Lecture 36 - Biostats - Intro to Probability

# Lecture 36 - Biostats - Intro to Probability - Characterize...

This preview shows pages 1–2. Sign up to view the full content.

Characterize scales of measurement (nominal, ordinal, continuous) Interpret frequency distribution in describing a set of biological measurements Define mean, median, mode, percentile, variance, standard deviation, range, and inter-quartile range and describe how they are used Distinguish between the standard deviation and the standard error and explain the appropriate use of each Contrast the features of a normal distribution with those of a skewed distribution Distinguish when to use nonparametric vs. parametric statistics Explain what is meant by probability - Scales of measurement o Nominal, ordinal, interval, ratio scales o Interval and ratio also called numerical or continuous o Possible properties of a scale: Identity: each number has an inherent meaning Magnitude: inherent order from small to large Equal intervals: differences between units on the scale is the same, i.e. 1 to 2 is same as 101 to 102 Absolute/true zero: Zero represents absence - Nominal Scales o A nominal scale is used where arbitrary numbers or designations can be given to categories of the data o Examples are gender, ethnic groups, disease state (i.e. hypertension, yes or no) o No ordering is implied, i.e. 1=female, 2=male is same as 1=male, 2=female; male is not > female o No quantitative information, qualitative in nature o Identity property is only one that applies - Ordinal Scales o A scale that incorporates inherent order in the data o Properties include magnitude and identity, but NOT equal distances or true zero o Examples include: Cancer stages, i.e. lung cancer, stage I is confined to the lung, stages II and III are confined to the chest, and IV is metastasis Apgar scores, scale 0-10 Ranked preferences, i.e. soda or coffee Levels of agreement, i.e. Likert scale - Interval Scale o A scale in which a given distance along the scale means the same regardless of where on the scale o Properties include identity, magnitude, and equal distance, but NOT true zero point o Differences make sense, but ratios do not Examples include: Temperature, Celsius or Farenheit Dates Test scores, i.e. SAT or GRE scores - Ratio Scale o Sa m e a s a n interval scale, but zero has m e a ning, n a m ely the abs enc e of a characteristic o So properties include: identity, m a gnitude, equ al o It m akes s ens e to s ay 2 m is twice a s large as 1 m o Examples include: Height, weight, length Money Biomarkers, i.e. c-reactive protein, cholesterol, Sum m arizing Data - What is a frequ ency distribution? o

This preview has intentionally blurred sections. Sign up to view the full version.

View Full Document
This is the end of the preview. Sign up to access the rest of the document.

{[ snackBarMessage ]}

### Page1 / 4

Lecture 36 - Biostats - Intro to Probability - Characterize...

This preview shows document pages 1 - 2. Sign up to view the full document.

View Full Document
Ask a homework question - tutors are online