Topic Description

Mean Simple average

Median Mid-point of values
Inter-quartile range Q3-Q1

Mode Value that occurs most often

Positive square root of the

mean of the square deviations
taken from arithmetic mean
Standard deviation (S) of the data
For frequency distribution
Direct method
Sample Std Dev
Z-score
Frequency table
Comparing data
Box plot
Scatter plot
Frequency polygon
Formula
Xbar = Sum of all values (Sigma X)/ total no of values (N)
If data has even no of values then Mean = N+1/2; if odd, then N
IQR = 75th percentile (Q3) - 25th percentile (Q1)
If a dataset has no repeat values, it has no mode, if it has more
than one repeat values, then it has more than one mode

S = Sq Root of ((X-X-bar)2/n)
S = Sq Root of (Sigma f(X-X-bar)2/Sigma f)
S = Sq Root of ((X-X-bar)2/n)
S = Sq Root of ((X-X-bar)2/n)
Z = (x-Xbar)/StdDev
Terms used meaning
X: values in data; N: no of value
N: values in data arranged in increasing order

X = individual values, Xbar = Mean, n = no of values

f = frequency
X = Total of X, Xbar = Mean, n = no of values

x = individual score, Xbar=Mean, SD=Std dev

 What is Frequency Table?

Frequency refers to the number of times an event or a value occurs.  A frequency table is a table that lists items and shows th
We represent the frequency by the English alphabet ‘f’. 
For example, Alan has to put the footballs in two boxes. He starts dropping one football after the other into two boxes named
Alan drops the balls randomly, and after dropping10 balls, he takes some rest and then again repeats the task with the remain
The given tables show the pattern of how Alan drops the footballs in two boxes.

Trial-1 Trial-2

Ball drops Ball drops

Effort in box A Effort in box A
or B or B

1 A 1 B
2 B 2 B
3 A 3 A
4 A 4 A
5 A 5 A
6 A 6 A
7 B 7 B
8 A 8 A
9 B 9 B
10 A 10 A

Plotting the frequency of ball falling in box A in case of both the trials in one table.

Frequency
Trials of balls dropping in box A
Trials - 1 8
Trials - 2 6

Such a table is known as the frequency table. 

e that lists items and shows the number of times the items occur.

e other into two boxes named A and B.

peats the task with the remaining 10 balls.  
Step 1: Calculate the mean - X-bar.
Data
46
69
32
60
52
41
X-Bar 50

Step 2: Find each score's deviation from the mean: X - X-bar

Data X-Xbar
46 -4
69 19
32 -18
60 10
52 2
41 -9
X-Bar 50

Step 3: Find square of X-Xbar for each score, and sum the squares

Data X-Xbar (X-Xbar)2

46 -4 16
69 19 361
32 -18 324
60 10 100
52 2 4
41 -9 81
X-Bar 50 886

Step 4: Find the variance. Divide the sum of the squares by (n-1) for sample and N for population. Since here it s a sample, we
 Variance = 177.2

Step 5: Find the square root of the variance. This is the Std Deviation.

Standard Deviation Square root of 177.2 13.31165

Therefore the SD is 13.31

n. Since here it s a sample, we will divide by (n-1).
Class interval Frequency (f) mid-value (x) fX (X-Xbar)2 f(X-Xbar)2
0-10 27 5 135 139.6694 3771.074
10-20 10 15 150 3.305785 33.05785
20-30 7 25 175 66.94215 468.595
30-40 5 35 175 330.5785 1652.893
40-50 4 45 180 794.2149 3176.86
50-60 2 55 110 1457.851 2915.702
Sigma 55 925 12018.18

Mean (Xbar)= Sigma f * X / Sigma F

Mean (Xbar)= 16.818181818

SD = Sqrt [(Sigma f(X-Xbar)2/Sigma f]

SD= SQRT of 218.51239669

SD= 14.782164818
 X X-Xbar X-Xbar sq
5 -19 361
10 -14 196
25 1 1
30 6 36
50 26 676
Xbar 24 1270
 X f fx x-xbar (x-xbar)2
60 2 120 -4 16
61 1 61 -3 9
62 12 744 -2 4
63 29 1827 -1 1
64 25 1600 0 0
65 12 780 1 1
66 10 660 2 4
67 4 268 3 9
68 5 340 4 16
100 6400 60

SD (S) = Sqrt of {Sigma f (x-Xbar)2/Sigma f}

Mean Xbar = Sigma fX/Sigma f

Sigma fx = 6400
Sigma f = 100
Sigma (x-xbar)2 60
Mean (Xbar) = 64

Therefore SD = Sqrt of 60
SD 7.745967
Method:

