# ISS (Statistical Services) Statistics Paper IV: Questions 71 - 75 of 92

Access detailed explanations (illustrated with images and videos) to **92** questions. Access all new questions we will add tracking exam-pattern and syllabus changes. *Unlimited Access for Unlimited Time*! View Sample Explanation or View Features.

Rs. 350.00 or

How to register?

## Question number: 71

» Design and Analysis of Experiments » Randomized Block and Latin Square Design

Appeared in Year: 2010

### Describe in Detail

Describe under which situations a Latin square design can be preferred to completely randomised design and randomised block design, What are the merits and demerits of LSD?

### Explanation

(i) **Latin square design compared to completely Randomized design:**

In CRD, we allocate the treatments at random to the experimental units, without the grouping of the experimental field. In some cases, this design suffers because of not having more information like other advanced designs. Since in CRD randomisation is not restricted in any direction

… (363 more words) …

## Question number: 72

» Design and Analysis of Experiments » Randomized Block and Latin Square Design

Appeared in Year: 2012

### Describe in Detail

Discuss the layout of a Latin square design. Give its example. Write its model (one observation per experimental unit). Give its ANOVA table. Write null hypothesis. Give comments on acceptance and rejection of null hypothesis**.**

### Explanation

**Layout of Latin Square designs:**

When the experimental area is divided into rows and columns, and the treatments are allocated such a way that each treatments occurs only once in a row and once in a column, the design is called as Latin square design.

In LSD the number of rows and columns are equal and thus the arrangement will form a square. i. e. in

… (657 more words) …

## Question number: 73

» Design and Analysis of Experiments » Basic Principle of Experimental Design

Appeared in Year: 2010

### Describe in Detail

Show that for BIBD:

(i) bk = rv

(ii) r (k- 1) = (υ - l),

Further show that for resolvable BIBD:

b≥v + r-1 Name the design when equality holds good,

### Explanation

(i) In a BIBD **υ** treatments will be repeated **r** timesand hence total total number of plots in the design is **υr.** Further, there will be **b** blocks each of zize **k**, there will be **bk** plots all together.

hence **bk = rv**

**(ii)** let us take be as the 1 x 1 matrix whose elements are unity.

(a) we know that

=

… (695 more words) …

## Question number: 74

» Design and Analysis of Experiments » Basic Principle of Experimental Design

Appeared in Year: 2013

### Describe in Detail

Discuss the concept of Balanced incomplete block design (BIBD). How does this design differ from randomized block design?

For a BIBD with parameters ** ,** b, r, kand ** ,** show that b **≥ **

### Explanation

An arrangement of the υ treatments in b blocks of k plots each (k < υ) is known as BIBD if

(i) Each treatment occurs once and only once in r blocks and

(ii) Each pair of treatments occurs together in λ blocks.

The variance of the estimate of any treatment mean which has been replicated *r* times is where is the error variance. Thus in BIBD a

… (649 more words) …

## Question number: 75

» Design and Analysis of Experiments » Randomized Block and Latin Square Design

Appeared in Year: 2014

### Describe in Detail

Obtain necessary conditions for a symmetric BIBD with an even number of treatments to exist.

### Explanation

Necessary conditions for a symmetric BIBD with an even number of treatments to exist:

The determinant of is given by

=

Since

=

Using the fact

When BIBD is sy

… (145 more words) …