• No results found

DFT of real signals

of determining the extent to which test performance is

related to some other valued measure of performance.

Construct Validation:

It is defined as the process of

determining the extent to which test performance can be

interpreted in terms of one or more psychological constructs.

A2 The three main concerns of validity are:

i.

determining the extent to which performance on a test

represents level of knowledge of the subject matter content

ii.

iii.

which the test was designed to measure – content validity of the test.

determining the extent to which performance on a test

represents the amount of what was being measured possessed by the examinee – construct validity of the test.

determining the extent to which performance of a test

represents an examinee’s probable performance on some

other related test or task-criterion (concurrent and predictive) validity of a test.

A3 The factors that affect the value of criterion validity index are:

i.

ii.

iii.

the validity of the criterion variable itself (validity of the instrument used in obtaining criterion scores)

the time interval between the administration of the two test (predictor and criterion measures)

the selection of criterion group based on performance on the predictor test scores which results in a homogeneous group that is no more a group which inference based on test validity is to be made.

4.0 CONCLUSION

In this unit you learned about validity and types of validity.

Furthermore you learned about content validation, criterion validation and construct validation. In addition you learned validity of criterion reference mastery tests. Finally you learned about factors that influence

validity.

5.0 SUMMARY

Validity is a measure or the degree to which a test measures what it is

intended to measure.

The three concerns of validity are:

- determining the extent to which performance on a test represents level of knowledge of the subject matter content which the test was

designed to measure (content validity of the test);

- determining the extent to which performance on a test represents the

amount of what was being measured possessed by the examinee

(construct validity of the test); and

- determining the extent to which performance on a test represents an examinee’s probable performance on some other related test or task

(criterion validity of a test).

166

Content Validation is the process of determining the extent

to which a set of test tasks provided a relevant and

representative sample of the domain of tasks under consideration.

Criterion Validation is the process of determining the extent to which test performance is related to some other

valued measure of performance.

Correlation coefficient expresses the degree of relationship between two sets of scores by numbers ranging from +1.00 to -1.00.

Two common methods of computing correlation coefficients are:

- Spearman Rank-Difference Correlation - Pearson Product-Moment Correlation

Construct Validation is the process of determining the extent to which test performance can be interpreted in

terms of one or more psychological construct.

A construct is a psychological quality that are assumed

exists in order to explain some aspect of behaviour

Criterion – referenced mastery tests are not designed to

discriminate among individuals. Therefore statistical validation procedures play a less prominent role.

Many factors influence the validity of a test. These factors

include factors in the test itself, factors in the test administration, factors in the examinee’s response,

functioning content and teaching procedures as well as

nature of the group and the criterion.

6.0 TUTOR MARKED ASSIGNMENT 1. What is Validity of a test?

2.

In a class of 20 students the following scores were obtained in the first continuous assessment test in Economics and Geography:

Economics 98 97 95 94 93 91 90 89 88 87 86 84 83 81 80 79 77 76 75 74 Geography 76 75 72 70 68 66 64 60 58 57 56 54 52 50 48 46 44 45 62 77

Using Spearman rank-difference method, calculate the correlation coefficient between the two set of scores obtained by the students of

this class.

3. Explain with the aid of a diagram how to interpret correlation coefficient (r) Values

7.0 REFERENCES/FURTHER READINGS

Gronlund, N.E. (1985). Measurement and Evaluation in Teaching, New York: Macmillan Publishing Company.

Nenty, H. J. (1985). Fundamentals of Measurement and Evaluation in

Education. Calabar. University of Calabar.

168

UNIT 5 PROBLEM OF MARKING TEST AND QUALITY CONTROL IN MARKING SYSTEM

CONTENTS 1.0 Introduction 2.0 Objectives 3.0 Main Content

3.1 Marks and Marking 3.2 Types of Marking Systems

3.2.1 Traditional Marking Systems 3.2.2 Pass-Fail System

3.2.3 Checklists of Objectives

3.3 Quality Control: Current Marking Systems 3.3.1 Multiple Marking System

3.3.2 Guidance for Developing a Multiple Marking

3.4

System

Assigning Letter Grades

3.4.1 Determining what to include in a Grade 3.4.2 Combing Data in Assigning Grades

3.4.3 Selecting the Proper Frame of Reference for

Grading

3.4.4 Determining the Distribution of Grades.

4.0 Conclusion 5.0 Summary

6.0 Tutor Marked Assignments 7.0 References /Further Readings 1.0 INTRODUCTION

From Module 3 Unit 1 of this course we have been discussing test and test related issues. In this Unit we shall round-up our discussion with the problem of marking tests and quality control in marking system.

Specifically, you will learn about marks and marking, types of marking systems namely the traditional marking system, the pass-fail system and

checklist of objectives. Furthermore, you will learn quality control:

current marking systems – multiple marking systems and guidelines for

developing a multiple marking system. Finally, you will learn about assigning letter grades which involves determining what to include in a

grade, combining data in assigning grades, selecting the proper frame of

reference for grading and determining the distribution of grades.

2.0 OBJECTIVES

By the end of this unit you will be able to:

explain the meaning of mark and marking systems;

identify the various types of marking systems and their peculiar characteristics,

state the importance of the multiple marking system;

enumerate the guidelines for developing system;

a multiple marking assign letter grades to marks using the range and the stanine

weighting systems; and

select the proper frame of reference for grading 3.0 MAIN CONTENT

3.1 Marks and Marking

Marks and marking have been very deeply rooted in our educational

system. This is to the extent that they have become the basis in whole or

in part for a wide range of actions and decisions within a given educational institution, between levels in the educational structure, and in

the relations of the educational system in the outside world. For instance, eligibility for admission to certain programmes, for scholarship and, for continuing in school …are determined by academic standing.

For these reasons, marking system have been so desirable, durable and

so resistant to change.

Marks with all these technical limitations remain one of the best predictors of later achievement and so are important in conveying

information about likelihood of success in college generally or in specific institutions or programmes. Marks have a significant role to

play in informing the individual as well as the institution to which he

may later apply of his prospects for academic success. Marking practices on the other hand are expressions of individual and group value systems as much as they are impartial report of student behaviour.

Nevertheless the marking practices are faced with some challenges such

as:

- Should students be penalized for handling in paper late or get extra credit for doing optional work?

-

Should students with the same level of scholastic aptitude get on

the average the same grades irrespective of the subject or

department involved?