Step 1 Organise the data in increasing order

Step 2 If no of values are odd, the median is the middle number, if even then N+1/2
Step 3 mid point of the lower half of data is Q1, mid point of upper half is Q3
Step 4 IQR = Q3-Q1

Solved eg:
Z score = (x – μ) / σ

where:

x: Original value
μ: Mean of data
σ: Standard deviation of data
A box plot is a type of plot that we can use to visualize the five number summary of a dataset, which includes:. The minimum; The first quartil
This tutorial explains how to create a box plot in Google Sheets. Example: Box Plots in Google Sheets

Minimum value (Q0 or 0th percentile)

First quartile (Q1 or 25th percentile)
Median (Q2 or 50th percentile)
Third quartile (Q3 or 75th percentile)
Maximum value (Q4 or 100th percentile)

Why Do We Use Box and Whisker Plot?

Box and Whisker diagrams allow us to read the data very effectively and easily.
It summarises the data from multiple sources and displays it in a single graph.
It helps us to make an effective decision as it compares the data from different categories.

Box and Whisker Plot Solved Example

Example: Draw the box plot for the given set of data: {3, 7, 8, 5, 12, 14, 21, 13, 18}.
Solution:
STEP1, write the given data in increasing order.
3, 5, 7, 8, 12, 13, 14, 18, 21
STEP 2: Range = Maximum value – Minimum value
Range = 21 – 3 = 18
STEP 3, Median = center value of the given data
Median = 12
Now, we need to find the quartiles.
STEP 4: First quartile = Q1 = Median of data values present at the left side of Median
Q1 = Median of (3, 5, 7, 8)
Q1 = (5+7)/2 = 12/2 = 6
STEP 5: Third quartile = Q3 = Median of data values present at the right side of Median
Q3 = Median of (13, 14, 18, 21)
Q3 = (14+18)/2 = 32/2 = 16
STEP 6: Therefore, the interquartile range = Q3 – Q1 = 16 – 6 = 10
The five-number summary is given by:
Minimum, Q1, Median, Q3, Maximum
Hence, 3, 6, 12, 16, 21 is the five-number summary for the given data.
Now, we can draw the box and whisker plot, based on the five-number summary.
s:. The minimum; The first quartile; The median; The third quartile; The maximum
Scatter plots are the graphs that present the relationship between two variables in a data-set. It represents data points on a tw
The independent variable or attribute is plotted on the X-axis, while the dependent variable is plotted on the Y-axis. These plo

Scatter plot Example

Let us understand how to construct a scatter plot with the help of the below example.
Question:
Draw a scatter plot for the given data that shows the number of games played and scores obtained in each instance.
No. of gam 3 5 2 6 7 1 2 7 1
Scores 80 90 75 80 90 50 65 85 40
Solution:
X-axis or horizontal axis: Number of games
Y-axis or vertical axis: Scores
Now, the scatter graph will be:
represents data points on a two-dimensional plane
otted on the Y-axis. These plots are often called  scatter graphs or scatter diagrams.

ned in each instance.

7
100
A frequency polygon is almost identical to a histogram, which is used to compare sets of data or to display a cumulative freque

Steps to Draw Frequency Polygon

To draw frequency polygons, first we need to draw histogram and then follow the below steps:
Step 1- Choose the class interval and mark the values on the horizontal axes
Step 2- Mark the mid value of each interval on the horizontal axes.
Step 3- Mark the frequency of the class on the vertical axes.
Step 4- Corresponding to the frequency of each class interval, mark a point at the height in the middle of the class interval
Step 5- Connect these points using the line segment.
Step 6- The obtained representation is a frequency polygon.
Let us consider an example to understand this in a better way.
Example
Example 1: In a batch of 400 students, the height of students is given in the following table. Represent it through a frequenc
 to display a cumulative frequency distribution. It uses a line graph to represent quantitative data.

middle of the class interval

present it through a frequency polygon.

inferential statistics
probability, in pie chart, in normal distribution,

hypothesis testing
direction in hypothesis testing

critical value
rejection region - one taile/two tailed test
significance level
confidence level - 1-2 alpha
p - value
hyothesis error - type 1 and 2
power of test
standard error
degrees of freedom
z-test
assumptions of z test
statistical power
hypotheses/test power - 1 - beta = stats power

effect size - cohen's d

confidence intervals
sampling error due to chance
margin of error

testing difference of 2 means

central limit theorem

law of large numbers

parametric/non-parametric test
t-test
paired sample
2 sample
assumption of t test
one sample t test
independent sample t test

variance and co-variance

correlation
linear and curvilinear
form and direction
pearsons r
chi square and goodness of fit
chi square test for independence

