CH 14 - Exam 2 Flashcards

1
Q

Can research studies still be published or peer reviewed if they use the wrong type of statistical test or measure to analyze its study?

A

no

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
2
Q

What are the 5 levels of measurement

A
  • nominal
  • ordinal
  • interval
  • ratio
  • continuous variable
How well did you know this?
1
Not at all
2
3
4
5
Perfectly
3
Q

A ___ measure is the lowest level of measurement and involves using ___ to designate attributes

A
  • nominal

- numbers

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
4
Q

Can the numeric indicators used in a nominal study be used mathematically

A

no

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
5
Q

___ measurements rank people based on an attribute, where the number relates to the rating of the attribute

A

ordinal

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
6
Q

___ measurements rank people on attributes with a number that clearly specifies a distance b/t the two

A

interval

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
7
Q

An IQ is an example of what type of level of measurement

A

interval

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
8
Q

___ measurements are the highest level, and the numbers included are able to have a meaningful zero

A

ratio

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
9
Q

Ratio measures have 2 values that can be accurately described by their ___

A

ratio

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
10
Q

___ ___ are variables with interval and ratio measurements

A

continuous variables

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
11
Q

Descriptive statistics are used to ___ and ___ data

A

synthesize and describe

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
12
Q

Parameters are ___ values such as ___ and ___

A
  • calculates
  • percents
  • averages
How well did you know this?
1
Not at all
2
3
4
5
Perfectly
13
Q

A ___ is a descriptive index from a sample

A

statistic

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
14
Q

A frequency distribution takes a list of values and organizes it ___ to ___ and includes a ___.

A
  • lowest to highest

- count

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
15
Q

Symmetric distributions are ones where if the graph is folded in 1/2 it would be ____.

A

superimposed

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
16
Q

A skewed distribution the majority of the data ___ to ___ ___

A

peaks to one side

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
17
Q

A normal distribution has a ___ ___ which has a ___ peak than other types of distribution

A

bell-shaped curve

lower

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
18
Q

___ attributes tend to have a bell shaped curve

Ex:

A
  • human

- height and intelligence

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
19
Q

___ ___ includes methods to determine a central value for a set of numbers

A

central tendency

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
20
Q

When measures of central tendencies are the same for two different sets of distribution it is know as ___

A

variability

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
21
Q

___ ___ is a variability index calculated based on every value is a distribution

A

standard deviation

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
22
Q

Standard deviation is the ___ amount of deviation of values from the ___

A
  • average

- mean

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
23
Q

The lower the standard of deviation the more ___ the distribution

A
  • homologous
How well did you know this?
1
Not at all
2
3
4
5
Perfectly
24
Q

For normal distribution what percentage of values will be within the first standard of deviation?
The 2nd?

A
  • 68%

- 95%

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
25
Q

If a frequency distribution is based on 3 variables a ___ ___ can be used to depict the data

A

crosstabs crosstable

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
26
Q

cross tabulations use __ variables ___ statistics, can can be used with ___ or ___ data

A
  • 2 variables
  • descriptive
  • nominal
  • ordinal
How well did you know this?
1
Not at all
2
3
4
5
Perfectly
27
Q

Correlations are methods to describe ____ between 2 ___

A
  • relationship

- variables

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
28
Q

The ___ ___ describes the intensity and direction of the relationship between two variables

A

correlation coefficient

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
29
Q

What is the range for correlation coefficients?

What do the numbers indicate?

A
  • range : -1 - +1
  • 0 - +1 = a positive relationship
  • -1 - 0 = a negative relationship
How well did you know this?
1
Not at all
2
3
4
5
Perfectly
30
Q

The most widely used correlation stat is ___ __ (the product moment correlation coefficient)

A

Pearson’s r

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
31
Q

Spearman’s ___ is a correlation coefficient calculated for values on an ___ scale

A
  • rho

- ordinal

32
Q

A ___ ___ displays correlation coefficients in tables

A

correlation matrix

33
Q

What is absolute risk

A

the proportion of people who actually experienced an undesirable outcome in each group involved in the study.

34
Q

What is absolute risk reduction?

A

when you subtract the value of absolute risk of the control group from the absolute risk value of the test group

35
Q

What is the odds ratio?

