NCMB315 BSN 3rd Year 2nd Semester Midterm 2023 PDF

NCMB315: Exam Week 12 BSN 3RD YEAR 2ND SEMESTER MIDTERM 2023 Bachelor...

NCMB315: Exam Week 12 BSN 3RD YEAR 2ND SEMESTER MIDTERM 2023 Bachelor of Science in Nursing 3YA Professor: Sharon B. Cajayon, RN, MAN Midterm Topics: (From Mam Cajayon) Experimental research Ethics - Research design where researchers are active agents and Privacy, confidentiality, beneficence, etc not merely passive observer. The researcher consciously Quantitative manipulates the conditions in the study and makes Experimental and types true and quasi observations in a tightly controlled environment. Non experimental and types descriptive, correlation, - It seeks to determine if a specific treatment influences an comparative outcome. Mixed method and types - It includes True experiments, with the random assignments Research design of subjects to treatment conditions and a Quasi experiments that use non randomized assignments of Pheno, grounded, etc subjects. Related Literature - Types: Theoretical Framework 1) True experimental Sampling and types 3 properties: Data collection process Manipulation – experiment group Mean, median, mode Control – group doesn’t receive exp. Categorical data Randomization – non biased selection Nominal, interval etc 2) Quasi experimental research Interview Lacks at least one of the properties of true Questionnaire experimental research Observation Involves manipulation of an independent variable, Themes but lacks randomization to treatment group. Anova, Pearson, t test variance, range Nonexperimental research Type 1 ang 2 error - Does not use manipulation and control of the independent variable and conducted mostly in the natural settings QUANTITATIVE DATA under natural conditions. Research Process - Types Phase 1: The Conceptual phase 1) Comparative – test difference (new / old curr) Phase 2: The Design and Planning phase 2) Correlational – test the strength of relationship (IQ / HT) Phase 3: The Empirical phase 3) Methodological – instrument (Tool /questionnaire) Phase 4: The Analytic phase 4) Survey – characteristics of the population. (school, Phase 5: The Dissemination phase community, normative, social survey) Quantitative Research - Is conducted to find answers to questions about Phase 4: The Analytic Phase relationships among measurable variables with the - Analyzing through appropriate quantitative or qualitative purpose of explaining, controlling and predicting methods, the research data phenomena. Hence, it is knowing the outcome stated in - Interpreting the results of the analyses numerical data Statistics - Scientific method which use a general set of orderly, - Deals with logical collection, organization, presentation, disciplined procedures to acquire information and moves analysis and interpretation of numerical data. in an orderly and systematic fashion. - Fields of statistics: - Characteristics 1) Descriptive – allow the researcher to organize the data Gathers empirical evidence in ways that give meaning and facilitate insight Numeric (frequency distributions and measures of central Statistical treatment tendency and dispersion) 2) Inferential – statistics designed to allow inference from Deductive reasoning a sample statistic to a population parameter; Experimental research Non-experimental research commonly used to test hypotheses of similarities and True experimental research Descriptive differences in subsets of the sample under study Quasi experimental research Comparative Doing research and the goals of science: to describe, to Correlational explain, to predict Methodological Survey J.A.K.E 1 of 19  NURSING RESEARCH 2: BSN 3RD YEAR 2ND SEMESTER MIDTERM 2023 Statistics and its place in research Level of statistical analysis 1) Conceptualization 1) Univariate analysis – Examination of the distribution of 2) Choice of research method cases on only one variables 3) Population and sampling 4) Observation 5) Data processing 6) Data analysis 7) Application Statistics and its importance in research A means to achieve the goals of science: - gives exact kind of description 2) Bivariate analysis – Two variables are studied, an element - enables us to draw conclusions of comparison is added - enable us to predict Table 1. Church attendance reported by men and women - helps us analyze causal relationships Men Women Reinforces systematic procedures Weekly 25.0 34.0 Brings order out of chaos Less often 75.0 66.0 What we need to know when quantifying data Total % 100.0 100.0 Understand the research problem 3) Multivariate analysis – Several variables are being studied Understand the nature of our variables - categorical or metric data - levels of measurement: NOIR Level of statistical analysis Distinguish the appropriate statistical procedures Nature of variables 1) Categorical data - Cases are in defined classes: data are counted or yield frequencies - Ex. gender (variable), categories male and female 2) Metric Data Mean, median and mode - Cases are measured. Thus, these data yield metric or Mean – average, add all values divided by the number of scale values. Ex. height (4.5 m), IQ (130) values Median – the value which divides the values into two Levels of measurement halves 1) Nominal Mode – most frequent occurring value - Data are classified into categories. These categories have no particular order. Descriptive analysis - Gender, civil status, political affiliation, etc. - It is a statistical technique that provides simple description 2) Ratio and summary about the sample and about the - Highest level of measurement. Aside from a constant observations that has been made. size in difference between numbers, it has a fixed zero Table 1: frequency distribution point. - Weight, height, income, allowance per week 3) Interval - The difference between numbers is a known constant size; zero is arbitrary - Temperature in Celsius, IQ scores 4) Ordinal (N=250) were the total number of respondents – 43.2% of the - Categories imply some sory of ranking respondents were male (108) and 56.8% were female (142). - Year standing, ranks of professors, likert “scale”, etc, SES Table 2: cross tabulated table J.A.K.E 2 of 19  NURSING RESEARCH 2: BSN 3RD YEAR 2ND SEMESTER MIDTERM 2023 In table 2 there are 140 (42.81%) males and 187 (57.19) Interpreting measures of association: females for a total of (N=327) participants. N the total row below were nurses where (23.8%) are males and (14.06%) are females. The researchers also considered 113 (34.56% PT as respondents for this research wherein 46 (14.06%) were males and 67 (20.49%) were female PT. Dentistry took par in this study, 16 (4.89) are males and 12 (3.67%) are female with the *take note of the direction of