Limat Prod Apple Tester

Follow @datamgmtandvisualization and get more of the good stuff by joining Tumblr today. Dive in!

I am exploring the factors associated with the nicotine dependence such as introductory age to cigarette, alcohol, marijuana, and the number of best friends of respondent who smoked at least one cigarette a day.

Individually, logistic regression analysis concluded that the association between the response variable and explanatory variable were statistically significant for the following pairs.

  However, when looking at all the explanatory variables in a single model, it shows that introductory age to marijuana was not statistically significant.

I went further and removed association of the number of best friends who smokes from model, which indicated that introductory age to marijuana, introductory age to alcohol was also not statistically significant.

From this, I conclude that the number of best friends smoking cigarette, confounds the relationship between the introductory age to marijuana and nicotine dependence. Also, the same can be said for the number of best friends smoking, confounds the relationship between the introductory age to alcohol and nicotine dependence.

The odd ratio indicates for individuals with best friend smoking are 2.114 times more likely to be nicotine dependence. In addition the confidence interval is between 1.87 and 2.4 for nicotine dependence and the number of best friends who smokes.  

H1TO2 = "Introductory Age to Cigarette" /*1 to 20*/    H1TO14 = "Introductory Age to Alcohol" /*1 to 19*/    H1TO30 = "Introductory Age to Marijuana" /*1 to 18*/    H1TO9 = "# of best friends, how many smoke at least 1 cigarette a day?"    H1TO3 = "Have you ever smoked cigarettes regularly, that is, at least 1 cigarette every day for 30 days?"   ;

/* Tried smoking everyday: 6 = Refused; 7= Legit Skip; 0 = no; 1 = yes;*/ if H1TO3 > 1 then H1TO3 = .; /*Of your 3 best friends, how many smoke at least 1 cigarette a day? */ if H1TO9 > 3 then H1TO9 = .; /* Introductory Age to Cigarette */  if H1TO2 = 0 or H1TO2 > 95 then H1TO2  = .;

/*Introductory Age to Alcohol 1 to 19*/  if H1TO14 = 0 or H1TO14 > 95 then H1TO14 = .; /*Introductory Age to Marijuana - 1 to 18*/  if H1TO30 = 0 or H1TO30 > 95 then H1TO30 = .;

/*Model with all the explanatory variables - Removed the Best Friends smoking*/ PROC LOGISTIC DESCENDING; MODEL  H1TO3 = H1TO2 H1TO14 H1TO30 ; run;

I also hypothesis that nicotine dependence of an individual is also associated with the number of best friends who smoke regular with that individual and how well the individual’s self rated depression feelings.

To examine the probability of nicotine dependence changing  in the presence of feeling depressed, or # of best friends smoking cigarettes using the odd ratio.The odd ratio for nicotine dependence and self rated feeling of depression is less than one. Therefore the nicotine dependence will increase with or without the feeling of self rated depression.The odd ratio for nicotine dependence and best friends smoking is greater than one. Therefore  as the number of friends who smokes increases, the nicotine dependency will likely to increase.However, since none of the odd ratios are significant, I am unable to make the following statements on the probability of explanatory variable and response variable.  “The adolescents with best friends smoking cigarettes is 1.486  times more likely to be nicotine dependence with 95% confidence of this probability falling between 0.963 and 2.293 for new sample data.”

/*Missing Values: Racial Background 6-Refused; 7-Legitimate Skip; 8-don’t know; 9-Not Applicable*/ if H1GI8 > 5 THEN H1GI8 = .; if H1TO3 > 1 then H1TO3 = .; /* Tried smoking everyday */

/*Introductory age*/ IF H1TO2 = 0  or H1TO2 > 20 THEN H1TO2 = .; IF H1TO11 = 0 OR H1TO11 > 18  OR H1TO11 = '.'  THEN H1T011 = .; IF H1TO14 > 19 THEN H1T014 = .; IF H1TO30 = 0 OR H1TO30 > 18 THEN H1T030 = .; IF H1TO34 = 0 OR H1TO34 > 18 THEN H1T034 = .; IF H1TO37 = 0 OR H1TO37 > 18 OR H1TO37  = '.' THEN H1TO37  = .; IF H1TO40 = 0 OR H1TO40 > 18 OR H1TO40  = '.' THEN H1TO40  = .;

