From 870d3275f1af219b322153b27308abbab7a88c0f Mon Sep 17 00:00:00 2001 From: kayliebrehm Date: Wed, 6 Jul 2022 04:12:14 +0000 Subject: [PATCH 1/4] Q3 Initial --- gss2018.rmd | 11 ++++++++--- 1 file changed, 8 insertions(+), 3 deletions(-) diff --git a/gss2018.rmd b/gss2018.rmd index 4774400..e896b8b 100644 --- a/gss2018.rmd +++ b/gss2018.rmd @@ -1,7 +1,7 @@ --- title: "General Social Survey" -author: "Your Name" -date: "Year 2020" +author: "Kaylie Brehm" +date: "Summer 2022" output: html_document: number_sections: true @@ -83,11 +83,16 @@ Is there a difference in years of education (EDUC) between the those who did or Determine if a persons performance on the wordsum test (WORDSUM) is independent of their level of schooling (DEGREE). +$H_0$ A persons performance on the wordsum test is not independent of their level of schooling. +$H_A$ A persons performance on the wordsum test is not independent of their level of schooling. + ## Methods -##Results +Both are numerical variables, each with many variables. The analysis technique we will use is Num~Num The results will show a scatterplot, some numerical values, and an anova plot. + +## Results From a540fe26c45ecf89e0edbb03f5a340c4fe39ea21 Mon Sep 17 00:00:00 2001 From: kayliebrehm Date: Wed, 6 Jul 2022 04:22:56 +0000 Subject: [PATCH 2/4] Q3 Data --- gss2018.rmd | 23 ++++++++++++++++++++++- 1 file changed, 22 insertions(+), 1 deletion(-) diff --git a/gss2018.rmd b/gss2018.rmd index e896b8b..37e13e5 100644 --- a/gss2018.rmd +++ b/gss2018.rmd @@ -90,7 +90,7 @@ $H_A$ A persons performance on the wordsum test is not independent of their leve -Both are numerical variables, each with many variables. The analysis technique we will use is Num~Num The results will show a scatterplot, some numerical values, and an anova plot. +The numerical values on the average score of WORDSUM test will be compared with the level of schooling degree (categorical) using a numerical-categorical analysis. I will use a boxplot graph, some numerical values, and an aov to observe this. ## Results @@ -102,15 +102,36 @@ Both are numerical variables, each with many variables. The analysis technique w + +```{r} +boxplot(WORDSUM~DEGREE,data=GSSdata) +``` + + + + #### Numerical Descriptive Results +```{r} +favstats(WORDSUM~DEGREE,data=GSSdata) +``` + + + ### Inferential Results +```{r} +model1 <- aov(WORDSUM~DEGREE,data=GSSdata) +summary.aov(model1) +``` + + + # Discussion and Conclusion From 8691c6fa6b9f5352836e60c6f0cf6095a51c2998 Mon Sep 17 00:00:00 2001 From: kayliebrehm Date: Wed, 6 Jul 2022 04:29:44 +0000 Subject: [PATCH 3/4] Q3 Final --- gss2018.rmd | 8 ++++---- 1 file changed, 4 insertions(+), 4 deletions(-) diff --git a/gss2018.rmd b/gss2018.rmd index 37e13e5..554b23f 100644 --- a/gss2018.rmd +++ b/gss2018.rmd @@ -84,7 +84,7 @@ Is there a difference in years of education (EDUC) between the those who did or Determine if a persons performance on the wordsum test (WORDSUM) is independent of their level of schooling (DEGREE). $H_0$ A persons performance on the wordsum test is not independent of their level of schooling. -$H_A$ A persons performance on the wordsum test is not independent of their level of schooling. +$H_A$ A persons performance on the wordsum test is independent of their level of schooling. ## Methods @@ -107,7 +107,7 @@ The numerical values on the average score of WORDSUM test will be compared with boxplot(WORDSUM~DEGREE,data=GSSdata) ``` - +This boxplot shows us median and quartile values, which seem to differ between each group. It also shows us the outliers of certain degrees. Overall, the data is very close in values, but there is still a clear difference between groups. The more advanced in education, the higher the score seems to be, and vise versa. #### Numerical Descriptive Results @@ -118,7 +118,7 @@ boxplot(WORDSUM~DEGREE,data=GSSdata) favstats(WORDSUM~DEGREE,data=GSSdata) ``` - +This table shows the numerical values for median, mean, quartiles, and standard deviation. Overall, we see a different mean for each degree level. The mean in bachelors and junior college is about the same but all the other means are different. The max range is 12 for all groups except less than high school, which is 11. The quarter three value is the same in all groups apart from high school and less than high school. These ever changing values show variation within WORDSUM scores in each group. ### Inferential Results @@ -130,7 +130,7 @@ model1 <- aov(WORDSUM~DEGREE,data=GSSdata) summary.aov(model1) ``` - +The null hypothesis was "A persons performance on the wordsum test is not independent of their level of schooling." I reject the null hypothesis due to the p-value being 0.000236, which is less than 0.05. When observing mean and median scores within the box plot, there does seem to be a difference between the average score on the WORDSUM test and level of schooling DEGREE. This fact is proven in the numerical findings section. Additionally, there is a significant difference between less than high school and graduates. I cannot prove whether or not result on WORDSUM test is due to level of schooling degree but the observed difference is something to take into consideration when performing such tests. # Discussion and Conclusion From e5d28187c17cf694e4be3ba5189bd27b8425b94b Mon Sep 17 00:00:00 2001 From: kayliebrehm Date: Wed, 6 Jul 2022 04:32:05 +0000 Subject: [PATCH 4/4] Q3 Edit --- gss2018.rmd | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/gss2018.rmd b/gss2018.rmd index 554b23f..3580f9d 100644 --- a/gss2018.rmd +++ b/gss2018.rmd @@ -130,7 +130,7 @@ model1 <- aov(WORDSUM~DEGREE,data=GSSdata) summary.aov(model1) ``` -The null hypothesis was "A persons performance on the wordsum test is not independent of their level of schooling." I reject the null hypothesis due to the p-value being 0.000236, which is less than 0.05. When observing mean and median scores within the box plot, there does seem to be a difference between the average score on the WORDSUM test and level of schooling DEGREE. This fact is proven in the numerical findings section. Additionally, there is a significant difference between less than high school and graduates. I cannot prove whether or not result on WORDSUM test is due to level of schooling degree but the observed difference is something to take into consideration when performing such tests. +The null hypothesis was "A persons performance on the wordsum test is not independent of their level of schooling." I reject the null hypothesis due to the p-value being 0.000236, which is less than 0.05. The high F value at 10.04 shows significance as well. When observing mean and median scores within the box plot, there does seem to be a difference between the average score on the WORDSUM test and level of schooling DEGREE. This fact is proven in the numerical findings section. Additionally, there is a significant difference between less than high school and graduates. I cannot prove whether or not result on WORDSUM test is due to level of schooling degree but the observed difference is something to take into consideration when performing such tests. # Discussion and Conclusion