o POPULATION - Entire aggregation of the case where a researcher is interested Often, it is not feasible to include all the members of the population in research o A homogenous mixture is that mixture in which the components mix with each other, and its composition is uniform throughout the solution. A heterogenous mixture is that mixture in which the composition is not uniform throughout, and different components are observed. SAMPLING - Process of selecting the sample or a portion of the population NON-PROBABILITY SAMPLING - SAMPLE - Subset of the population elements REPRESENTATIVENESS - How well the sample represents the population An important characteristic of a sample must be considered REPRESENTATIVE SAMPLE - - - There is a form of bias in the selection of sample There is no assurance that each element in the population has the same equal chance of being selected There is no assurance that each that each unit in the population is properly represented The findings are limited to the sample PROBABILITY SAMPLING - One whose key characteristics closely approximate those of the population - There is random selection of sample There is greater representation in each unit in the population Each element in the population has the same equal chance of being selected as a sample The findings can be generalized to the population SAMPLING ERROR - - - Result to overrepresentation or underrepresentation of some segment of the population Occurs if the selection of the sample does not take place in the way it was planned Smaller sample size = bigger chance of sampling error The appropriate sample size also depends in the heterogeneity (Heterogenous group – bigger size) and homogeneity (Homogenous group – smaller size) TYPES OF NON-PROBABILITY SAMPLING Convenience Sampling - Selection of samples based on the convenience of the researcher Involves the most conveniently available people to participate Sometimes called Accidental Sampling Snowball Sampling - - “Referral System” “Chain System” Initial sample members are asked to refer other people who meet the criteria required by the researcher People who share the same traits or experiences know each other Useful for participants who are hard to find Purposive Sampling - The selection of the sample is based on the selective judgment of the researcher Judgmental Sampling Sets a criterion that is relevant to the topic under study Quota Sampling - - Researcher identifies population sections or strata and decide how many participants are required from each section Allow better representation from each unit in the population Has requirements/criterion unordered number in electing name from the list. Systematic Random Sampling - - Uses the Kth interval formula k=N/n o k = sampling interval o n = desired sample o N = Population Sampling interval is the standard distance between elements chosen for the sample Stratified Random Sampling - - - Population is divided into subgroups or strata Just like quota sampling, stratification is based on variables related to the study After stratification, appropriate number of elements are selected from each stratum at random No requirements/criterion Cluster Sampling - Useful when the population is large and widely dispersed Sampling is done in several stages Is also called multi-stage sampling The resulting design is described in terms of the number of stages TYPES OF PROBABILITY SAMPLING Simple Random Sampling - - - Each member of the population has the same equal chance of being selected as a sample Based on chance Two methods: Fishbowl – write each name on a card and choose cards through a pure chance selection. Number Generated – known as sampling frame; give a number to member and then use randomized or SAMPLE SIZE IN QUANTITATIVE STUDIES In a quantitative study, the sample size is an important aspect that must be carefully considered. There are existing procedures that can be used to estimate the appropriate sample size, but statistical knowledge is required to understand this procedure. There are no fixed rules nor simple formulas that can tell us how large a sample should be when conducting quantitative studies, but there are recommendations: 1. The larger the sample size, the better. Smaller sample size tends to produce less accurate estimates. 2. If the sample is homogenous, a small sample size may be adequate. Homogeneity means that the population elements were all identical with respect to key attributes. 3. If there is reason to expect that the independent and dependent variables will be strongly related, then a relatively small sample should be adequate to demonstrate the relationship statistically. 4. For studies that will take a long time to finish (longitudinal studies) researchers should factor in anticipated of subjects over time. Therefore, a larger sample size is necessary. So, in case there will be a high attrition or dropouts from the study, the sample size will still be adequate. IMPLEMENTING A SAMPLING PLAN IN QUANTITATIVE STUDIES Steps in Sampling Quantitative Studies ( Polit and Beck, 2007) The steps to be undertaken in drawing a sample vary somewhat from one sampling design to the next, but a general outline of procedures can be described. 1. Identify the population. 2. Specify the eligibility criteria. 3. Specify the sampling plan. 4. Recruit the sample. INTRODUCTION TO STATISTICS - In statistics, before the main analysis, the data are assuming to meet all the requirements that a data should have, or a data should undergo first some preliminary checking to test if a certain statistical technique is appropriate for the analysis When performing a hypothesis test, a p (probability) value helps to determine the significance of the results. In decision making, a p-value that has a value which is less than 0.05 (a) indicates significance. RELATIONSHIP HYPOTHESIS NULL HYPOTHESIS “HO” - NEGATIVE RELATIONSHIP - A type of hypothesis which states that there is no statistical significance/relationship or effect existed between two or more groups. ALTERNATIVE HYPOTHESIS “Ha” - Also known as the research hypothesis, it is the proposed hypothesis or expected outcome of the research. Also called as inverse relationship. Aside from the test statistic having a negative value, the correlation between two variables is said to have a negative/inverse relationship as the amount of one variable increases, the level of another variable