/*# of Cig that's smoked in the past 30 days*/ if H1TO7 = 0 or H1TO7 > 95 THEN H1TO7 = .; IF H1TO16 => 90 THEN H1TO16 = .; if H1TO32 = 0 OR H1TO32 > 800 THEN H1TO32 = .; IF H1TO36 = 0 OR H1TO36  > 33 THEN H1TO36  = .; IF H1TO39 = 0 OR H1TO39 > 789 OR H1TO39 = '.' THEN H1TO39  = .; IF H1TO42 = 0 OR H1TO42 > 132 OR H1TO42 = '.' THEN H1TO42 = .;

*Find the means to center Introductory Age to Tobacco, alcohol; PROC MEANS; VAR  H1TO2  H1TO11 H1TO14 H1TO30 H1TO34 H1TO37 H1TO40  H1TO7 H1TO16 H1TO32  H1TO36 H1TO39   ; RUN;

Individual's with younger introductory age to cigarette on average will have -1.192 nicotine dependence.  As per the confidence interval, the introductory age to cigarette will have nicotine dependence  between -1.896 and -0.4886, if a  different sample is selected from the population.

Individual's with younger introductory age to marijuana on average will have -1.248 nicotine dependence. As per the confidence interval, the introductory age to marijuana will have nicotine dependence between -1.979 and -0.516 , if a  different sample is selected from the population.

I using the Q-Q plot to evaluate the assumption that the residuals from the regression model are normally distributed.  From the graph below the dots deviates at the higher and lower quantiles.  This is an indication that the model's estimated residuals do not follow a perfect normal distribution. From this, it can be concluded that the linear association that we observed in the scatter plot may not be fully estimated by the linear term.

For standard normal distribution,  the residuals plots should fall between 2 standard deviations for more than 95% (from the observation). There are 5 extreme outliers which fall above 3 standard deviations. The residuals are greater than the absolute value of 2.5. This is enough evidence that the level of error within the model is unacceptable.  In other words this models a fairly poor fit to the observed data.

Using the leverage plot, I can identify the observations that unusually  have large impact on the estimation of the predicted value of the response variable (nicotine dependence) or their outlier.  

This graph can show us by how much the predicted score will differ in the observation. In this case the outliers  (red dots) are close to zero leverage values which means they don't have strong influence on the estimation of the regression parameters.  The circled observation in the graph has a high leverage but it s not an outlier.

/*Introductory age*/ IF H1TO2 = 0  or H1TO2 > 20 THEN H1TO2 = .; IF H1TO11 = 0 OR H1TO11 > 18  OR H1TO11 = '.'  THEN H1T011 = .; IF H1TO14 > 19 THEN H1T014 = .; IF H1TO30 = 0 OR H1TO30 > 18 THEN H1T030 = .; IF H1TO34 = 0 OR H1TO34 > 18 THEN H1T034 = .; IF H1TO37 = 0 OR H1TO37 > 18 OR H1TO37  = '.' THEN H1TO37  = .; IF H1TO40 = 0 OR H1TO40 > 18 OR H1TO40  = '.' THEN H1TO40  = .;

/*# of Cig that's smoked in the past 30 days*/ if H1TO7 = 0 or H1TO7 > 95 THEN H1TO7 = .; IF H1TO16 => 90 THEN H1TO16 = .; if H1TO32 = 0 OR H1TO32 > 800 THEN H1TO32 = .; IF H1TO36 = 0 OR H1TO36  > 33 THEN H1TO36  = .; IF H1TO39 = 0 OR H1TO39 > 789 OR H1TO39 = '.' THEN H1TO39  = .; IF H1TO42 = 0 OR H1TO42 > 132 OR H1TO42 = '.' THEN H1TO42 = .;

*Find the means to center Introductory Age to Tobacco, alcohol; PROC MEANS; VAR  H1TO2  H1TO11 H1TO14 H1TO30 H1TO34 H1TO37 H1TO40  H1TO7 H1TO16 H1TO32  H1TO36 H1TO39   ; RUN;

*Scatterplot with linear regression line; proc sgplot; reg x=H1TO2 y= H1TO7  / lineattrs=(color=blue thickness=2) clm; yaxis label ="# of Cigarettes Smoked in last 30 days"; xaxis label ="Introductory age to Cigarette"; run;

*Scatterplot with linear regression line; proc sgplot; reg x=H1TO2 y= H1TO7  / lineattrs=(color=blue thickness=2) degree=1 clm; reg x=H1TO2 y= H1TO7  / lineattrs=(color=green thickness=2) degree=2 clm; yaxis label ="# of Cigarettes Smoked in last 30 days"; xaxis label ="Introductory age to Cigarette"; run;

*Evaluating the Residual's Stardard deviation; proc gplot; label stdres ="standarized residual" H1GI20="Addolecent age"; plot stdres*H1GI20/vref=0; run;

Hypothesis  For this assignment I would like to look into the following hypothesis/research question.  An individual’s amount of cigarette smoking is associated with the individual’s age on when the very first cigarette was introduced/smoked.  

