Brainscape's Knowledge GenomeTM

Browse over 1 million classes created by top students, professors, publishers, and experts.


See full index

Community medicine > Biostatistics > Flashcards

Biostatistics Flashcards

1
Q

What are the assumptions made when using parametric tests?

A
  • The observations must be independent
  • The dependent variable should be continuous (interval or ratio)
  • The independent variable is categorical with two or more levels
  • The observations must be drawn from normally distributed populations
  • The populations must have the same variance
  • The groups should be randomly drawn from normally distributed and independent populations with no overlap
How well did you know this?
1
Not at all
2
3
4
5
Perfectly
2
Q

What are the advantages of using parametric tests?

A
  • They are more powerful and flexible than nonparametric tests
  • They allow the researcher to study the effect of many independent variables on the dependent variable as well as the study of their interaction
How well did you know this?
1
Not at all
2
3
4
5
Perfectly
3
Q

What are the main types of data used in nonparametric tests?

A

Nominal and ordinal data

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

What are the advantages of using nonparametric tests?

A
  • They require no assumptions about the population probability distributions
  • They can be used with smaller samples
  • They are good for data with outliers
How well did you know this?
1
Not at all
2
3
4
5
Perfectly
5
Q

What conditions must a statistical test satisfy to be considered nonparametric?

A

At least one of the following:

  • It can be used with nominal data
  • It can be used with ordinal data
  • It can be used with interval or ratio data without making assumptions about the population probability distribution (i.e. in small samples)
How well did you know this?
1
Not at all
2
3
4
5
Perfectly
6
Q

What are the types of statistical tests?

A
  • Tests for differences between groups with independent samples
  • Tests for differences between groups with dependent samples
  • Tests for relationships between variables
How well did you know this?
1
Not at all
2
3
4
5
Perfectly
7
Q

What is the test used for a nominal variable with 1 sample?

A

χ2 test

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

What is the test used for a nominal variable with 2 independent samples?

A

χ2 test

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

What is the test used for a nominal variable with 2 dependent samples?

A

McNermar’s χ2 test

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

What is the test used for a categorical variable with more than 2 independent samples?

A

χ2 test

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

What is the test used for a categorical variable with more than 2 dependent samples?

A

Cochran’s Q test

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

What is the test used for an ordinal variable with 2 independent samples?

A

Mann–Whitney U test

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

What is the test used for an ordinal variable with 2 dependent samples?

A

Wilcoxin matched-pair signed-rank test

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

What is the test used for an ordinal variable with more than 2 independent samples?

A

Kruskal–Wallis H test

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

What is the test used for an ordinal variable with more than 2 dependent samples?

A

Friedman’s ANOVA

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

What is the test used to assess correlation in ordinal variables?

A

Spearman’s rank correlation coefficient (ρ)

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

What is the parametric test used for 1 sample?

A

z-test or t-test

18
Q

What is the parametric test used for 2 independent samples?

A

Unpaired t-test (Student t-test)

19
Q

What is the parametric test used for 2 dependent samples?

A

Paired/matched t-test

20
Q

What is the parametric test used for more than 2 independent samples?

A

One-way ANOVA between groups

21
Q

What is the parametric test used for more than 2 dependent samples?

A

One-way ANOVA within groups (repeated measure)

22
Q

What is the parametric test used to assess correlation?

A

Pearson’s product–moment correlation coefficient (r)

23
Q

Which parametric test can be used for all multisample parametric tests?

A

Factorial (two-way) ANOVA

24
Q

What are the conditions that must be met to use a χ2 test?

A
  • The sample must be random
  • The data must be in raw frequencies (not grouped frequencies or percentages)
  • The sample size must be ≥20
  • Observations must be independent
  • The expected frequency for each cell of the contigency table must be >5
25
Q

How can the normality of data be evaluated?

A

Shapiro–Wilk test:

  • If the significance value is ≥0.05, the data are normally distributed
  • If the significance value is <0.05, the data are not normally distributed
26
Q

What is the formula for the χ2 test?

A

χ2 = ∑[(O – E)2 / E]

27
Q

What is the formula for the number of degrees of freedom for the χ2 test?

A

df = (n – 1)×(m – 1), where n is the number of rows of the contigency table and m is the number of columns

28
Q

What is the χ2 goodness of fit test used for?

A

Determining whether the observed frequency distribution differs significantly from a hypothesized frequency distribution

29
Q

How is the expected frequency calculated in a χ2 test?

A

E = (row total × column total) / grand total

30
Q

How is a χ2 test carried out in SPSS?

A
  • Analyze > Descriptive Statistics > Crosstabs…
  • Select the variables for the rows and columns then click Statistics…
  • Select Chi-square then click Continue
  • The p-value is given in the column “Asymp. Sig. (2-sided)”
31
Q

What parameters/statistics are used in the t-test?

A

Means (µ/x̄)

32
Q

Who invented the t-test?

A

William Gosset (under the pseudonym “Student,” hence the name Student t-test)

33
Q

What are the conditions and assumptions made when using an unpaired 2-sample t-test?

A
  • The dependent variable must be continuous (interval or ratio)
  • The groups should be randomly drawn from normally distributed and independent populations
  • The independent variable must be nominal with two levels
  • The distribution of the two independent variables is normal
  • The two variables have equal variance
34
Q

What is the formula for the unpaired 2-sample t-test?

A

t = (x̄1 – x̄2)/SE, where SE is the standard error

35
Q

What is the formula for the standard error in a 2-sample t-test?

A

SE = √[(s12/n1 + (s22/n2)]

36
Q

What is the formula for the number of degrees of freedom for the unpaired 2-sample t-test?

A

df = n1 + n2 – 2

37
Q

How is an unpaired 2-sample t-test carried out in SPSS?

A
  • Analyze > Compare Means > Independent-Samples T Test…
  • Select the test variable
  • Click Define Groups…, set the values to 1 and 2, then click Continue and then OK
  • The p-value is given in the column “Sig. (2-tailed)” for the row “Equal variances assumed”
38
Q

What is the formula for the paired-sample t-test?

A

t = d̄ / (sd/√n), where

d is the difference in means for each pair
n is the number of pairs

39
Q

How can the power of a t-test be increased?

A
  • Increase the difference between the means
  • Reduce the standard error by
    • reducing the variance, or
    • increasing n
  • Increase α from 0.01 to 0.05
40
Q

How is an paired-sample t-test carried out in SPSS?

A
  • Analyze > Paired-Samples T Test…
  • Select the variables then click OK
  • The p-value is given in the column “Sig. (2-tailed)”
41
Q

What is the formula for the number of degrees of freedom for a paired-sample t-test?

A

df = n – 1, where n is the number of pairs

Community medicine (7 decks)

Brainscape helps you reach your goals faster, through stronger study habits.
© 2024 Bold Learning Solutions. Terms and Conditions