effect size

strength of correlation
Phi = root of chi-square/n

cramer's v = root of chi-sq/n * df

cohen's w for goodness of fit

reporting results
APA style for t-test

ANOVA
one way
repeated measures
mixed anova

T-Test
only 2 variables
ANOVA
way more number of variables

anova - systematic and random variance

variables in anova
between groups and sum of squares

anova tables
F test for anova
post-hoc test

P value, Z statistic, t test

The statistical power of a binary hypothesis test is the probability that the test correctly rejects the null hypothesis (H₀) when
It is commonly denoted by 1-β, and represents the chances of a "true positive" detection conditional on the actual existence o
Statistical power ranges from 0 to 1, and as the power of a test increases, the probability β of making a type II error by wrongl
he null hypothesis (H₀) when a specific alternative hypothesis (H₁) is true.
onal on the actual existence of an effect to detect.
aking a type II error by wrongly failing to reject the null hypothesis decreases.
Z Test is used when sample size > 30; otherwise t test is used.
The sample size should be greater than 30. Otherwise, we should use the t-test.
Samples should be drawn at random from the population.
The standard deviation of the population should be known.
Samples that are drawn from the population should be independent of each other.
The data should be normally distributed, however for large sample size, it is assumed to have a normal distribution.

Z = (x – μ) / ơ   
where x = any value from the population
μ = population mean
ơ = population standard deviation

We know that: Z score = x - Xbar/S; here x = individual data; Xbar = Mean; and S = Std Dev

Z statistic = Inferential statistic for testing null-hypothesis

Z = Xbar - Mu / (sigma / sqrt n); here Xbar = sample mean, Mu = population mean; Sigma = Std Dev; n =

Process for testing:

If: calculated Z statistic value > (critical value; Z critical)
• Then: reject the null hypothesis

• If: calculated Z statistic value < (critical value; Z critical)

• Then: fail to reject the null hypothesis
a normal distribution.

n mean; Sigma = Std Dev; n = sample size

Z Test Calculation (Step by Step)
The formula for z-test statistics for a population is derived by using the following steps:
1. Firstly, calculate the population means and population standard deviation based on the observation captured in the p

Population mean,

Population standard deviation,

2. Finally, the z-test statistics are computed by deducting the population mean from the variable, and then the result is d
Z = (x – μ) / ơ

The formula for z-test statistics for a sample is derived by using the following steps:
3. Firstly, calculate the sample mean and sample standard deviation the same as above. Here, the total number of obser

Sample mean,

Sample standard deviation,

4. Finally, the z-test statistics is calculated by deducting the sample mean from the x-value, and then the result is divided
Z = (x – x_mean) / s
bservation captured in the population mean, and each observation is denoted by xi. The total number of observations in the popul

riable, and then the result is divided by the population standard deviation, as shown below.

e, the total number of observations in the sample is denoted by n such that n < N.

and then the result is divided by the sample standard deviation, as shown below.
of observations in the population is denoted by N.
Example #1
Let us assume a population of students in a school who appeared for a class test.
The mean score in the test is 75, and the standard deviation is 15. Determine the z-test score of David, who scored 90 in

Given,
The population mean, μ= 75
Population standard deviation, ơ = 15

Therefore, the z-test statistics can be calculated as,

Z = (90 – 75) / 15
Z Test Statistics will be –

Z=1
Therefore, David’s test score is one standard deviation above the mean score of the population, i.e., as per the  z-score table, 8
e of David, who scored 90 in the test.

i.e., as per the  z-score table, 84.13% of students less score than David.
Example #2
Let us take the example of 30 students selected as a part of a sample team to be surveyed to see how many pencils were
Given,
x = 5, since the 3rd student’s response, is 5
Sample size, n = 30
Sample mean,  = (3 + 2 + 5 + 6 + 4 + 7 + 4 + 3 + 3 + 8 + 3 + 1 + 3 + 6 + 5 + 2 + 4 + 3 + 6 + 4 + 5 + 2 + 2 + 4 + 4 + 2 + 8 + 3
Mean = 4.17
Now, the sample standard deviation can be calculated by using the above formula.
ơ = 1.90
Therefore, the z-test score for the 3rd student can be calculated as,
Z = (x – x ) / s
Z = (5 –17) / 1.90
Z = 0.44
Therefore, the 3rd student’s usage is 0.44 times the standard deviation above the mean usage of the sample i.e. as per z- score ta
o see how many pencils were being used in a week. Determine the z-test score for the 3 rd student of based on the given responses:

5 + 2 + 2 + 4 + 4 + 2 + 8 + 3 + 6 + 7) / 30

he sample i.e. as per z- score table, 67% students use fewer pencils than the 3 rd student.
ased on the given responses: 3, 2, 5, 6, 4, 7, 4, 3, 3, 8, 3, 1, 3, 6, 5, 2, 4, 3, 6, 4, 5, 2, 2, 4, 4, 2, 8, 3, 6, 7.
Difference Between Z-Test and T-Test of Hypothesis Testing ([Link])