goes down. POSITIVE RELATIONSHIP - Or a direct relationship whereas the amount of one variable increases, the amount of a second variable also increases. LINEAR RELATIONSHIP - Statistical term used to describe the relationship between two sets of data. SAMPLE - NONPARAMETRIC STATISTICS - Type of statistics that should be use when the data violated the requirements for a parametric test (i.e., if the data are not *Normally Distributed; or if the measurements of the data are on an ordinal scale etc.) Is a relatively small subset of people, objects, groups, or events that is selected from the population TEST STATISTIC - It is considered as numerical summary of a data – set that reduces the data to one value that can be used to perform a hypothesis test. PARAMETRIC STATISTICS - - P value When the data are in interval level and are *Normally Distributed, parametric statistics is a type of statistics that should be use. Always superior to Nonparametric counterpart for decidedly Normal population. VARIABLES - In research, it is a logical set of attributes, factors that can be controlled or change in experiment/research TYPES OF VARIABLES INDEPENDENT VARIABLE - It is the variable that the researchers have control over, can be choose and manipulated. Usually, it is what the researcher think will affect the dependent variable - DEPENDENT VARIABLE - Represented as “Y”, it is the response variable or the presumed effect in a study which can be measured in interval or nominal scale. - RATIO SCALES - DIFFERENTIAL STATISTICS - It is the statistical procedures that the researcher uses To describe the population, they are studying INFFERENTIAL STATISTICS - It is the statistics that is concerned with making predictions or inference About a population from observations and analysis using a sample and can generalize it to the larger population that the sample represents Distances between data elements can be determined at the interval level of measurement. In other words, the interval is the same. Oftentimes in psychology things are measured by a Likert scale in which one rates a statement (often by how much they agree with the statement). Arbitrary zero (the starting point) (can be negative/positive) (temperature) - Possess the advantage of all other measurement scales for it is the only measurement that can be analyzed with the widest range of statistical methods which makes it as the highest form of measurement precision. It has all the components of an interval scale but here, the zero point is meaningful and means the absence of whatever it is measuring. Common examples are age, height, weight, test, and heart rate. Absolute Zero NONMETRIC MEASUREMENT SCALES MEASUREMENT SCALES To accurately represent the concept of interest, measurement of the variables is essential and is instrumental in the selection of the appropriate statistical method of analysis. Based on the types of attributes or characteristics the data represent, it can be classified into one of two categories: nonmetric and metric. - NOMINAL SCALES - METRIC MEASUREMENT SCALES - Data that are metrically are used when subjects differ in amount or degree on a particular attribute. Metric data reflects relative quantity or degree and are appropriate for attributes involving amount or magnitude, i.e., Level of satisfaction INTERVAL SCALES Describes differences in type or kind by indicating the presence or absence of a characteristics or property. Nominal level (or categorical) data refers to data that can only be put into groups. It only represents categories or classes and do not imply amounts of an attributes or characteristics. Commonly used examples of nominally scaled data include many demographic attributes (e.g., gender, religion, occupation). ORDINAL SCALES - In the case of ordinal scales, variables can be ordered or ranked in relation to the amount of the attribute possessed, Ordinal scales provide no measure of the actual amount or magnitude in absolute terms, only the order of the values. - The researcher knows the order, but not the amount of differences between the values SAMPLING - Method From one population you will get representatives on the in the way of your sampling technique MEASUREMENT OF SCALES METRIC - INTERVAL – Arbitrary zero – possible negative values (temperature, Likert scale) POPULATION - Entire aggregation RATIO – Absolute zero – NO negative values (test scores, salary) SAMPLE - Representative NONMETRIC - Equal chances NOMINAL – categories SIMPLE – Fish-bowl method STRATIFIED – group/target number of requirements SYSTEMATIC – kth interval (n/N) STATISTICAL ANALYSIS - CLUSTER – multistage sampling, the population is too big (levels) NON-PROBABILITY - Not Equal – biased PURPOSIVE – Set of criteria QOUTA – group/target number of requirements/requirements SNOWBALL – referral, chain system Categories/ranking ORDINAL – ranking, orders (birth order, academic awards) PROBABILITY SAMPLING TECHNIQUE - Specific values What to use as statistical analysis based on the group, measurement of scale, etc. CORRELATION - Measuring 2 Continuous Variables if there is a relationship in the two variables. o Continuous Variable – both variables are measurable o Example: ALLOWANCE MOTIVATION CONVENIENCE – proximity/accessibility Pearson’s Product Moment Correlation (PEARSON’S R) COMPARATIVE - INDEPENDENT T-TEST o Comparing two groups Example: Measuring the Motivation of: 1. 2. Modular Students Online Class students (OCR) o o If P value is lower than (<) significant value = reject Ho If the P value is higher than (>) significant value = accept Ho Example: P value – 0.001 Significance – 0.05 - ONE-WAY ANOVA o Comparing 3 or more groups o Reject Null Hypothesis (Ho) – there is a significance Example: Comparing the 4 Strands in SHS: STEM, HUMMS, GAS, ABM P value – 0.73 Significance – 0.05 o - PRE-TEST & POST-TEST o 1 group – experimentation and want to know if the group will improve Example: Study about effects of diet – if the weight will decrease? o o The other test already has experiment and the other test have none PAIRED T-TEST – INTERVENTION (experiment, pre-test, post-test) MANUSCRIPT RESEARCH LOCALE - Geographic RESEARCH DESIGN - Approach/comparative or correlation RESEARCH ETHICS - Ethical, citations, consent, etc. RESEARCH INSTRUMENTS - Tools ANALYSIS - Comparing the P VALUE and SIGNIFICANT VALUE Accept Null Hypothesis (Ho) – there is no significance