Variables of my Analysis: Explanatory Variable (Quantitative):  Age to the introduction of the 1st Cigarette Response Variable (Quantitative): Number of cigarettes smokes within the last 30 days 

The F Statistics is 60.34 and the P value is biking…roller blading} H1DA5 {Active Sports -> Soccer, baseball} H1DA6 {Exercise}

H1FS4 {feel good as other people} H1FS6 {feel Depressed} H1FS7 {Feel too tired} H1FS9 {feel life is a failure} H1FS11 {feel happy} H1FS14 {feel people were unfriendly to you} H1FS15 {enjoyed life} H1FS16 {feel sad} H1FS17 {felt that people disliked you} H1FS18 {was hard to get started doing things} H1FS19 {felt life was not worth living}

 a) Report the study design that generated that data (for example: data reporting, surveys, observation, experiment). The study design that was used to generate the data was survey (questionnaires) filled in by an In-Home interviewer. 

b) Describe the original purpose of the data collection. The purpose of this longitudinal data collection is to study the environmental impacts and the outcome of the adolescent students.

 a) Describe what your explanatory and response variables measured. The list below are the explanatory and response variable as potential candidates, selected for my research.

H1DA1 (House Work/Chores) H1DA2 {Hobbies} H1DA3 {TV/Video Games} H1DA4 {Physical Activity -> biking…roller blading} H1DA5 {Active Sports -> Soccer, baseball} H1DA6 {Exercise}

H1FS1 {bothered by things that usually don’t bother you.} H1FS4 {feel good as other people} H1FS6 {feel Depressed} H1FS7 {Feel too tired} H1FS9 {feel life is a failure} H1FS11 {feel happy} H1FS14 {feel people were unfriendly to you} H1FS15 {enjoyed life} H1FS16 {feel sad} H1FS17 {felt that people disliked you} H1FS18 {was hard to get started doing things} H1FS19 {felt life was not worth living}

c) Describe how you managed your explanatory and response variables. Since, all the selected data elements for explanatory and response variables are categorical, the survey had 4 options to indicate their degree or frequency or measure as a response. There were two more options provided for the respondent to refuse to answer or to claim unawareness. For the latter two options, I used it as missing data.

For this assignment I would like to look into the following hypothesis/research question.  An individual’s amount of cigarette smoking is associated with the individual’s age on when the very first cigarette was introduced/smoked.  In addition, the individual’s amount of cigarette smoking  is moderated by the number of best friends who are also smokers.

Variables of my Analysis: Independent Categorical Variable:  Age to the introduction of the 1st Cigarette (20 Levels) Dependent Continuous Variable: Number of cigarettes smokes within the last 30 days Moderating Categorical Variable: Number of friends who are smokers (3 levels)

Please note that Anova test on introduction to 1st Cigarette vs the number of cigarettes smoked had a significance difference.  However, when I conducted the post hoc Duncan test it turned  out only 3 groups were significantly difference.  I am not sure if Duncan result has any relevance as indicator in proceeding with the testing of significance in the moderation variable  (please feel free to comment on this).   For the sake of this assignment, I am going to proceed with the testing significance of the moderation variable.

The Image Below  is the summary of the ANOVA analysis.  From ANOVA analysis, there was a significant difference for each of the moderating group.   

The below image/table is created by consolidating the means of each group with the moderating variable resulted from ANOVA analysis. I have selected few  age groups from my independent variable by highlighting them to demonstrate the impact of the moderating variable.   The age group is broken down further by the moderating group levels.  It clearly shows an increase in the number of cigarettes smoked as the number of friends who smokes increases.

LABEL   H1TO2 = "Age of introduction to the first Cigeratte" H1TO7 = "Number of Cigarettes smoked in a day, (within past 30 days)" H1TO9 = "Number of Best friends smoke atleast 1 cigerate a day " ;

PROC ANOVA;  CLASS H1TO2; MODEL H1TO7 = H1TO2; MEANS H1TO2/DUNCAN; PROC ANOVA;  CLASS H1TO2; MODEL H1TO7 = H1TO2; MEANS H1TO2; BY H1TO9; RUN;

            My initial research is to study the association between self rated mental health and the physical activities.  All the data elements related to my research is categorical.  Subsequently for  the sake of this assignment I would like to change my research question to the following.

