Sampling and Sample Size Analysis

The target population consists of sampling unit, elements, time and extent (Frankfort-Nachmias, & Nachmias, 2008). This study is to determine the correlations that exist between knowledge of respondents and practice of preventive (lifestyle-modification) measures in hypertension; it will be conducted in Ikoyi local government areas of Lagos state, Nigeria. The population of the community is about two hundred thousand people (National Population Commission, Nigeria, 2004). The target population for this study is adults (age 18 years and above) living and working in various parts of Ikoyi, Lagos State, Nigeria. Quantitative correlation research design will be used to explain important human behavior and to determine the likely outcome by identifying correlations among variables (Frankfort-Nachmias & Nachmias, 2008). Therefore, this research study is designed to answer this question: What is the correlation between knowledge and practices of preventive care (lifestyle-modification) measures in hypertension among the adult respondents? Hypotheses The null hypotheses H0: ρ= 0: There is no correlation between knowledge of respondent and practice of preventive measures (lifestyle modification) in hypertension. The alternate hypotheses H1: ρ ≠ 0: There is real correlation between knowledge of respondents and practice of preventive measures (lifestyle modification) in hypertension. Variables From the stated hypotheses above, the dependent variable (DV) is practice of preventive care measures in hypertension while independent variable (IV) is the knowledge of the respondents. Sampling Strategy for the Research proposal According to Eugene and Bourne (2013) a sample is define as a subset of the population being studied. It is a research technique used to gather information about a population without having to measure the entire population (Abdullahi & Amzat, 2011). The sampling method to be used in this study is multi-stage sampling technique in which the population of Ikoyi will be divided into geographical areas (tertiary units), organizations (secondary units) and finally an individual (primary units). At each stage, a proportion of the corresponding unit will be selected. The respondents that will finally participate in the study will subsequently be chosen from each unit by a systematic sampling method of 1 in 5 (Ike, Aniebue, & Aniebue, 2010). Determining sample size There are three methods of determining sample size in a research study (Lunsford & Lunsford, 1995). Method 1: the minimum number of subjects required in each group of a study is estimated based on a strategy used to detect a significant difference (Cochran, 1965). Method 2: the second method depends on effect size and power (Schiesselman, 1973). The Method 3: the third method answers the question, “How many subjects are needed to detect a certain percent change or effect due to treatment (Lunsford & Lunsford, 1995)?” For the purpose of this study, I will use method 1 to determine sample size and G*Power will be run to determine appropriate sample size based on effect size and statistical power for the study. The minimum sample size will be calculated using the formula; n= z2pq e2 n – Minimum sample size for a statistically significant survey z – Standard normal deviation at 95% confidence limit = 1.96 p – Prevalence of hypertension in Nigeria which is 15.2% (FMOH) q – (1-p) e – Margin of error acceptable or measure of precision usually set at 0.05 n = (1.96)2(0.15)(0.85) 0.052 n = 196 Therefore, the minimum sample size for this study is 196.

Determining Sample Size using G*P Software to Calculate Using power = 80%, effect size of .3, alpha of .01, Compute Sample size. Steps: 1. Test family: Exact. 2. Statistical test: Correlation: Bivariate Normal Model selected. 3. Type of power analysis: A prior: Compute required sample size- given α, power, and effect size selected. Input parameter

Tail one Correlation ρ H1 0.3 α err prob 0.01 Power (1-β err prob) 0.80 Correlation ρ H0 0

Then after entering all these parameter above, I click on calculate to get the output parameter below:

Output parameter

Lower Critical 0.2246524 Upper Critical 0.2246524 Total sample size 107 Actual power 0.8001225

Using of G*P to calculate Sample size = 107

Order now