Data analysis is one important step in order to obtain the findings of research results. This is due, the data will lead us to the direction of scientific findings when analyzed with appropriate techniques. The data that has not been analyzed is still the raw data. In research activities, raw data will give meaning, when analyzed and interpreted. In order to analyze and interpret the data, it is necessary to understand about the existence of the data itself. Broadly speaking, the existence of data can be classified into two types, namely:
Qualitative data
Qualitatively charged data is also called soft data. Such data is obtained through research using a qualitative approach, or qualitative assessment. The existence of qualitative data is a field record in the form of notes or recording of words, sentences, or paragraphs obtained from interviews using open questions, participatory observation, or the meaning of the researcher on documents or relics. To derive meaning from such data through data interpretation, qualitative data analysis techniques are used, as described in the above chapter.
Quantitative data
The existence of quantitative data is the numbers (quantities), whether obtained from the sum of a merger or measurement. Quantitative loaded data obtained from the sum of a merge always uses a counting number. Examples of such data are census results, tabulated figures on answers to questionnaires or structured interviews. The quantitative data measured results are scores obtained through measurements, such as the score of achievement test, motivation scale scores, scales, and the like.
TECHNIQUES DATA ANALYSIS
Data analysis techniques there are two, namely quantitative data analysis techniques and qualitative data analysis techniques. Quantitative data analysis techniques are different from qualitative.
Technique Analysis of quantitative data
Data analysis in quantitative use statistical approach.
In data analysis techniques using statistics, there are two kinds
statistics used are descriptive and inferential statistics. Inferential statistics include parametric and nonparametric statistics.
a. Descriptive statistics
Descriptive statistics are statistics used to analyze data by describing or describing data that has been collected. Included in descriptive statistics include frequency distribution, percent distribution and measurement of central tendencies. The frequency distribution table that describes the arrangement of data regularly in a table. Data are arranged sequentially according to the size of the numbers or are classified in classes corresponding to the appropriate level and number in the class.
b. Cumulative frequency
Is the frequency calculated increasing to top from the lowest frequency to the highest.
Central Tendency Measurement
Another way of describing descriptive statistics is to use central tendencies. Examples of central tendency numbers are mean (mean), median and mode. Central tendency is useful for drawing numbers that can represent a particular group of numbers.
Mean
Can be searched by summing up all the values then divided by the number of individuals.
Mode
Mode is the value with the greatest number of frequencies. To find the value of the mode can be seen at the largest number of frequencies.
Median
is the middle value that limits the lower half and the upper half of the frequency.
Inferential statistics
Inferential statistics, (often also called inductive statistics or probability statistics) are statistical techniques used to analyze sample data and the results are applied to the population. These statistics would be suitable when samples were taken from a clear population and sampling techniques from the population were randomized.
These statistics are called probability statistics, because the conclusions imposed for the population based on the sample data are a probability. A conclusion of the sample data to be applied to the population has an opportunity of error and truth (trust) and expressed in percentage form. If the error rate 5% then 95% confidence level, if the chance error of 1%, then the level of confidence 99%. This error and confidence opportunity is called the level of significance.
Parametric and Nonparametric Statistics
The parametric statistics are used to test population parameters through statistics, or to test population size through sample data. In the statistic hypothesis tested is the null hypothesis, because no desired difference between population parameters and statistics (data obtained from the sample). Nonparametric statistics do not test parameter population, but test the distribution. The use of parametric and nonparametric statistics depends on the assumptions and types of data to be analyzed. Parametric statistics are mostly used to analyze interval and ratio data, whereas nonparametric statistics are mostly used to analyze nominal, ordinal data. In the table it is seen that parametric statistics are used to analyze interval and ratio data, and nonparametric is used for nominal and ordinal data. So to test the hypothesis in quantitative research using statistics, there are two main things that must be considered is the kind of data and the form of hypothesis proposed.
Qualitative data
Advertisement
Quantitative data
The existence of quantitative data is the numbers (quantities), whether obtained from the sum of a merger or measurement. Quantitative loaded data obtained from the sum of a merge always uses a counting number. Examples of such data are census results, tabulated figures on answers to questionnaires or structured interviews. The quantitative data measured results are scores obtained through measurements, such as the score of achievement test, motivation scale scores, scales, and the like.
TECHNIQUES DATA ANALYSIS
Data analysis techniques there are two, namely quantitative data analysis techniques and qualitative data analysis techniques. Quantitative data analysis techniques are different from qualitative.
Technique Analysis of quantitative data
Data analysis in quantitative use statistical approach.
In data analysis techniques using statistics, there are two kinds
statistics used are descriptive and inferential statistics. Inferential statistics include parametric and nonparametric statistics.
a. Descriptive statistics
Descriptive statistics are statistics used to analyze data by describing or describing data that has been collected. Included in descriptive statistics include frequency distribution, percent distribution and measurement of central tendencies. The frequency distribution table that describes the arrangement of data regularly in a table. Data are arranged sequentially according to the size of the numbers or are classified in classes corresponding to the appropriate level and number in the class.
b. Cumulative frequency
Is the frequency calculated increasing to top from the lowest frequency to the highest.
Central Tendency Measurement
Another way of describing descriptive statistics is to use central tendencies. Examples of central tendency numbers are mean (mean), median and mode. Central tendency is useful for drawing numbers that can represent a particular group of numbers.
Mean
Can be searched by summing up all the values then divided by the number of individuals.
Mode
Mode is the value with the greatest number of frequencies. To find the value of the mode can be seen at the largest number of frequencies.
Median
is the middle value that limits the lower half and the upper half of the frequency.
Inferential statistics
Inferential statistics, (often also called inductive statistics or probability statistics) are statistical techniques used to analyze sample data and the results are applied to the population. These statistics would be suitable when samples were taken from a clear population and sampling techniques from the population were randomized.
These statistics are called probability statistics, because the conclusions imposed for the population based on the sample data are a probability. A conclusion of the sample data to be applied to the population has an opportunity of error and truth (trust) and expressed in percentage form. If the error rate 5% then 95% confidence level, if the chance error of 1%, then the level of confidence 99%. This error and confidence opportunity is called the level of significance.
Parametric and Nonparametric Statistics
The parametric statistics are used to test population parameters through statistics, or to test population size through sample data. In the statistic hypothesis tested is the null hypothesis, because no desired difference between population parameters and statistics (data obtained from the sample). Nonparametric statistics do not test parameter population, but test the distribution. The use of parametric and nonparametric statistics depends on the assumptions and types of data to be analyzed. Parametric statistics are mostly used to analyze interval and ratio data, whereas nonparametric statistics are mostly used to analyze nominal, ordinal data. In the table it is seen that parametric statistics are used to analyze interval and ratio data, and nonparametric is used for nominal and ordinal data. So to test the hypothesis in quantitative research using statistics, there are two main things that must be considered is the kind of data and the form of hypothesis proposed.
No comments