the relationship tota of 28 (8.56%) participants. Suggested by: Gibbon and Morris Table 3: weighted mean Type of research question Statistics Descriptive Mean, frequency Complex descriptive Cross-tabulations, factor analysis Single factor difference t-test, z-test, one-way questions ANOVA Complex pr multifactor Factorial ANOVA difference questions Basic associational Correlation questions Scale: 1.0-1.49; Very Rare; 1.5-2.49; Rarely: 2.5-3.49; Complex or multivariate Pearson R; when predicting: Sometime; 3.5-4.49; Often: 4.5-5.0; Very Often assosciational questions Multiple Regression Choosing the Appropriate Measure Bivariate Analysis: Choosing the Appropriate Measure Univariate Analysis: Describing Data Describing Data Nominal Measures of dispersion - applicable to at scales Phi coefficient Range - highest value - lowest value - Or mean square contingency coefficient and is a measure Variance and Standard Deviation - "variance is the of association for two binary variables. Introduced by Karl average of the squares of the distance each value is from Pearson, this measure is similar to the Pearson correlation the mean (Bluman, 1993:95). The square root of the coefficient in its interpretation. variance is the standard deviation. - A phi coefficient of 0 would indicate that there is no Standard Deviation - how disperse the values are from the systematic pattern across the 2x2 matrix. Or mean Gender Male Female Choosing the Appropriate Measure Bivariate Analysis: Marital Married 5 5 Describing Data Status Single 1 2 Measures of association Ordinal Levels of measurement Spearman rho Nominal Ordinal Scale - Is a nonparametric measure of rank correlation (statistical Correlation Phi Spearman Pearson R dependence between the ranking of two variables). coefficients coefficient rho - Spearman’s rank correlation coefficient or spearman’s rho, (2x2) Kendall’s tau named after Charles spearman Contingency Kruskall- Spearman rho (maximum value is 1) coefficient wallis - Is the nonparametric version of the pearson correlation Cramer’s coefficient. Your data must be ordinal, interval, or ratio. statistic - Spearman’s returns a value from -1 to 1, where: +1 = a perfect positive correlation between ranks -1 = a perfect negative correlation between ranks 0 = no correlation between ranks. Kruskal-wallis H test - Sometimes also called the “one-way ANOVA on ranks” - Is a rank based nonparametric test that can be used to determine if there are statistically significant differences between two or more groups of an independent variable on a continuous or ordinal dependent variable. - The test determines whether the medians of two or more groups are different. Like most statistical tests, you calculate a test statistic and compare it to a distribution cut-off point. - J.A.K.E 3 of 19  NURSING RESEARCH 2: BSN 3RD YEAR 2ND SEMESTER MIDTERM 2023 - Example: Setting the level of significance is setting the probability of 1) You want to find out how test anxiety affects actual test erroneously rejecting a true Ho to be at the most equal to a scores. The independent variable “test anxiety” has a is conventionally set at 0.05, 0.01 or 0.1 three levels: no anxiety, low medium anxiety and high Interpreting the results anxiety. The dependent variable is the exam score, Hypothesis testing rated from 0 to 100%. Statistical Hypothesis is subjected to statistics. 2) You want to find out how socioeconomic status affects CV =/‹ TV ----- accêpt the Ho attitude towards sales tax increases. Your independent CV › TV ------- reject the Ho variable is “socioeconomic status” with three levels: ERRORS working class, middle class and wealthy. The - Type I dependent variable is measured on a 4 point likert scale - Type II from strongly agree to strongly disagree. Data Scale - Pearson r is a statistical formula that measures the strength between variables and relationships. - To determine how strong the relationship is between two variables, you need to find the coefficient value, which can range between -1.00 and 1.00 Pearson R - If the coefficient value is in the negative range, then that means the relationship between the variables is negatively correlated, or as one value increases, the other decreases. - If the value is in the positive range, then that means the relationship between the variables is positively correlated, or both values increase or decrease together. - Example: ERRORS 1) Participants' age and reported level of income. if there Type I: is positive or negative relationship between someone's - Error that occurs when the researcher concludes that the age and their income level. After conducting the test, samples tested are from different populations (a significant your Pearson correlation coefficient value is +.20 (near difference exists between groups) when, in fact, the 0). Therefore, you would have a slightly positive samples are from the same population (no significant correlation between the two variables, so the strength difference exists between groups); null hypothesis is of the relationship is also positive and considered weak. rejected when it is true You could confidently conclude there is a weak Type II: relationship and positive correlation between one's age - Error that occurs when the researcher concludes that no and their income. In other words, as people grow older, significant difference exists between the samples their income tends to increase as well. examined when, in fact a difference exists; the null 2) Participants' anxiety score and the number of hours hypothesis is regarded as true when it is false. they work each week. After conducting the test, your Example: Pearson correlation coefficient value is -.80 near -1. Therefore, you would have a negative correlation Ho: not guilty between the two variables, and the strength of the Ha: guilty relationship would be strong. You could confidently Decision of the judge: he is guilty. but in reality, he is not! conclude there is a strong relationship and negative (Type I error) correlation between one's anxiety score and how many Decision of the judge: he is not guilty or he is innocent. hours a week they report working. Therefore, those who but in reality , he is guilty/criminal. (Type II error) scored high on anxiety would tend to report less hours Type I: (False Positive Error) of work per week, while those who scored lower on - A Type I error (sometimes called a Type 1 error), is the anxiety would tend to report more hours of work each incorrect rejection of a true null hypothesis. week. - Is asserting something as true when it is actually false. This - p- value= Alternative approach in decision making false positive error is basically a "false alarm" - Decision rule: if p