
|
|
Cluster sampling
|
divide the population into sections (or clusters); randomly select some of those clusters; choose all members from selected clusters
|
|
correlation Studies
|
describes something in relation to something else; observations are not manipulated, merely related to each other
|
|
Cross Sectional Study
|
Data are observed, measured, and collected at one point in time.
|
|
Retrospective Study
|
Data are collected from the past by going back in time.
|
|
Prospective (or Longitudinal) Study
|
Data are collected in the future from groups (called cohorts) sharing common factors.
|
|
A group of UH researchers randomly selected five elementary schools in HISD and measured the BMI of every student and educator in those schools. This is an example of what type of sample?
|
cluster (the population is the teachers and students)
|
|
Frequency Distribution (or Frequency Table)
|
Lists data values (either individually or by groups of intervals), along with their corresponding frequencies or counts (illustrated by a histogram)
|
|
Median is the most appropriate measure of central tendency when the data is
|
positively or negatively skewed
|
|
The ____ ____ is the one being manipulated. The ____ _____ is not manipulated.
|
Independent variable
dependent variable
|
|
determine the strength of the following (r) data:
a) r= -0.93
b) r= 0.56
c) r= 0
d) r= 1.00
|
(a) Strong (b) moderate (c) none (d) linear
|
|
interval scale of measurement?
|
variables refer to quantities of units on a continuum, distance between variables is meaningful. (temperature in F or C, intelligence quotient IQ) (median and frequency distribution can be calculated)
|
|
nominal (scale of measurement)
|
mutually exclusive, un-ordered catergories. (gender, political affiliation, movie genres) (frequency distribution can be calculated)
**Paired with another variable, you can use it to calculate a linear correlation coefficient**
|
|
ordinal (scale of measurement)
|
characteristics that can be put in order, but there is no consistent difference between adjacent scores (median freq. distr. can be calculated)
|
|
ratio (scale of measurement)
|
variables refer to quantities of units on a continuum; has an absolute zero (annual salary, distance traveled in the 12-minute run test, body fat %) (all Freq. distr. , mediian, mean, ratio)
|
|
Name 4 types of reliability
|
test retest, interrator, internal consistency, parallel
|
|
concerned about the reliability of the field sobriety test used by Houston police. She orders two officers to independently apply the test to a group of drivers suspected of intoxication. What is she trying to establish?
|
interrater reliability (Correlation of scores measured by two different observers or raters)
|
|
An attorney is concerned that the three components of the field sobriety test do not assess the same thing. What is he calling into question?
|
internal consistency reliability
|
|
In 2002, a group of college students complained that the version of the GRE Test that they wrote was more difficult than the previous three versions of the test. What are they calling into question?
|
parallel forms reliability (Correlation of scores between two different versions of a test such as IQ test or exam 3A vs. exam 3B)
|
|
Test-Retest Reliability
|
Correlation of scores on a test given at two separate times. Affected by: Change, Carry-over effects
|
|
The Physical Fitness Test recognizes students for their level of physical fitness in 5 events: curl-ups, shuttle run, endurance run, push-ups, and V-sit.
Is a child who scores well in one event likely to score well in the other four events? This is a question of:
|
CONTENT VALIDITY (Property of a test such that the test items sample the universe of items for which the test is designed)
|
|
Every time I do a 1.5-Mile run test, my performance varies a lot.
|
test-retest reliability
|
|
The number of calories determined by a 24-hour food recall depends on who does the interview
|
Interrater reliability
|
|
One version of the MCAT is much harder than the others
|
parallel forms reliability
|
|
Criterion Validity
|
Any variable one wants to "predict" by measuring another (SATs predict College GPA, Extraversion predicts sales totals)
|
|
Construct Validity
|
abstract concept made up of interrelated variables (E.g Honesty, intelligence, depression)
|
|
Validity
|
The extent to which a measurement scale does what it says it does
|
|
What is aerobic fitness?
|
- The ability of the heart, lungs and blood vessels to supply oxygen to the working muscles
- The ability of the muscles to use the available oxygen
|
|
How do we measure aerobic fitness?
|
Exercise testing:
* Oxygen consumption
* Power output
* Field tests
- 12-minute run/walk
- Generalized 1-mile run/walk
- Shuttle run
Non-exercise approximations
|
|
Storage Fat
|
body fat in excess of essential fat; stored in adipose tissue
|
|
(ANOVA) Assumptions:
|
1) Each group is comprised of a randomly selected sample.
2) Scores in each group are normally distributed
3) The variances of each group population are homogeneous.
|
|
F-score
|
1) distribution is not symmetric; it is skewed positively.
2) The values can be 0 or positive; they cannot be negative.
3) distribution changes shape with respect to degrees of freedom
|
|
T/F: An excessively large F test statistic is
|
TRUE
|
|
Variance WITHIN groups
|
How spread out is the data in each group relative to its group mean?
|
|
what happens when there is a significant effect of treatment?
|
Then (MSb) will be large relative to (MSw) and F will be large
|
|
(dfw) degrees of freedom within groups
|
= number of data points - number of groups
= N - k
|
|
Variance BETWEEN groups
|
How spread out are the group means?
|
|
(dfb)degrees of freedom between groups
|
= number of groups - 1
= k - 1
|
|
what happens when there is no effect of treatment?
|
Then (MSb) will be relatively small and F will be small.
|
|
What happens when F>Fcrit?
