STATISTICAL ANALYSIS AND SOFTWARE - Statistical analysis is harder
APPLICATION - Collected using interviews, written
documents, observations Statistics – is the science of conducting studies to - Verbal and written feedback collect, organize, summarize, analyze, and draw - Narrative story conclusions from data. o First-hand (direct experience) - is used in almost all fields of human o Second-hand (telling someone endeavor. else) - it is used to analyze the results of surveys and o Third-hand (outside story teller) as a tool in scientific research to make - Visual images, drawings, or models decisions based on controlled experiments. - Experiential sensations Other uses of statistics include operations - Descriptions of: color; texture; research, quality control, estimation, and smells; tastes; appearance; beauty; prediction. feelings; intuition; sensations; choices; values; beliefs Variable – is a characteristic or attribute that can 2. Quantitative Data – data type that can be assume different values. measured and expressed numerically. Random Variables – whose values are determined - Number-based by chance. - Statistical analysis is easier - is a variable that is used to quantify the - Collected using surveys, outcome of a random experiment. observations, experiments and interviews Data Set – a collection of data values. - Money; time; speed; movement; Data Value or a Datum – each value in the data set. height; length; area; volume; weight; temperature; humidity; pressure; TWO MAIN AREAS OF STATISTICS sound level; categories (age, gender, 1. Descriptive Statistics – are numbers that are occupation); positioning; status used to summarize and describe data. The FOUR LEVELS OF MEASUREMENT word “data” refers to the information that has been collected from an experiment, a 1. Nominal Level – data that is classified into survey, a historical record, etc. categories and cannot be arranged in any 2. Inferential Statistics – the sample is a set of particular order. data taken from the population to represent - Examples: eye color, gender, the population. Probability distributions, religious affiliation hypothesis testing, correlation testing and 2. Interval Level – similar to the ordinal level, regression analysis all fall under the category with the additional property that meaningful of inferential statistics. amounts of differences between data values can be determined. There is no natural zero Population – consists of all subjects (human or point. otherwise) that are being studied. - Example: temperature on the Sample – is a group of subjects selected from a Fahrenheit scale population. 3. Ordinal Level – data arranged in some order, but the differences between data values TYPES OF DATA cannot be determined or are meaningless. 1. Qualitative Data – data type that consists of - Example: during a taste test of 4 soft descriptive statements. drinks, Mellow Yellow was ranked - Text-based number 1, Sprite number 2, Seven-up number 3, and Orange Crush number ➢ Quantitative Data Collection 4. o Probability Sampling 4. Ratio Level – the interval level with an o Interviews inherent zero starting point. Differences and o Surveys & Questionnaire ratios are meaningful for this level of o Observations measurement. o Document Review - Examples: monthly income of Phone Surveys surgeons, or distance traveled by manufacturer’s representatives per - High confidence month. - Need to hire an agency TYPES OF VARIABLES Online Surveys 1. Nominal Variables – it represents categories - Self-manage that cannot be ordered in any way. - Data accuracy - It is a variable with no quantitative - Need internet value. - It has two or more categories but does In-person Interviews not imply ordering of cases - In-depth - Examples: eye color, business type, - Time consuming religion, political affiliation, gender, race SAMPLING TECHNIQUES 2. Interval Variables – it has values that lie 1. Probability Sampling – utilizes random along an evenly dispersed range of numbers. sampling techniques to create a sample. This - It is a measurement where the group of sampling methods give all the difference between two values does members of a population equal chances of have meaning. being selected. - Examples: temperature, time IQ test a. Simple Random Sampling – every 3. Ordinal Variables – it represents categories individual has an equal and that can be ordered from greatest to smallest. independent chance of being selected - This variable has two or more from the population. Lottery Method categories which can be ranked. b. Cluster Sampling – the entire - Includes like scale: 1 = very poor, 2 = population is divided into clusters and poor, 3 = fair, 4 = good, 5 = excellent the sample is chosen at random. - Examples: socio economic status; c. Systematic Sampling Technique – educational level: 1 = high school the sampling starts by selecting an graduate, 2 = college undergraduate, element from the list at random and 3 = master’s degree graduate, 4 = then every (k) th element in the frame doctorate degree graduate; income is selected. Where (k) is the sampling brackets interval, n is the sample size, N is the DATA COLLECTION population size. k = N/n d. Stratified Random Sampling – ➢ Qualitative Data Collection population is divided into two or more o Interviews groups called “strata”, according to o Surveys some criterion, such as geographic o Group Discussions location, grade level, age, or income, o Observations and subsamples are randomly selected from each strata. Elements within each strata are homogeneous - also viewed as a two-stage but are heterogeneous across strata. restricted judgement sampling. 2. Non-probability Sampling – samples are In the first stage restricted collected in a way that does not give all the categories are built as discussed units in the population equal chances of being above and in the second stage selected. It does not involve random selection respondents are selected on the at all. basis of convenience of a. Convenience Sampling – also judgement of the researchers. referred to as accidental or incidental FREQUENCY DISTRIBUTION sampling. - involves choosing readily ORGANIZING DATA available people or objects for Data organization – is a process of organizing raw study. - this probably the most frequently data, by classifying them into different categories. used sampling method This raw data includes the observations of variables. - saves time and money Raw data – is the data that is collected from a source, - use results that are easy to get but in its initial state. It has not yet been processed — b. Purposive Sampling (Judgmental or cleaned, organized, and visually presented. Sampling) – the researchers choose the sample based on who they think A frequency distribution is the organization of raw would be appropriate for the study. data in table form, using classes and frequencies. - this is used primarily when there TWO TYPES OF FREQUENCY is a limited number of people that DISTRIBUTIONS: have expertise in the area being researched 1. Categorical Frequency Distribution – is - a researcher may have a specific used for the data that can be placed in specific group in mind categories, such as nominal or ordinal level - it may not be possible to specify data. the population and may not 2. Grouped Frequency Distribution – when represent the population as the range of data is large, the data must be whole grouped into classes that are more than one c. Snowball Sampling – choosing the unit of width. participants to find more participants Range = Highest Value – Lowest Value for making a sample group Width = Range/Number of Classes - mostly researchers used this sampling technique where Cumulative Frequency Distribution – is a participants are difficult to locate distribution that shows the number of data values less in a general participation than or equal to a specific value (usually an upper d. Quota Sampling – it is a procedure boundary). that restricts the selection of the sample by controlling the numbers of respondents by one or more criterion - the restriction generally involves quotas regarding respondent’s demographic characteristics, specific attitudes, or specific behaviors GRAPHS 3 MOST FREQUENTLY USED GRAPHS IN RESEARCH 1. Histogram – is a graph that displays the data by using contiguous vertical bars (unless the frequency of a class is 0) of various heights to represent the frequencies of the classes. 2. Frequency Polygon – is a graph that displays the data by using lines that connect points plotted for the frequencies at the midpoints of the classes. The frequencies are represented by the heights of the points. 3. Cumulative Frequency Graph (Ogive) – third type of graph that can be used to represents the cumulative frequencies for the classes. Cumulative Frequency – is the sum of frequencies accumulated up to the upper boundary of a class in the distribution.
ED 203 Statistics Course OverviewTITLE ED 203 Statistics MAEd Course Syllabus TITLE ED 203 Statistics Concepts, Methods and ApplicationsTITLE ED 203 Statistics for Education Graduate Students