Scribd
Upload
3 views

Inferential Statistics

The document provides an overview of inferential statistics, focusing on statistical inference methods such as estimation of parameters and hypothesis testing. It explains concepts like confidence intervals, types of hypotheses, significance levels, and statistical tests like chi-square and t-tests. Additionally, it covers regression and correlation techniques to analyze relationships between variables.

Uploaded by

ayeshaalam220103
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
3 views

Inferential Statistics

The document provides an overview of inferential statistics, focusing on statistical inference methods such as estimation of parameters and hypothesis testing. It explains concepts like confidence intervals, types of hypotheses, significance levels, and statistical tests like chi-square and t-tests. Additionally, it covers regression and correlation techniques to analyze relationships between variables.

Uploaded by

ayeshaalam220103
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/ 26

Inferential

Statistics
Muhammad Afzal
Senior Research Officer
Islamabad Medical and Dental college
Statistical Inference:

Drawing the conclusions from Quantitative or


Qualitative information using the methods of
statistics to describe and arrange the data
and test suitable hypothesis.
Two ways to make inference

1. Estimation of parameters

2. Hypothesis Testing
Estimation of parameters

1. Point Estimation ( X or p)

2. Intervals Estimation (confidence


interval)
Population Point estimate Interval estimate
I am 95%
Mean confident that μ
Mean, μ, is X = 50 is between
unknown 40 & 60

Sample
CONFIDENCE INTERVAL :
Interval or range of values,
which most likely contain the
true population value.
Calculation of Confidence Interval
C.I = point estimate ± margin of error

Margin of error = confidence level x SE


Confidence level may be 95% (1.96) or 99% (2.58)
SE = SD/ n

So, C.I = μ= X + Z×
SE
Hypothesis testing

A statistical method that uses sample


data to evaluate a hypothesis about
a population parameter.
What is a Hypothesis?

An assumption about the population


parameter e.g.
I assume the mean SBP of students in the class
is 120 mmHg.
OR
The mean SBP of male and female is different.
Types of Hypotheses

• Null Hypothesis : Ho:


one that reflects no difference, no
association, or no effect
• Alternate Hypothesis : Ha:
that reflects the investigator’s belief.
1. Formulation of Hypothesis
This will always
with the sign of
equality
Or
no difference

Ho : µ 1 = µ 2
Ha : µ 1 ≠ µ 2
>
<
Example :
We want to test that is there any difference in
weights of male and female patients ?

H0: μ (male) = μ (female)


i) H1: μ (male) ≠ μ (female)
• ii) H1: μ (male) > μ (female)
iii) H1: μ (male) < μ (female)
2. Level of significance (alpha)
• The probability that a test leads to the rejection of H0
when it is actually true is called the level of the
significance of the test.

• Tests are constructed such that this probability is


small that is usually 0.05 or 0.01. (5% & 1% level of
significance)
Test of Significance for Two independent
samples
Design Nature of Statistical Statistic
variable Test derived

Qualitative Chi square χ2


(nominal)

Two independent
Groups Quantitative Student ‘t’ test t
(continuous)
Chi-square test:
• The chi-square analysis is used to test the null
hypothesis (H0), that states that there is no
significant difference between expected and
observed data. Investigators either accept or reject
H0, after comparing the value of chi-square to a
probability distribution.
• In general, a chi-square analysis evaluates whether
or not variables within a contingency table are
independent, or that there is no association between
them.
Students t-test :
• The t-test is probably the most commonly used
Statistical Data Analysis procedure for hypothesis
testing.
• There are several kinds of t-tests, but the most
common is the "two-sample t-test" or the
"independent samples t-test".
• The t-test assesses whether the means of two groups
are statistically different from each other. This
analysis is appropriate when we want to compare
the means of two groups.
P-value
P-value represents the probability of making a
Type 1 error (α error), which is rejecting the
null hypothesis when it is true.
OR
The p-value represents the probability of
falsely rejecting the null hypothesis.
The smaller the p-value, the lower is the
probability that you would be making a
mistake by rejecting the null hypothesis.

Typically we compare p-value with 0.05


Conclusion:

• If P-value > 0.05 Accept Ho

• If P-value < 0.05 Reject Ho


REGRESSION & CORRELATION

■ Regression & correlation are two


statistical techniques used for defining the
linear relationship/association between
two quantitative variables
e.g. height & weight or
salt intake & BP etc.
Regression
• Regression is a technique that can be used to
investigate the effect of one or more
predictor variables (independent variables)
on an outcome variable (dependent variable)
Regression Analysis
• The outcome variable is called dependent
variable and the risk factors are called
independent variables
• e.g. association of total cholesterol with body
mass index (BMI) and age.
• In regression analysis dependent variable is
denoted by y and independent variables by x.
Types of linear Regression
• Simple Linear Regression: when there is single
continuous dependent variable and a single
independent variable, the analysis is called
simple linear regression analysis.
• Multiple linear regression analysis: is used to
assess the association between two or more
independent variables and a single dependent
continuous variable.
CORRELATION
• CORRELATION:
is a statistic that measures the
strength of association
Or
relationship between two variables x
& y.
CORRELATION COEFFICIENT (r)
■ Correlation Coefficient ( r ) simply
expresses the strength & direction
of relationship between two
variables.

■ Values of “r” vary from –1 to +1


CORRELATION Coefficient)

• Strength of relationship is indicated by


size of coefficient & direction by sign.

• A plus sign shows positive correlation


between two variables I.e. x & y, &
minus sign negative correlation.

You might also like