|
Then there is an effect of treatment, and we can reject the null hypothesis
|
|
Definition of Health:
|
1) Absence of: Physical pain, Physical disability, Conditions likely to cause death
2) Emotional well-being
3) Satisfactory social functioning
|
|
Body Composition
|
**The different components that make up the human body: Fat, Muscle, Bone
*Important in assessing health status and disease risk
|
|
Percent body fat (%BF):
|
Weight of fat in the body relative to the person's total weight
|
|
Essential fat:
|
Minimal amount of body fat needed for normal physiological functions; constitutes about 3-5% of total weight in men and 8-12% in women
|
|
Lean body mass
|
Body weight without body fat
|
|
Direct techniques involve looking inside the body and measuring the different tissues by volume (or area)
|
*Dual energy X-ray absorptiometry (DXA)
*Magnetic resonance imaging (MRI)
*Computed tomography (CT)
|
|
DXA
|
**2nd "gold standard" technique
**Uses high powered magnets and imaging software
**Measures total and regional adiposity
**Safe; no problems with radiation exposure, etc.
**Procedure can be time consuming and is very expensive
|
|
CT
|
- Measures regional adiposity by imaging multiple cross-sectional slices
- Measures fat layers within body cavity, limbs or organs
- Sequential images are segmented into adipose and non-adipose tissue pixel values measured in Houndsfield units (HU)
- Uses higher-dose X-ray energy
- R…
|
|
Indirect techniques involve measurements outside or on the surface of the body to estimate what is inside:
|
* Hydrostatic weighing
* Air displacement
* Skinfold thickness
* BMI, WC, WHR
* Girth measurements
* Bioelectrical impedance
|
|
Hydrostatic Weighing
|
- A person's "land" weight is compared with underwater weight
- Fat is more buoyant than lean tissue
- Not feasible to test large number of people
|
|
Air Displacement
|
- Bod Pod-Computerized pressure sensors determine the amount of air displaced by the person
- Body volume is calculated by subtracting the air volume with the person inside the chamber from the volume of the empty chamber (air in the lungs is taken into consideration) Body density and pe…
|
|
Skinfold Thickness
|
** Based on the principle that approximately half of the body's fat tissue is directly beneath skin.
** All measurements should be taken on the right side of the body
|
|
Waist Circumference
|
Predicts disease risk according to region of adiposity (waist versus other areas)
|
|
Waist-to-Hip Ratio
|
Predicts disease risk according to distribution of adiposity ("apple" vs. "pear" shape)
|
|
Girth Measurements
|
Requires a standard measuring tape
|
|
Bioelectrical Impedance
|
** Sensors are applied to the skin and a weak electrical current is run through the body to estimate body fat, lean body mass, and body water
** Based on the principle that fat tissue is a less-efficient conductor of an electrical current
** Hydration status can influence results
|
|
How to measure aerobic fitness?
|
* Exercise testing:Oxygen consumption, Power output, Field tests
* Non-exercise approximations: which Uses age, measures of body composition and physical activity to estimate VO2max
|
|
Maximum VO2 consumption
(Most accurate)
|
High risk; Expensive equipment and trained personnel; Subjects need to be monitored by physician.
|
|
Sub-maximal
VO2 consumption
(Safe, less strenuous)
|
Less accurate; Expensive equipment and trained personnel required.
|
|
Maximum treadmill time
(Highly accurate)
|
High risk. Subjects need to be monitored by physician.
|
|
Timed/Distance Run
(Feasible for mass testing)
|
Not appropriate for elderly or unhealthy subjects
|
|
Nonexercise estimations
(Easy to administer)
|
Least accurate; not appropriate for highly fit subjects
|
|
24 Hour Recall
|
- Interviewer helps subject remember all foods consumed and assists in determination of portion sizes.
- Interviewer asks what subject first ate and drank upon waking THAT day, and works forward to time of interview.
- Interviewer then begins at point exactly 24 hours ago and works forw…
|
|
Food Record/Diary
|
Subject records, at time of consumption, the types and amounts of food and beverages consumed for a period of time ranging from 1-7 days.
-- Weighted: food is weighed then recorded
--Un-weighted: portions are estimated with household measures (cups, teaspoons etc)
|
|
Food Frequency Questionnaires
|
1) Assesses energy and/or nutrient intake by determining frequency of consumption of a limited number of foods known to be major sources of the dietary component under investigation
2) Lists approximately 100 food or food groups
3) May ask for indication of portion size
4) Portion numb…
|
|
Diet History
|
Assesses subject's usual dietary intake over an extended period of time
|
|
Duplicate Food Collection
|
Subjects collect identical portions of all food and beverages consumed over a specified period of time. Duplicate portions are then chemically analyzed for nutrient content
|
|
Physical activity
|
"Any bodily movement produced by the skeletal muscles that results in energy expenditure."
|
|
Exercise
|
" A sub-category of physical activity, that is planned structured purposeful and repetitive."
|
|
Characteristics in Measuring Physical Activity
|
Frequency
Intensity
Duration
|
|
METs:
|
multiples of the metabolic equivalent of sitting quietly for one hour
|
|
Accelerometers:
|
Measure accelerations of the human body
(Actigraph (or CSA) - most commonly used)
|
|
Methods to Assess PA Subjective Measures:
|
Physical activity logs (PALS)
24 hour recall
7 day recall
Previous month recall
Previous year recall
Questionnaires
(All are self-administered or interviewer administered, either in-person or on telephone)
|
|
Methods to Assess PA Objective Measures:
|
Accelerometers
Heart rate monitoring
Pedometers
Direct observation
GPS systems
|
KIN 4310: Statistics