0% found this document useful (0 votes)
8 views21 pages

Basic Statistical Concepts-3

Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PDF, TXT or read online on Scribd
0% found this document useful (0 votes)
8 views21 pages

Basic Statistical Concepts-3

Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PDF, TXT or read online on Scribd
You are on page 1/ 21

INNOVATION

Research Bangladesh

Basic Statistical Concepts-3


MAHBUB TAREK
Founder & Chief Scientist
AGENDA

Tabular presentation Graphical


of data presentation of data Research Question Hypothesis testing
Tabular presentation of data
Nominal Variables

Nominal variables: Frequency

Nominal variables: Relative frequency


Tabular presentation of data(Cont..)
Ordinal Variables
Ordinal variables: Frequency Ordinal Variables: relative frequency

Ordinal Variables: Cumulative relative frequency

For example, if the cumulative relative


frequency at the “satisfied” level is 70%,
this means that 70% of the individuals are
either satisfied or very satisfied.
Tabular presentation of data(Cont..)
Cross- tabulation: two-way table

Sometimes we are interested in presenting two categorical variables in the same table, which we
call the two-way table (as we have two variables).
Tabular presentation of data(Cont..)
Cross- tabulation: Three-way table

Three categorical variables can be presented in the same table such as sex, disease status, and
smoking status as follows
Graphical presentation of data
It is important to use the appropriate graph for each data type that clearly delivers the meaning.

Nominal Variables
Nominal variables: Pie chart
Nominal variables: Bar graph
Graphical presentation of data(Cont..)
Ordinal Variables

Ordinal variables: Pie chart

Ordinal variables: Bar graph


Graphical presentation of data(Cont..)
Two Categorical Variables
Graphical presentation of data(Cont..)
Numerical Variables

Numerical variables: Histogram Numerical variables: Box plot


Graphical presentation of data(Cont..)
Numerical Variables

Two numerical variables: Scatter plot


If we have two variables that are numerical (or ordinal), the relationship between them can be
illustrated using a scatter diagram.
It plots one variable against the other in a two-way diagram.
One variable is represented on the horizontal axis and the other is plotted on the vertical axis with
each dot representing one case.
Research Question

In any research project, it is not enough for the researcher to have an idea, we need to formulate it into
a research question.
A research question should be
A question
Specific (time/place/subjects/condition)
Answerable
Novel
Relevant to medical knowledge
Examples of research questions
▪ What is the prevalence of diabetes mellitus in Egypt?
▪ Does lowering blood pressure reduce the risk of coronary heart disease in diabetic patients?
▪ Is the prognosis following stroke dependent on age at the time of the event?
▪ Is drug A better than drug B in lowering blood pressure?
▪ Is there a difference between males and females regarding response to drug X?
Hypothesis testing
If we have a research question and we want to reach a conclusion about it, we do what is called
hypothesis testing. (The key message is one variable to another variable relationship finding)
Steps for hypothesis testing
1. Define the null and alternative hypotheses.

2. Choose the level of significance.

3. Pick and compute the test statistic.

4. Compute the p-value

5. Check whether to reject the null hypothesis by comparing the p-value to the level of significance.

6. Draw a conclusion from the test.


Hypothesis testing
Null and Alternative hypotheses
If we have a research question and we want to reach a conclusion about it, we do what is called
hypothesis testing. (The key message is one variable to another variable relationship finding)
Hypothesis testing
Null and Alternative hypotheses
Hypothesis testing
Before hypothesis tasting we need to know some essential term

Type 1 and Type 2 errors

In the real world (population): Smoking rate in males = smoking rate in females
Hypothesis testing
Before hypothesis tasting we need to know some essential term

Level of significance

The level of significance (α) is the maximum allowed probability of committing a Type I error. The
smaller the value of α, the lower the risk of committing a type 1 error. Hence, we choose a level of
significance depending on the consequence of committing a Type I error. Common values for α are
0.05 and 0.01 indicating 5% and 1%, respectively.

Confidence Interval & Level


A Confidence Interval (CI) is a range of values we are fairly sure the true value lies in. Upper & lower value called confidence level

So, the confidence interval depends on both the variability in the data and the sample size.
Hypothesis testing
Before hypothesis tasting we need to know some essential term

Standard error

The standard error tells us how accurate the mean of any


sample is likely to be compared to the true population mean.
Hypothesis testing
Before hypothesis tasting we need to know some essential term

P-value(Probability value)

The P value is defined as the probability under the assumption of no effect or no difference (null
hypothesis), of obtaining a result equal to or more extreme than what was actually observed.
It determines null hypothesis is accepted or rejected.
P-value is a probability and therefore lies between 0 and 1
0.05 or 5% is commonly used as a cut-off (significance level)
Hypothesis testing
One tailed & Two tailed test

Two-tailed tests One tailed tests

You might also like