Scenario One (Child and Adolescent Development).
Student’s Name
Institutional Affiliation
Course Name and Number
Date
INTRODUCTION.
I chose the first scenario because it aligns with my concentration (Child and Adolescent behaviour). Parents are usually scared when infants take time getting to specific stages of development like teething and crawling, especially crawling. I have chosen this scenario because it might help put some parents at ease when faced with the dilemma of why their child has not started crawling yet. The parties involved in this study are infants between 28 to 34 weeks. The study answers the question,” Does seasonal variation in climate influence the onset of locomotion?” The dataset describes two different but related variables; this means we can run a regression and correlation analysis and reach a cause-effect conclusion.
When analysing this scenario am obeying the principle of competency in APA’s Ethical principles of psychologists. My concentration is Child and adolescent behaviour, and this is the only scenario that analyses this category (American Psychological Association, 2017). The research also exemplifies confidentiality by not revealing the identities of the children. The ethical issue that may arise from the analysis and interpretation of the dataset is equal representation. Ethics requires all data on participants to be accounted for in the results, but this might lead to misinterpretation of results due to outliers. When reporting my results, I will align myself with APA’s ethical principles by ensuring I only reach informed conclusions and do not falsify any results, but showing all my workings.
DATA ANALYSIS
Sample Size.
The sample size for this research was 425 infants (n=425). This is a large sample size; therefore, the sample will give reliable results with more precision (greater confidence level and effect size). Having a large sample allows the researcher to account for variability in the datasets. Therefore, the sample size is powerful enough to draw valid conclusions. Since we have a large population, we have a greater chance of getting a significant effect; a large sample size reduces our systematic and standard errors (Littler, 2018).
what statistical procedures should be implemented in your analysis?
The statistical procedure to implement in this analysis is correlation and regression. Why use these two tests? Correlation measures the degree of relationship between two variables. However, it does not determine the cause and effect between variables. On the other hand, regression determines how variables are related to each other; what an increase in the independent variable would mean for a dependent variable (does the dependent variable increase or decrease) (Surbhi, 2021). So why are these two tests sometimes referred to as a pair?
Regression only exists if two variables are correlated. An independent and dependent variable can be positively correlated, negatively correlated, or have no correlation at all. Regression only exists if there is a positive or negative correlation. The correlation coefficient (r) ranges from +1 to – 1. A positive number shows a positive correlation, and a negative number has a negative correlation. Linear regression provides a formula from the scatter plot diagram that allows the researcher to analyze the effect of manipulating a specific variable.
For this scenario, we investigate how the season a child is born influences the beginning of locomotion when experimental factors like seasonal climate change are evaluated. Therefore, it is an analysis examining the relationship between two factors and how they influence each other. Correlation will identify the relationship between these factors and regression how the variables affect each other when adjusted. T-test, Z-test, and Anova are tests that are mostly used to compare means, and in this case, we are not comparing means.
Chance factor.
The chance factor is mainly caused by variability in data; the presence of outliers in a dataset. The presence of extreme values in a variable, especially in small sample sizes, produces no correlation in a dataset when there actually is a correlation or vice versa. In this report analysis, a histogram and scatter plot will be used to identify outliers, and they will be deleted to check if they cause any change in our results. Using histograms, box plots, and scatter plots helps in identifying extreme values. If these extreme values do not severely affect our results, they won’t be deleted, but if they do, they will be deleted and recorded as missing data.
Commute Mean and Standard deviation.
Average age kids start to crawl in weeks:
Mean = x̄
=
average yearly temperature six months after the birth in units Fahrenheit
Mean = x̄
= 50.25
Standard deviation.
| Average Age Starting to Crawl (weeks) | x− x̄ | (x− x̄)2 |
| 29.84 | -1.93 | 3.7249 |
| 30.52 | -1.25 | 1.5625 |
| 29.7 | -2.07 | 4.2849 |
| 31.84 | 0.07 | 0.0049 |
| 28.58 | -3.19 | 10.1761 |
| 31.44 | -0.33 | 0.1089 |
| 33.64 | 1.87 | 3.4969 |
| 32.82 | 1.05 | 1.1025 |
| 33.83 | 2.06 | 4.2436 |
| 33.35 | 1.58 | 2.4964 |
| 33.38 | 1.61 | 2.5921 |
| 32.32 | 0.55 | 0.3025 |
| Total | ||
| 381.26 | 0.02 | 34.0962 |
| standard deviation | 1.760584 |
Standard deviation =
=1.760584
| Average Temperature 6 Months After Birth Month (in units Fahrenheit) | x− x̄ | (x− x̄)2 |
| 66 | 15.75 | 248.0625 |
| 73 | 22.75 | 517.5625 |
| 72 | 21.75 | 473.0625 |
| 63 | 12.75 | 162.5625 |
| 52 | 1.75 | 3.0625 |
| 39 | -11.25 | 126.5625 |
| 33 | -17.25 | 297.5625 |
| 30 | -20.25 | 410.0625 |
| 33 | -17.25 | 297.5625 |
| 37 | -13.25 | 175.5625 |
| 48 | -2.25 | 5.0625 |
| 57 | 6.75 | 45.5625 |
| Total | ||
| 603 | 0 | 2762.25 |
| standard deviation | 15.84657 |
Standard deviation =
=15.84657
Histogram
what does the shape of each distribution tell us about the data?