         From the scatter plot and from the bar graph I see a negative linear relationship. I get an R Value of -0.11849 and p-value of 0.0001 from the Pearson correlation coefficient test .  My R-value indicates a very week negative relationship even though my p-value is less than 0.05.  In order for the association to be significant the p-value has to be less than 0.05  and  R has to closer to  -1 or +1.  Hence, this test indicates that the observation is due chance or luck.  (Check out this link for more info on my type of finding ) .

LABEL   H1DA11="Hours Listening to Radio" H1GI1Y="Year of Birth" H1DA8="Hours Watching Television" ;   /* Missing value: 6:Refused; 8:Don't Know  */ IF H1DA11 > 99 OR H1DA11 = 0 THEN H1DA11 =.; IF H1DA8 > 99 OR H1DA8 = 0 THEN H1DA8 =.;

 My research is related to the association between physical activities and self rated mental health.  Based on the AddHealth data set, I hypothesize that there is an association between exercising and feeling depressed.

Explanatory variable is the frequency of exercising in the past week, and as follows the   frequency of feeling depressed in the past week will be the response variable.  These two variables are categorical with 4 groups.  

Null Hypothesis: There is no association between exercising and feeling depressed. Alternate Hypothesis: There is association between exercising and feeling depressed.

For the practice of this assignment, I will pretend that my P value < 0.05 and try to avoid Type 1 Error. Therefore, I will compare 6 pairs of groups  to examine difference in the significance level per pair.  The difference in the significance level should be less than 0.0083, following the Bonferroni adjustments.

From the Chi Square Statistics: P Value of Group 0 & 1 = 0.88 P Value of Group 0 & 2 = 0.27 P Value of Group 0 & 3 = 0.76 P Value of Group 1 & 2 = 0.02 P Value of Group 1 & 3 = 0.38 P Value of Group 2 & 3 = 0.42

For all the comparison, the observed values are significantly different from the adjusted significance level of 0.0083. Therefore, I should accept my Null hypothesis.

/*For my research, I am only interested in Adolecents who are aged from 13 to 18.   There is no reference as to when the survey was conducted. Therefore I am going to assume grade 9 to grade 12 as adolcents*/

/*The missing Values*/ /* IF H1GI20 = 7 OR  H1GI20 = 8 OR  H1GI20 = 96 OR H1GI20 = 97 OR H1GI20 = 98 OR  H1GI20 = 99 THEN H1GI20 =.; */   /* Missing value: 6:Refused; 8:Don't Know  */ IF H1FS6 = 6 OR H1FS6 = 8 THEN H1FS6=.; IF H1DA6 = 6 OR H1DA6 = 8 THEN H1DA6=.;

  VALUE  H1FSF   0="Never or rarely"                1="Sometimes"                2="A lot of time"                3="Most of the time"                6="Refused"                8="Unsure";

My previous research question does not involve any quantitative variables, and consequently I am changing my research question for this assignment to the following.  

My P-value is 0.66m which is greater than 0.5 which indicates my null hypothesis can be rejected. There is no association in racial background and the amount of hours spent watching television among adolescents. Therefore, I accept the null hypothesis.

For practice of this assignment, the Duncan test was conducted (the Post Hoc tests for ANOVA). By conducting the Duncan test, there is only one group which indicates that none of the groups are significantly difference.

LABEL   H1GI8="Which one category best describes your racial background?" H1DA11="Hours listening to radio" H1DA8="How many hours a week do you watch television"

;/*For my research, I am only interested in Adolescents who are aged from 13 to 18.   There is no reference as to when the survey was conducted. Therefore I am going to use the grades to filter the adolescent which is from grade 9 to grade 12*/

/*The missing Values*/ IF H1GI20 = 7 OR   H1GI20 = 8 OR   H1GI20 = 96 OR   H1GI20 = 97 OR   H1GI20 = 98 OR     H1GI20 = 99     THEN H1GI20 =.;

/* Missing value: Watching TV {996=Refused; 998=Don't know; 0=Don't Watch; */ IF H1DA8 = 996 OR H1DA8 = 998 OR H1DA8 = 0 THEN H1DA8 =.;PROC ANOVA;  CLASS H1GI8;

 For this assignment, I have used the variables self-rated depression feeling (H1FS6) and the self-rated leisure activity level (H1DA4) such as roller-skating, skate-boarding and etc for the analysis.

Self rated depression is one measure out of many that contributes to a self-rated mental health and leisure activity is one of many measure to rate the physical activity level of an individual.

