Lecture 7 Data Analysis.pdf

DENT4407 Research Methods in Dentistry Lecture 7: Data Analysis Assoc. Prof. Magrur Kazak [email protected] 14.11.2023 Resources Data Analysis The researcher has an idea to investigate From that idea, the researcher plans the research Conducts the research Gets the primary/raw data Data...

DENT4407 Research Methods in Dentistry Lecture 7: Data Analysis Assoc. Prof. Magrur Kazak [email protected] 14.11.2023 Resources Data Analysis The researcher has an idea to investigate From that idea, the researcher plans the research Conducts the research Gets the primary/raw data Data are the values of variables that the researcher searches for. e.g.: compressive strength, contact angle, porosity, roughness, etc. After collecting the raw data, it should be analysed with the appropriate statistical methods before interpreting them. Statistical tests need to be clarified to determine whether the differences observed between the examined groups/examined and control groups are significant or not significant. Data Analysis The process of performing certain calculations and evaluations in order to extract relevant information from data is called data analysis. The data analysis may take several steps to reach certain conclusions. 1-Classification and tabulation 2-Graphical representation 3-Measure of location 4-Measure of variability 5-Measure of relationship 6-Estimating the unknown 7-Testing of hypothesis Data Analysis Step 1 1-a-Classification of data means the categorization of data The classification can be done on the basis of the quality of attributes such as gender, literacy, age, city, time… 1-b-Tabulation (making a table) is the frequency distribution of variables. The main objective of tabulation is to condense the data and to make comparison easy. With the tabular form, the necessary interpretation can be easily achieved. The data looks very clear. Preparation of the table depends on the size and nature of the data. Data Analysis Step 2 2-Graphical representation of data The data can be displayed with half of a graph and diagram instead of a classification of tabulation. The graphs present the summary of the data. The graphs give a visual presentation of data. At looking the graphs, one can understand the data easily. Data Analysis Common types of graphs: 1. Simple bar cart 2. Multiple bar chart 3. Pie chart 4. Histogram 5. Scatter diagram Same Data Analysis Step 3 3-Measure of location Measures of location describe the central tendency of the data. The most common measures of tendency include the arithmetic mean, median and mode. The arithmetic mean is useful when data is relatively homogeneous, The median is used when data or values are relatively heterogeneous The mode is useful when one value occurs more frequently. The arithmetic mean of values is obtained by adding all the values and then dividing by their number. Symbolically it is described as Data Analysis The median is the middle value in a set of data. The median is the number in the middle {2, 3, 11, 13, 26, 34, 47}, which in this instance is 13. Mode is the value of the data which is more frequent in the data. e.g.:12, 14, 12, 15, 12, 13, 14, 12, 15. 12 is the mode of data. Data Analysis Step 4 4-Measure of variability Statistical analyses of differences resulting from changes in data are called measures of change. The most useful measures are range, Standard deviation and variance. The range is the difference between the maximum and minimum values. Range = Maximum Measurement - Minimum Measurement The range depends only on the extreme values of the data and does not consider other values. The occurrence of extreme values in the data greatly affects the range, so it is not considered a good measure of distribution. It provides information about whether the group has a homogeneous or heterogeneous distribution. Example: 78, 89, 56, 36, 48, 92, 59, 60 Range: 92-36=56 Data Analysis Standard deviation is a measure of how far the data deviates from the arithmetic mean in a data group. It is a reliable measure of change. greater the value of standard deviation means greater is the variation in the data. a smaller value of standard deviation means smaller variations in the data Variance is a statistical measure of how spread out data points are within a sample or data set. Data Analysis Step 5 5-Measure of relationship In certain situations, the researcher is interested in finding out the relationship between variables. e.g.:roughness and hardness values Whether there is a strong relationship between two variables or a weaker relationship between variables The measure of relationship is classified as: 1. Regression is used to estimate one variable on the basis of other variables. 2. Correlation describes the relationship between two variables. Data Analysis Step 6 Step 7 6-Estimating the unknown It is simply a process or procedure of estimating the unknown parameters of the population. 7-Testing of hypothesis Hypotheses are acceptable/rejectable judgments. The procedure which leads to accepting or rejecting specified statements about tested parameters is called testing of hypothesis. e.g.: the researcher wants to investigate the relationship between country and caries incidence The hypothesis of the researcher is caries incidence will be lower as the country gets richer. The researcher should accept or reject this hypothesis. Data Analysis Types of hypothesis: 1-Null Hypothesis 2-Alternative/Research Hypothesis The researcher may have one hypothesis which is called the null hypothesis: H0 A null hypothesis is a hypothesis that there is no relationship between the variables. The researcher sometimes needs more than one hypothesis. It is called an alternative/research hypothesis: H1 The alternative/research hypothesis states that there is a difference or relationship between the variables. Data Analysis The name of the software used for statistical analysis is usually mentioned. Most computer programs are equipped with Excel software. The most common software in medical science is Statistical Package for the Social Sciences (SPSS). These tools enable the researcher to enter the raw data and perform a wide range of statistical and multivariate analyses on them.