Week 8 Flashcards

1
Q

What is epidemiology?

A

A study aimed at studying determinants of disease, injury or dysfunction in populations

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

Epidemiology is another way of saying ____

A

Epidemiology is another way of saying risk

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

Risk in PT can be expressed in terms of _____

A

• Experiencing an adverse outcome
• Patients not improving with treatment
• Requiring more invasive or expensive subsequent
interventions in spite of treatment

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

Epidemiology generally uses observational designs with ___ variables

A

Epidemiology generally uses observational designs with dichotomous variables

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

What studies are intended to study risk factors?

A

Case-Control & Cohort Studies

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

Case-Control & Cohort Studies looks at the ____ between disease & exposure

A

Case-Control & Cohort Studies looks at the association (“cause”) between disease &
exposure

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

The IV and DV in case-control & cohort studies are what kind of variables?

A

Dichotomous

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

In case-control & cohort studies, there is ___ strength in thinking something is causal of the other

A

In case-control & cohort studies, there is less strength in thinking something is causal of the other

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

How are subjects in a cohort study selected?

A

Subjects selected based on

exposure or not

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

Is a cohort study usually prospective or retrospective?

A

Usually prospective, but

can be prospective or retrospective

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

Does a cohort study work for rare conditions?

A

Doesn’t work well for very

rare conditions

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

What does a cohort study examine?

A

Examine if there is a different

incidence of disease

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
13
Q

How are subjects in a case control study selected?

A

Subjects selected based on
whether or not they have
disorder

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

Where should the controls of a case control be selected from?

A

Controls should be selected

from same population as Cases

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

What does a case-control study examine?

A

Examine if exposure is different between cases and control

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

What condition does a case control work especially well for?

A

Works especially well for very

rare conditions

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

What are the primary ways to quantify risk?

A
  • Relative Risk (RR)

* Odds Ratios (OR)

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

What do the primary ways to quantify risk actually quantify?

A

Both quantify strength of association between “exposure” and “disease”

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

In what study is RR used and in what study is OR used?

A
  • RR in Cohort studies

* OR in Case-control studies

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

What does it mean when an RR or OR = 1 ?

A
  • = “null value”

* No association between an exposure and a disease

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

What does it mean when an RR or OR > 1?

A
  • A positive association between an exposure and a disease

* The exposure is considered to be harmful

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

What does it mean when an RR or OR < 1?

A
  • A negative association between an exposure and a disease

* The exposure is protective

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

RR is the ratio of ___ compared to ____

A

Incidence of disease among
exposed individuals compared to Incidence of disease among
unexposed individuals

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

Since OR is selected based on whether they have disease or not, so can’t determine rate of ___

A

Since OR is selected based on whether they have disease or not, so can’t determine rate of “incidence”

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

OR is the ratio of ___ compared to ____

A

Odds of exposure among cases (with disease) compared to Odds of exposure among controls (w/o disease)

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

The computation of OR is kinda like ___

A

The computation of OR is kinda like kappa

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
27
Q

____ uses relationships (correlation) as a basis for prediction

A

Regression uses relationships (correlation) as a basis for prediction

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

What are the characteristics of a linear regression?

A
X and Y are correlated
• X = independent variable (= predictor variable)
• Y = dependent (or criterion) variable
• We use X to predict Y
    • The value of Y depends 
       on X
    • (Thats why Y is called the 
        dependent variable)
How well did you know this?
1
Not at all
2
3
4
5
Perfectly
29
Q

What is the error from line/ residual in a regression line?

A

The distance between each data point and the line of best fit

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
30
Q

Residuals are squared to eliminate ___ and penalize for ___

A

Residuals are squared to eliminate sign and penalize for worse errors

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

What is the line of best fit?

A

Line with least squared errors

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
32
Q

Is regression a parametric or non parametric statistic?

A

Parametric

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
33
Q

What are the assumptions of a linear regression analysis?

A
  1. Linear relationship = approximation of true line in population
  2. For every X there is a normal distribution of Y
    • Sample data include random samplings from these distributions on Y
  3. Homogeneity of variance
How well did you know this?
1
Not at all
2
3
4
5
Perfectly
34
Q

What is a way to test the assumptions of a linear regression?

A

Analysis of residuals by:

Plot Residuals on Y-axis, vs predicted values on x-axis

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
35
Q

What assumption of linear regression does the analysis of residuals test the most?

A

Homogeneity of variance

36
Q

What are you looking for in the analysis of residuals to test linear regression assumptions (assumptions are met)?

A

Looking for the residual’s distance between the predictive value and the actual value be symmetric and consistent throughout

37
Q

What does the analysis f residuals graph look like when the assumptions of linear regression are not met?

A
  • The graph starts to get wider the further it goes(data is further away from the line, the higher you go)
  • Data is not symmetric
38
Q

What happens if the linear regressions assumptions are not met?

A

Use a non linear regression

39
Q

What are the thing that helps a researcher determine whether to retain or discard a data with an outlier?

A

• Due to peculiar circumstances?
• Can discard if error identified
• Generally not justified on statistical grounds
alone

40
Q

What are the peculiar circumstances that have to be taken into consideration when determining whether to retain or discard a data?

A
  • Measurement error
  • Recording error
  • Equipment malfunction
  • Miscalculation
  • Aberrant subject (should have been excluded)
41
Q

What are the things that looks a the accuracy of prediction of the regression equation?

A

• Correlation coefficient (R)
Coefficient of determination (R2)
• ANOVA of Regression

42
Q

What are the characteristics of a correlation coefficient as it relates to the accuracy of prediction?

A
  • Rough indicator of goodness of fit for regression line

* Same as correlation coefficient (r)

43
Q

What does the coefficient of determination represent?