Differences Between Z-Test and T-Test

Z Test is the statistical hypothesis which is used in order to determine that whether the two samples means calculated are different
Z-tests and t-tests are the two statistical methods that involve data analysis, which has applications in science, business, and man

Uses
#1 – Z-Test
Z-test Formula, as mentioned earlier, are the statistical calculations that can be used to compare population averages to a samp
The z-test will tell you how far, in standard deviations terms, a data point is from the average of a data set.
A z-test will compare a sample to a defined population that is typically used for dealing with problems relating to large

#2 – T-Test
T-tests are also calculations that can be used to test a hypothesis, but they are very useful when we need to determine if there i
In other words, a t-test asks whether the comparison between the averages of 2 groups is unlikely to have occurred due
Usually, t-tests are more appropriate when dealing with problems with a limited sample size (i.e., n < 30).

Z-Test vs. T-Test Infographics

Here we provide you with the top 5 differences between the z-test vs. t-test you must know.
 You are free to use this image on your website, templates etc, Please provide us with an attribution link

Key Differences
One of the essential conditions for conducting a t-test is that population standard deviation or the variance is unknown. Conver
The t-test, as mentioned earlier, is based on student’s t-distribution. On the contrary, the z-test depends upon the assumption
Z-test is used as given in the above table when the sample size is large, which is n > 30, and the t-test is appropriate when the si

Z-Test vs. T-Test Comparative Table

Basis Z Test
Basic Definitio Z-test is a kind of hypothesis test which ascertains if the averages of the 2 datasets are different from each other when standard deviation or variance is given.
Population VarThe Population variance or standard deviation is known here.
Sample Size The Sample size is large.
All data points are independent.
Key Assumptio
Normal Distribution for Z, with an average zero and variance = 1.
Based upon (a Based on Normal distribution.

Conclusion
By and to the larger extent, both these tests are almost similar, but the comparison comes only to their conditions for their appli
Well, there are also different tests like the f test, two-tailed vs. single-tailed, etc., statisticians must be careful while applying them
 means calculated are different in case the standard deviation is available and sample is large whereas the T test is used in order to determine
s in science, business, and many other disciplines. The t-test can be referred to as a univariate hypothesis test based on t-statistic, wherein th

population averages to a sample’s.

ge of a data set.
h problems relating to large samples (i.e., n > 30). Mostly, they are very useful when the standard deviation is known.

we need to determine if there is a statistically significant comparison between the 2 independent sample groups.
nlikely to have occurred due to random chance.
e (i.e., n < 30).
e variance is unknown. Conversely, the population variance formula, as stated above, should be assumed to be known or be known in the
epends upon the assumption that the distribution of sample means will be normal. Both the normal distribution and student’s t-distribution
test is appropriate when the size of the sample is not big, which is small, i.e., that n < 30.

T-Test
n standard deviation or variance is given. The t-test can be referred to as a kind of parametric test that is applied to an identity, how the averages of 2 sets of data differ from each other
The Population variance or standard deviation is unknown here.
Here the Sample Size is small.
All data points are not dependent.
Sample values are to be recorded and taken accurately.
Based on Student-t distribution.

their conditions for their application, meaning that the t-test is more appropriate and applicable when the size of the sample is not more th
be careful while applying them after analyzing the situation and then deciding which one to use. Below is a sample chart for what we discuss
t is used in order to determine a how averages of different data sets differs from each other in case standard deviation or the variance is not kno
based on t-statistic, wherein the mean, i.e., the average is known, and population variance, i.e., the standard deviation, is approximated from

ation is known.
be known or be known in the case of a z-test.
on and student’s t-distribution appears the same, as both are bell-shaped and symmetrical. However, they differ in one of the cases that in a

s of 2 sets of data differ from each other when the standard deviation or variance is not given.

e of the sample is not more than thirty units. However, if it is greater than thirty units, one should use a z-test. Similarly, there are also other
mple chart for what we discussed above.
ation or the variance is not known.
eviation, is approximated from the sample. On the other hand, Z-test, also a univariate test which is based on a  standard normal distributio
fer in one of the cases that in at-distribution, there is lesser space in the center and more in their tails.

Similarly, there are also other conditions, which will make it clear that which test is to be performed in a situation.
a  standard normal distribution.
Effect size
Cohen's D

How large, important or meaningful the statistical significance is

no of sample size >50
d = XBar − μ / σ
Xbar = Sample mean
Mu = population mean
Sigma = Std Dev

d = 0.20, small effect

d = 0.5, moderate effect
d = 0.8, large effect