From the shape of the distribution, we can see that there are no outliers; therefore, we will not have any problems with homogeneity of variance or outliers affecting our results. The second diagram is negatively skewed because most of its data lie to the left, while the first diagram is positively skewed because most of its data lie to the right.
HYPOTHESIS.
There was a difference between the two means, however we cannot compare them because they are not related.
Average yearly temperature six months after the birth in units Fahrenheit = 50.25
Average age kids start to crawl in weeks= 31.77
Null hypothesis and alternative hypothesis.
H0: r = 0
There is no relationship between variation in seasonal climate and onset of locomotion.
Ha: r ≠ 0, -1 > r < +1
There is a relationship between season climate variation and the age at which children start to crawl.
RESULTS.
Valid Effect
The relationship between the two variables has a valid effect because their correlation coefficient is between +1 and -1 but is not zero; r the correlation coefficient for the data is -.70. This means that there is a valid effect between the dependent and independent variables. The relationship between the two variables is strong, negative, and linear. It is strong because most of the points on the scatter plot are close to the line, and the correlation coefficient is greater than .70. The relationship is linear because the line of best fit is straight. The relationship is negative because the correlation coefficient is negative, and the line of best fit drops downwards towards the right. Therefore, increasing the age at which a child starts to crawl in weeks decreases the variation in seasonal climate in Fahrenheits.
Statistical significance.
The results showed a statistical significance between the age at which a child starts crawling and seasonal climate variation. There is a relationship between season climate variation and the age at which children start to crawl. Therefore, we reject the null hypothesis and accept the alternative hypothesis.
CONCLUSION.
Interpretation
It means that as Janette Benson had predicted, Variation in seasonal climate influences the onset of locomotion in children (Benson, 1993). The correlation coefficient helped us conclude that there is a relationship between the onset of locomotion and seasonal variation in climate. However, it does not allow us to reach the cause-effect conclusion. The regression line helps us develop a regression equation from the scatterplot, which helps us get a cause-effect conclusion. The equation suggests that the age at which a child starts to crawl is negatively affected by seasonal temperature variation. Therefore, when the average temperature increases, the average time taken by a child to crawl decreases.
Justifying the data analysis procedures
The correlation was used to determine if there was a relationship between the dependent and independent variables. Regression determined the cause-effect between the relationship. A histogram for both data set was made to determine the distribution, identify the variation in values, and identify the outliers for the two variables. A scatter plot was used to determine the relationship between the onset of locomotion and seasonal variation in climate, generate a regression equation and the square of the correlation coefficient. The mean, correlation coefficient, and standard deviation helped us determine that the two variables were not identical.
Statistical procedures required to interpret the data further.
After the study is repeated, a test-retest, inter-item, inter-observer correlation test should be done to ensure that the data is reliable over time and within the group. This study needs to be repeated to determine if the variables’ projections are valid over time and with a different observer.
We need to carry out a partial correlation test while controlling factors like genes and nutrition to determine if the relationship is valid and if other factors influence it.
References.
American Psychological Association. (2017, March). Ethical principles of psychologists and code of conduct. https://www.apa.org. https://www.apa.org/ethics/code
Benson, J. B. (1993, March). Season of birth and onset of locomotion: Theoretical and methodological implications. ScienceDirect.com | Science, health and medical journals, full text articles and books. https://www.sciencedirect.com/science/article/abs/pii/0163638393800298
Littler, S. (2018, June 19). The importance and effect of sample size. Select Statistical Consultants. https://select-statistics.co.uk/blog/importance-effect-sample-size/
Surbhi, S. (2021, February 26). Difference between correlation and regression. Key Differences. https://keydifferences.com/difference-between-correlation-and-regression.html
Leave a Reply