The Role of Measurement in the Public Polls (Albanian Case)

Introduction

There are a lot of concepts that are tied with each other. The concept that are tied with each other, are the types of measurement, the role of reliability, the role of validity, the role of measurement.

To have reliability and validity result we should have the good relationship with each element of the research design. Measurement provides information about where we have been, where we are currently, and whether we are changing over time. 1 So it is very important to choose the right types of measurement. According to the Steven’s Stately we have four types of measurement that are:

Nominal Scale Ordinal Scale Interval Scale Ratio Scale

The nominal scale simply places people, events, perceptions, etc. into categories based on some common trait. The nominal scale is the lowest form of measurement because it doesn’t capture information about the focal object other than

1 D. Lynn Kelley “Measurement made accessible” A Research Approach Using Qualitative, Quantitative, & Quality Improvement Methods -SAGE Publications 2 00 o International Educational and Professional Publisher Thousand Oaks London New Delhi” fq 1

whether the object belongs or doesn’t belong to a category. Coding of nominal scale data can be accomplished using numbers, letters, labels, or any symbol that represents a category into which an object can either belong or not belong. 1

The ordinal scale has at least one major advantage over the nominal scale. The ordinal scale contains all of the information captured in the nominal scale but it also ranks data from lowest to highest. Rather than simply categorize data by placing an object either into or not into a category, ordinal data give you some idea of where data lie in relation to each other. 2

Unlike the nominal scale that simply places objects into or out of a category or the ordinal scale that rank orders objects, the interval scale indicates the distance one object is from another. In the social sciences, there is a famous example often taught to students on this distinction. 3

The scale that contains the richest information about an object is ratio scaling. The ratio scale contains all of the information of the previous three levels plus it contains an absolute zero point. To use the example above, the ratio scale allows you to measure the stumps from the bottom of the lake; the bottom of the lake represents the absolute zero point. 4

So I can say that I have used the ratio scale in my research in order to reduce the error margin, because it is the only types of measure that is more correctly that the other types of measurement.

Methodology

So I have done two types of survey in Tirana in different period of times, when I have used a criteria of not identify the respond and in another survey I have used another criterion when I have not identified the respondent. I emphasize that the problem that I have studied, are delicate problem and the respondent here in Albania are afraid to tell the truth. So the reliability and the validity of the result of the research it will not be the truth.

Also another element that is important in my research is the role of the sample. We have a lot of types of sample which are:

) Probability Sampling Methods.

ii) Non probability sampling methods. 5

And we can say that the belong methods of sampling are:

Simple Random Sampling Stratified Random Sampling Cluster Sampling

Quota Sampling: Purposive Sampling Systematic Sampling

1 http://www.socialresearchmethods.net/kb/measlevl.php

2 http://www.socialresearchmethods.net/kb/measlevl.php

3 http://www.socialresearchmethods.net/kb/measlevl.php

4 http://www.socialresearchmethods.net/kb/measlevl.php

The types of sample that I have used in my research are quota sampling and the systematic sampling, which the meanings of these are:

Quota sampling: This method of sampling is almost same with that of stratified random sampling as stated above, the only difference is that here in selecting the elements randomization is not done instead quota is taken into consideration.

Systematic sampling: In this method every n th element is selected from a list of population having serial number. 1

I emphasize that this types of sample enter a margin of error, that effect in the reliability and the validity of the scientific research. In my study two types of these samples enter a margin of error when the systematic sampling enters an error and also the quota sampling enters an unspecified error.

Results of Data Processing

Survey on the Road:

ISW (street) = [Δ (life satisfaction) + Δ (Happiness)] / 2 =[+ 4. 4% + 30. 1%] / 2 = + 34. 5% / 2 = + 17. 25% So we have to ISW (street) = + 17. 25 %

The Survey in the Family:

ISW (family) = [Δ (life satisfaction) + Δ (Happiness)] / 2 =

[+ 20% + 28. 9%] / 2 = + 48. 9% / 2 = 24. 45%

So we have to ISW (family) = + 24. 45%

Margin required is:

ISW (Family) = + 24. 45% - ISW (Street) = + 17. 25% = + 7. 2%

As the margin it will be [- 7. 2%+ + 7. 2%]. From this margin will be "expected" statistical error, that inserts the sample of size (for sampling with size 100 units) is + / - 10. 6%. We will have: (- 7. 2%)- (- 10. 6%) = - + 17. 8%

So the margin remains [-17. 8% + 17. 8%]. CONCLUSIONS

As conclusion, we can say it is so important to choose the right types of measurement, the right types of sampling and the right way to do the reliability results. As I have chosen the right items also results that have entered an error. This error effect negatively in the results of the surveys.

So it is so important to use the right instrument to have good results and the reliability and validity results.

References