A

Proportion of variance in Y scores that can be explained by X scores

44
Q

What does the ANOVA of regression test?

A

Tests hypothesis that predictive relationship occurred by chance (Ho: b = 0)

45
Q

What does it mean when b=0 in an ANOVA of regression?

A

If b (slope) = 0, line is horizontal = no relationship

46
Q

What happens when p< than alpha in an ANOVA of regression?

A

If p < than alpha, reject the null and conclude the predictive relationship is
significant

47
Q

How many predictors are in a simple linear regression model and how many are in a multiple linear regression model?

A

There is only 1 predictor in a simple model and there are multiple predictors in a multiple linear regression model

48
Q

What are the assumptions of a multiple linear regression analysis?

A
  1. Linear relationship = approximation of true line in population
  2. For every X there is a normal distribution of Y
    • Sample data include random samplings from these distributions on Y
  3. Homogeneity of variance
  4. DV = continuous measure
49
Q

Coefficient of determination is the square of ____

A

Coefficient of determination is the square of correlation coefficient

50
Q

What is an adjusted R squared and what do you get punished for?

A

Chance corrected R2, get punished for having more predictor variables

51
Q

What is the goal of a linear regression?

A

The more you can predict with fewer variables, the better

52
Q

What is a regression coefficient?

A
  • The value/slope in the linear equation

* The rate of change in Y for each unit change of X

53
Q

What is a standardized beta weight helpful for?

A

Helpful to know relative contribution of each predictor

variable

54
Q

Which will always be higher or the same, out of an R square or an adjusted R square?

A

The R square will always be higher than or equal to the adjusted R square

55
Q

What is multicolinearity?

A

When the Xs in the model are substantially correlated with each other

56
Q

What does multicolinearity create a problem with?

A

Creates problems with interpretations of b weights

57
Q

What is the risk of the force entry of all possible predictors in a multiple regression method?

A
  • Risk of multicolinearity (correlation between predictors)
  • Risk of retaining non-contributing predictors
  • Risk of more predictors than justified by sample size
58
Q

How is the criteria in a stepwise procedure set?

A

Criteria set to retain or reject predictors

59
Q

Which predictor is entered first in a stepwise procedure?

A

Predictor with highest partial correlation entered first

60
Q

What does a stepwise procedure result in?

A

Should result in model with greatest parsimony and

least multicolinearity

61
Q

What is a parsimony model?

A

A model that is the most predictive, with the least amount of variables

62
Q

What is a simple correlation?

A

The overlap between 2 variables

63
Q

What is a partial correlation?

A

The unique correlation between 2 variables

64
Q

What is a forward stepwise regression method?

A

A method that starts with no predictors, then adds them, starting with the strongest

65
Q

What is a backward stepwise regression method?

A

A method that starts with all predictors, then removes them, starting with the weakest

66
Q

What is a stepwise stepwise regression method?

A

A method that starts with no predictors, then add,

but can also remove

67
Q

What is the level of measurement for predictors/ IV in a stepwise multiple linear regression model?

A
  • Most predictors are continuous scales
  • Can also use dichotomous or ordinal scale predictors
  • But not multicategory nominal (e.g. race)
68
Q

A large number of predictors is needed in a stepwise multiple linear regression hence it requires ___

A

A large number of predictors in a regression requires a very large sample size

69
Q

What is the rule of thumb for the predictors of a stepwise multiple linear regression model?

A

At least 10-15 subjects per predictor in model

70
Q

What happens if there are too many or too few predictors in a stepwise multiple linear regression model?

A

Become susceptible to “model overfit” (chance associations, i.e. type 1 error).

71
Q

What is a logistic regression?

A

When you are trying to predict a dichotomous variable

72
Q

What is the DV level of measurement of a logistic regression?

A

Dichotomous

73
Q

What is the predictor/ IV level of measurement of a logistic regression?

A

Continuous, ordinal, or dichotomous

74
Q

What are the pros MANOVA?

A

• MANOVA gets around multiplicity problem (familywise alpha:
increased Type I error risk)
• MANOVA can be more powerful if DVs related

75
Q

What are the cons MANOVA?

A

• “Combo DV” is not directly interpretable
• If statistically significant, then must follow up with post-hoc
ANOVAs

76
Q

What is a factor analysis?

A

Method of simplifying & organizing large sets of variable into fewer abstract components

77
Q

What is a path analysis?

A

Visual modeling of both direct & indirect relationships

78
Q

Path analysis is an extension of ____

A

Path analysis is an extension of multiple regression

79
Q

Compared to a multiple regression, a path analysis is more __ and ____

A

Compared to a multiple regression, a path analysis is more flexible and comprehensive

80
Q

What can a path analysis analyze?

A

Can analyze both direct and indirect relationships between 1 or more exogenous variables (IVs) and 1 or more endogenous variables (DVs)

81
Q

What is a hierarchical linear modeling also known as?

A
  • Multilevel linear modeling

* Linear mixed modeling

82
Q

A hierarchical linear modeling comes from what type of analysis?

A

The type of analysis where you have some variables nested within other variables (students nested in a classroom when studying schools)

83
Q

A hierarchical linear modeling, has far fewer __ and is highly ___

A

A hierarchical linear modeling, has far fewer assumption and
highly flexible

84
Q

What is the Number Needed to Treat (NNT)?

A

How many patients you have to provide treatment to in order to prevent one bad outcome

85
Q

What is Control Event Rate (CER)?

A

Percent of patients in control group with bad outcome

86
Q

What is Experimental Event Rate (EER)?

A

Percent of patients in experimental group with bad outcome

87
Q

What is the equation for RR?

A

EER/CER