Use LEFT and RIGHT arrow keys to navigate between flashcards;
Use UP and DOWN arrow keys to flip the card;
H to show hint;
A reads text to speech;
40 Cards in this Set
- Front
- Back
What is the definition of confidence interval?
|
Range of values that has a certain degree of confidence of containing the population parameter -
We don't know the value of the parameter (eg. M mu) but we can estimate it by constructing an interval centered on an observed statistic (eg. x with line on top) |
|
Equation for confidence interval
|
CI = x with line on top +/- (zcv) x se
se = standard error of the mean (s/square root of n) |
|
what is the only difference between the equivalence of CI's and Hypothesis Test
|
CI gives us an idea of the range within which the mean could occur by chance
|
|
a form of reactivity whereby subjects improve an aspect of their behavior being experimentally measured simply in response to the fact that they are being studied,not in response to any particular experimental manipulation
|
Hawthorne effect
|
|
is obtained when moving an element from one set to another set raises the average values of both sets
diseases lead to an idea there was an improvement. changes in methods of diagnoses |
Will Rogers Phenomenon
|
|
Use a screening test to identify people with a certain disease, increase in survival due to treatment or intervention because able to diagnose early
|
Zero-time shift or lead-time bias
|
|
(A special example of selection bias) The set of selective factors that lead hospital cases and controls in a case-control study to be systematically different from one another. This occurs when the combination of exposure and disease under study increases the risk of hospital admission, thus leading to a higher exposure rate among the hospital cases than the hospital controls.
|
Berkson's Bias
|
|
Use a population approach to deal with health problem that only gives benefit to a small part of population
|
Prevention Paradox
|
|
Procedures to determine which means differ significantly after a significant f ratio has been found in ANOVA.
|
Post Hoc Multiple Comparison Tests
|
|
What is the degree of adjustment of critical values that contains a slight adjustment, less control over Type I errors, Increased power (more control over Type II errors)
|
Liberal Adjustment
|
|
What is the degree of adjustment of critical values that contains Large adjustment, greater control over Type I error, lower power (higher risk of Type II errors)
|
Conservative
|
|
This is a post Hoc test for equal n that is aslo called Honestly Significant Difference Test (HSD)
|
Tukey Method - designed to make all pairwise comparisons while maintaining alpha sub E at the pre-established alpha level, the test statistic is Q, compare the calculated value of the Q statistic with the critical value
|
|
This is the ONLY post hoc test that can be used for BOTH pairwise and nonpairwise comparisons
|
Scheffe Method (Complex comparisons)
|
|
The characteristics of a population are called ____. Represented with GREEK letters, ex: mean of population = mu
|
Parameters
(variance = o2, standard deviation = o) |
|
The characteristics of a sample are called ____. Represented with ROMAN letters, ex: mean of sample = x with line on top.
|
Estimates
(variance = s2, standard deviation = s) |
|
When we reject a true Ho - when it is falsely concluded that a significant difference exists between the groups being studied
|
Type I Error - denoted by alpha (the probability of making a Type 1 error, it is set before data is collected, also known as rejection region, level of significance, alpha level, alpha = 1 - probability value, chosen by the researcher
|
|
When we fail to reject a false Ho - when it is falsely concluded that no significant difference exists between populations, when, in fact, a true difference exists
|
Type II Error - denoted by Beta (the probability of making a type II error)
|
|
Reject Ho and Ho is true
|
Type 1 Error
|
|
Fail to reject Ho and Ho is false
|
Type II Error
|
|
If p-value is less than or equal to </= alpha then we
|
reject Ho, the smaller the p-value the more certain you can be that the observed difference in the study is not merely due to chance.
|
|
if p-value is > alpha then we
|
fail to reject Ho
|
|
There is a ____ relationship between alpha and beta, the most common way of reducing both Type 1 error and Type 2 error simultaneously is to _____ the sample size
|
inverse (decreasing alpha leads to increase in beta)
Increase the sample size |
|
Procedure used when the mean of a normal distribution if not 0 and the standard deviation is not 1 in order to use the Standard normal tablet
|
Z transformation, transformed value is known as z score, normal deviate, standard score, critical ratio
z = (raw score - mean)/standard deviation |
|
Number of observations that are free to vary after sample mean has been calculated, the number of observations less the number of restrictions place on them
|
degrees of freedom (df) = n - 1
|
|
Classifies objects into categories based on some defined characteristics. Then the number of objects in each category is counted (count # of observ with or without attribute), least precise, no logical order of the categories, categories are mutually exclusive
|
Nominal Scale
|
|
What type of measurement scale is religion?
|
nominal scale
|
|
What type of measurement scale is gender?
|
Nominal Scale
|
|
What type of measurement scale is eye color?
|
Nominal Scale
|
|
This measurement scale gives a logical order to classification. Differences in the amount of the measured characteristics are discernible and numbers are assigned according to that amount, categories are mutually exclusive
|
Ordinal Scale
|
|
What type of measurement scale is the letter-grading system (A,B,C,D,F)?
|
Ordinal Scale
|
|
Type of scale where the differences between levels of categories on any part of the scale reflect equal differences in the characteristic measured. The point 0 is just another point on the scale
|
Interval Scale (Equal Unit Scale)
|
|
What type of measurement scale is temperature?
|
Interval Scale (Equal Unit Scale)
|
|
The highest level in the hierarchy of measurement scales, most PRECISE measurement, a known/true zero reflects an absence of the characteristic measured
|
Ratio Scale - allows us to make statements about the proportional amounts of the characteristic that two objects possess.
|
|
This is an example of what type of scale, a bag of apples weighing 30 lbs does weigh twice as much as one weighing 15 lbs.
|
Ratio Scale
|
|
What is the hierarchy of measurement scales?
|
Ratio (most precise)
Interval Ordinal Nominal |
|
These variables are measured on the nominal or ordinal scales, measurement consists of unordered or ordered (ranked) discrete categories
|
Qualitative Variables
NO - nominal, ordinal |
|
These variables are measured on the interval or ratio scales
|
Quantitative Variables
|
|
Variables falling in a certain interval on which no theoretical restrictions are place. Measured along a scale
|
Continuous
|
|
These variables have no restriction place on them, there is no continuity
|
Discrete
|
|
These variables assume a value of one if a criterion is met, a value of zero otherwise
|
Dummy
|