Statistics III Flashcards

1
Q

Descriptive Statistics

A

Describe how many observations were recorded and how frequently each score or category of observations occurred in the data

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

inferential statistics

A

makes predictions about a population based on a sample of data taken from the population in question

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

2 types of statistics

A

Descriptive

Inferential

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

Inferences are based on _____

A

probability

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

In statistics, what is considered ‘significant’ p values?

A

p

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

what are the Two types of Inferential Statistics?

A

Comparative statistics

Regression statistics

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

What are the two types of Hypothesis testing?

A

null hypothesis Ho

alternative hypothesis Ha

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

What is Ho?

A

negative statement or no difference b/w two means

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

What is Ha?

A

alternative hypothesis or there is a difference bw/ two means

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

4 types of variables?

A

Nominal/categorical
ordinal/ranked
interval/numeric
ratio

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

What is nominal/categorical data?

A

Data that have names or arbitrary numeric assignments, unordered categories
Yes, No. Race/ethnicity, gender

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

What is ordinal data?

A

Data that can be arranged in ascending or descending order

Highest level of education, survey questions (disagree>neutral>agree) income categories

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

What is interval data?

A

Data with no true zero

Temperature, percent change

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

What is ratio data?

A

Numbers on a scale with a meaningful zero.

Height, weight, cholesterol levels

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

Two types of variables in hypothesis testing

A

Independent vs. dependent

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

What is Independent variable?

A

Variable that is systematically manipulated by investigator to show the effect on the outcome of experiment
changing diet to show body weight outcome

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

What is the dependent variable?

A

Response that is measured as a result of the independent variable
Variable likely to be though of as a different by the researcher

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

________ is based on the probability of a chance

A

Significance

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

What are the basic properties of Probabilities?

A

Property 1: probability of an event occurring is always b/w 0 and 1(0%-100%)
Property 2: the probability of an event that cannot occur is 0 (i.e pigs flying)
Property 3: The probability of an event that must occur is 1 (ie. sun rising in the east)

20
Q

p

A

reject the null hypothesis

21
Q

p>α

A

fail to reject the null hypothesis

22
Q

Test decisions with ___________

A

confidence intervals

23
Q

The probability that a particular value lies within this interval is called a _________

A

level of confidence

24
Q

Confidence intervals are used with 2 types of tests

A

Odds ratio OR

Rate Ratios RR

25
Q

CI that does not overlap 1 is equivalent of a p value of ____

A

p<0.05

26
Q

If CI overlaps 1, that is equivalent to a p value of ____

A

p>0.05

27
Q

2 categories of a test

A

parametric

non-parametric tests

28
Q

what is a parametric test?

A

assume that the variables have a particular distribution (normal distribution) to assess the p-value of the outcome
typically used for ratio and internal variables

29
Q

What is a non-parametric test?

A

typically used for ranked variables, categorical variables or when the distribution is not normal (skewness)

30
Q

What is a T-test?

A

useful statistical test that determines whether there is a difference b/w two means is significantly greater or lesser than would be expected based on the populations.
Can only assess one variable at at time!!!!

31
Q

What is a Chi Square test?

A

measures the differences bw what is observed and what is expected according to an assumed hypothesis

32
Q

T- Test analyses _____

A

continuous data

33
Q

Chi-Square analyses _____

A

categorical data

34
Q

What is correlation?

A

allows us to measure the relationship b/w two or more variables

35
Q

Two types of correlation ests

A

pearson (parametric)

spearman (non-parametric)

36
Q

r=_______

A

correlation coefficient

37
Q

If the r is close to -1, then there is a _________

A

strong negative correlation

38
Q

If the r is close to 0, then _________

A

there is no linear relationship

39
Q

If the r is close to +1, then there

A

is a strong positive correlation

40
Q

What is regression?

A

Test to see if we can predict an unknown variable’s value based on the value of a known variable or variables

41
Q

If outcome is is continuous, then there is one independent variable with 2 group, use _____

A

t-test

42
Q

If outcome is is continuous, then there is one independent variable with 3+ groups, use ____

A

ANOVA

43
Q

If the outcome is continuous and there is more than one independent variable use ____ if all independent variables are categorical

A

ANOVA

44
Q

If the outcome is continuous and there is more than one independent variable use ____ or multiple linear regression, if only some independent variables are continuous

A

ANCOVA (analysis of covariance)

45
Q

One way ANOVA

A

used to compare the mean values of continuous variables among independent groups

46
Q

Two way ANOVA

A

way of studying the effects of two factors separately and/or together