A

the odds of an undesirable event : divide the number of people who did not experience AE by those who did –> this value can be used to compare the 2 groups

36
Q

What is the number needed to treat

A

an estimate of how many people need to receive an intervention to prevent one undesirable outcome (1 divided by the absolute risk)

37
Q

___ statistics use the law of probability to test research hypotheses with data

A

inferential

38
Q

A ___ sample size helps reduce the risk of outlying data

A

large

39
Q

___ ___ of the ___ = standard deviation of the mean of a sample

A

standard error of the mean (SEM)

40
Q
A \_\_\_ (high/low) SEM is associated with more error associated with the sample selected 
Therefore a \_\_\_ SEM reflects a more appropriate sample size
A
  • higher

- lower

41
Q

parameter estimation is used to estimate a ___ ___ such as the __

A
  • population parameter

- mean

42
Q

A ___ ___ relates to the probability of the parameter estimation being correct

A

confidence interval

43
Q

What is the goal for a confidence interval (%)

A

95-99%

44
Q

Hypothesis testing uses ___ ___ to determine if the hypothesis is supported to rejected

A

objective criteria

45
Q

A null hypothesis is when there is ___ ___ between the ___ and ___ ___

A
  • no relationship

- independent and dependent variable

46
Q

Rejecting a null hypothesis that is true is a ___ ___ ___

A

type one error

47
Q

When the null hypothesis is assumed to be true when in fact the independent variable did have an effect is a __ __ __

A

type 2 error

48
Q

level of significance is indicated by the __ or a ___

A

alpha or designation

49
Q

The level of significance is calculated by :

A

subtracting the confidence level from 1

50
Q

To reduce the risk of a type to error you should

A

increase the sample size

51
Q

A ___ __ is calculated to determine the chance of a type 2 error

A

power analysis

52
Q

What is the goal for a power analysis?

What does this indicate?

A
  • goal = 0.8

- indicates there is a 20% chance of a type 2 error

53
Q

Since it is impossible to eliminate the possibility of errors studies aim to be ___ ___

A

statically significant

54
Q
  • If a study is statically significant it mean that the …
  • Statically significant values should fall w/I __ standard deviation(s) of the mean
  • Confidence intervals of ___ or greater are considered statically significant
A
  • results did not likely occur by chance
  • 2
  • 95%
55
Q

What test should be used when testing the difference b/t 2 group means

A

t-test

56
Q

what value determines if the results are significant

A

p value (<0.05)

57
Q

___ t tests are appropriate for two different groups of people

A

independent

58
Q

___ t tests are used when one group is tested at two different points in time

A

paired

59
Q

What test is used to test mean group differences of 3 or more groups

A

Analysis Of Variance ANOVA - calculates a F value which we use to find a p value

60
Q

What test focuses on the difference in proportion

A

chi-squared - still use p value

61
Q

___ ___ measures several independent variables, where the independent variables are called ___

A
  • multiple regression

- predictors

62
Q

a multiple correlation coefficient AKA __, it has a range of ___ to ___

A

R

0.0 - 1.0

63
Q

R squared gives a ___ of how influential the ___ were

A high R squared indicates

A
  • percentage, predictors

- high R squared = the predictors were more likely to account for the variation

64
Q

What is Analysis Of Covariance (ANCOVA)
When is it good
What does it attempt to do?

A
  • a combination of ANOVA and multiple regression
  • good when no control through randomization
  • control covariates of cofounding variables
65
Q

___ ___ analyzes the relationship b/t multiple independent variables

A

logistic reasoning

66
Q

logistic reasoning will yield ___ ___ for each ___ variable as well as ___ ___

A
  • odds ration
  • independent
  • confidence interval
67
Q

What are 3 reliability measurements

A
  • test retest reliability
  • interrater reliability
  • internal consistency reliability
68
Q

____ ___ ___ is used for test retest reliability and ranges from 0-1 where 1 indicates __ reliability

A
  • interclass correlation coefficient

- strong

69
Q

___ ___ is used in interrupter reliability and determine dichotomous classifications

A

Cohen kappa

70
Q

__ __ would be helpful to determine if two individuals would rate something similarly

A

choens kappa

71
Q

Internal consistency reliability uses __ or __ alpha

A
  • coefficient

- Cronbach’s

72
Q

___ ___ is used to measure how often components of a multicomponent toll measure the same attribute

A

coefficient alpha or Cronbach’s alpha

73
Q

___ ____ determine if the content of the items adequately reflect the construct of interest
Should be __ or higher

A
  • content validity

- 0.90

74
Q

___ ___ concerns the extent to which scores on a measure are consistent with a gold standard criterion
This has 2 types :

A
  • criterion validity

- sensitive and specificity

75
Q

Sensitivity is the ability …

A

of a measure to correctly screen or diagnosis a condition

76
Q

Specificity is the…

A

measures ability to correctly identify non-cases or screen out those without the condition

77
Q

___ ___ concerns the extent to which a measure is truly measure the target construct

A

construct validity –> uses various procedures