PH week 7 quiz

Univariate analysis

Describes ONE variable using simple statistics like frequencies, proportions, and means

When is univariate analysis used?

When researchers want to describe the data or study population simply

Bivariable analysis

Examines the relationship between TWO variables using tests like odds ratios or rate ratios

When is bivariable analysis used?

When comparing two or more groups/populations

Multivariable analysis

Examines relationships among THREE OR MORE variables

Variable

Any single item of information in a dataset

Continuous variable

A numeric variable that can take ANY value within a range

Example of a continuous variable

Weight

Discrete variable

A numeric variable that cannot take every value

Example of a discrete variable

Number of children

Ordinal variable

A variable with a meaningful order/ranking

Examples of ordinal variables

Always to never, best to worst

Nominal (categorical) variable

A variable with NO inherent order

Examples of nominal variables

Hair color, yes/no, country of birth

Mean

The average; add all values and divide by total number of values

Median

The middle value after ordering numbers least to greatest

Mode

The most frequently occurring value

Range

Maximum value minus minimum value

Quartiles

Values that divide data into four equal parts

Interquartile range (IQR)

The middle 50% of values in a dataset

Histogram

Displays distribution of numeric data using bars

Histogram axes

X-axis = values, Y-axis = frequency/count

Boxplot

Displays median, IQR, and outliers of a numeric variable

Bar chart

Displays categorical data using bars proportional to values

Pie chart

Displays percentages of categories within one whole population

Normal distribution

A bell-shaped curve with one peak in the middle

Skewness

A measure of asymmetry in a distribution

Kurtosis

Describes how peaked or flat a distribution is

Variance

Average of squared differences from the mean

Standard deviation (SD)

The square root of variance; measures spread of data

Small SD means

Responses are close to the mean

Large SD means

Responses are spread out widely from the mean

In a normal distribution, what percent falls within 1 SD?

68%

In a normal distribution, what percent falls within 2 SDs?

95%

In a normal distribution, what percent falls within 3 SDs?

More than 99%

Confidence interval (CI)

A range of plausible values for a population parameter

What happens to a CI when sample size increases?

The confidence interval becomes narrower

95% confidence interval

We are reasonably confident the true population value falls in that range

For roughly normal continuous variables, what should be reported?

Mean (SD)

For skewed continuous variables/outliers, what should be reported?

Median (IQR)

For categorical variables, what should be reported?

n (%) in each category

Table 1 in research papers

Summary of participant characteristics before the main analysis

What does Table 1 help readers understand?

Who participated and whether groups are similar at baseline

Fabrication

Making up fake data

Falsification

Misrepresenting results

Plagiarism

Using others’ work without proper credit

Mean vs median vs mode

Mean = average, Median = middle, Mode = most common

Range formula

Maximum minus minimum

IQR meaning

Middle 50% of the data

SD meaning

Measures spread/variability of data

Histogram vs bar chart

Histogram = numeric data, Bar chart = categorical data

Boxplot shows

Median, IQR, and outliers

68-95-99 rule

68% within 1 SD, 95% within 2 SDs, 99%+ within 3 SDs