Scribd
Upload
7 views

Chapter 3- Basic biostatistics

Uploaded by

ghadeer othman
Copyright
© © All Rights Reserved
Available Formats
Download as PDF, TXT or read online on Scribd
7 views

Chapter 3- Basic biostatistics

Uploaded by

ghadeer othman
Copyright
© © All Rights Reserved
Available Formats
Download as PDF, TXT or read online on Scribd
You are on page 1/ 12

Nutritional

epidemiology
(1110460)
Dr. Ghadeer Othman
Department of clinical nutrition and dietetics
Chapter 3: Basic biostatistics:
concepts and tools
Summarizing data

• Data exist as either numerical or categorical variables.


1. Numerical variables include counts, such as the number of children of a
specific age, and measurements, such as height and weight.
2. Categorical variables are the result of classifying. For instance, individuals
can be classified into categories according to their blood group; A, B, O, or
AB.
• Ordinal data – which express ranks – are a type of categorical data.
Summarizing data

• Tables and graphs can be used for summarizing data.

• Summary numbers include medians, means, ranges, standard


deviations, standard errors and variances.
Tables and graphs
• Tables and graphs are important means of summarizing and
displaying data, but they are seldom prepared with sufficient care.

• Their purpose is to display data in a way that can be quickly and easily
understood.

• Each table or graph should contain enough information so that it can


be interpreted without reference to the text.
Summary numbers: Means, medians and
mode
• One set of summary numbers are those that measure central
tendency, that is, they attempt to characterize the center of a sample
of measurements.

❑The mean
• Most prominent, and often the most appropriate, is the sample
average or mean, which for a sample with n values for a variable such
as x = body weight
i
Summary numbers: Means, medians and
mode
❑The median

• The median is defined as the middle after all the measurements


have been put in order according to their values.

• The median is especially useful when a few values are much larger
than others.
Summary numbers: Means, medians and
mode
❑The mode

• Another important measure is the mode, which is the value of the


measurement in the sample that occurs most frequently.
Summary numbers: Variances, standard
deviations and standard errors

• Measures of variability are another group of summary numbers. The


three most useful measures of variability are the:
1. variance
2. standard deviation
3. standard error.
Summary numbers: Variances, standard
deviations and standard errors
• Each of these is related to how unlike each other the individuals are in a
sample of measurements.
• These measures of variability can be calculated on;
1. the differences between members for all possible pairs of measurements
in the sample or
2. the difference between each observation in the sample and the sample
mean, that is : the squared deviation from the mean.

• The standard error of the mean reflects how unlike each other all possible
means of samples of size n might be if each sample were randomly
selected from the same population as the initial sample.
Basic concepts of statistical inference:
Using samples to understand populations
• Random samples
• The process of selecting a sample from a population is essential to
statistical inference.

• The first step is to select a random sample, whereby each member of


the population has an equal chance of being selected for the sample.

• If the mean of all these sample means, that is the mean of the means,
is the same as the population mean, then the sample mean is an
unbiased estimate of the population mean.
Basic concepts of statistical inference:
Confidence intervals
• Confidence intervals are one of the most useful tools in epidemiology.

• In general, a confidence interval uses these concepts to create


reasonable bounds for the population mean, based on information
from a sample.

• They are easy to prepare and relatively easy to understand.

You might also like