Leisure activity is the explanatory or independent variable and the depression feeling will be my response variable. The following are the two categorical variables values that I will be analyzing in this assignment.

The physical activity and the self-rated mental health measure graphs are both negatively skewed. The mode for PA graph is 0 which indicates that most of the adolescents were never involved in any leisure physical activity.  The mode for the depression level is also zero, which indicates that the adolescents never felt depressed.

Adolescents who never did leisure activity felt depressed 57% frequently depressed.   Adolescents who did 1 or 2 times leisure activity a week felt 50% frequently depressed. Adolescents who did 3 or 4 times of leisure activity a week felt 53% frequently depressed and the adolescents who 5 or more times leisure activity felt 45% frequently depressed.

LABEL   H1DA4="Frequency of doing leisure activities (walking, roller blading, skating..) in the past week?"   H1FS6="You felt depressed in the last week" H1FS6_F ="Frequency of depression feeling in the last week"; ;

/*For my research, I am only interested in Adolecents who are aged from 13 to 18.   There is no reference as to when the survey was conducted. Therefore I am going to use the grades to filter the adolecent which is from grade 9 to grade 12*/

/*The missing Values*/ IF H1GI20 = 7 OR   H1GI20 = 8 OR   H1GI20 = 96 OR   H1GI20 = 97 OR   H1GI20 = 98 OR     H1GI20 = 99     THEN H1GI20 =.;

/* For PHYSICAL ACTIVITY VARIABLE & Self Rated Mental Health varaiables, I am going to filter out data where the respondent has refused or was unsure. For my research, I am only interested in the data who have given a definite answer to the survey questions.

/* PROC FREQ; TABLES H1DA4 H1FS6 H1FS6_F; PROC UNIVARIATE; VAR H1DA4; PROC UNIVARIATE; VAR H1FS6; */ PROC GCHART; VBAR H1DA4/Discrete TYPE=PCT; PROC GCHART; VBAR H1FS6/Discrete TYPE=PCT;

Since my project only involved adolescents, the age group has to be from 13 to 17.  Since there is no age available, I will be deriving it from the grades or class that is studying in. I am assuming that students from grade 9 to 12 should fit the adolescent age group.

To measure physical activities, From adolescent health code book there are individual variables for house work (H1DA1),  leisure physical activity(H1DA4), active sports(H1DA5) and exercise(H1DA6). The same frequency scale has been used for all the indicated variables.  Therefore, for my research, the secondary variable physical activity is derived by combining (adding and averaging) the values of the individual associated variables.  

To measure the self-rated mental health, this secondary variable need to be derived by combining the variables from the survey such as feeling bothered by things, poor appetite, unable to shake of blues, trouble focusing, depression, feeling tiered, feeling life as a failure, feeling feared, feeling lonely, feeling sad, feeling life was not worth it and feeling that people dislike the respondent.

LABEL   H1DA1="Frequency of doing house work (chores) in the last week"   H1DA4="Frequency of doing leisure activities (walking, jogging, gym..) in the past week?"   H1DA5="Frequency of playing active sports (baseball, soccer, softball..) in the past week?" H1DA6="Frequency of doing exerecise in the last week"

H1FS1="You were bothered by things in the last week" H1FS2="You didn’t feel like eating (poor apetite) in the last week" H1FS3= "Unable to shake off the blues, even with help from your family and your friends in the last week." H1FS5="You had trouble keeping your mind on what you were doing in the last week." H1FS6="You felt depressed in the last week" H1FS7="You felt that you were too tired to do things in the last week" H1FS9="You thought your life had been a failure." H1FS10="You felt fearful in the last week" H1FS13="You felt lonely in the last week" H1FS16="You felt sad  in the last week " H1FS17="You felt that people disliked you in the last week" H1FS19="You felt life was not worth living in the last week" PA="Derived variable - Frequency of doing Physcial activities" SRMH="Derived variable - Degree of feelling towards Self Rated Mental Health" ;

/*For my research, I am only interested in Adolecents who are aged from 13 to 18.   There is no reference as to when the survey was conducted. Therefore I am going to use the grades to filter the adolecent which is from grade 9 to grade 12*/

/*The missing Values*/ IF H1GI20 = 7 OR   H1GI20 = 8 OR   H1GI20 = 96 OR   H1GI20 = 97 OR   H1GI20 = 98 OR     H1GI20 = 99     THEN H1GI20 =.;

/* For PHYSICAL ACTIVITY VARIABLE & Self Rated Mental Health varaiables, I am going to filter out data where the respondent has refused or was unsure. For my research, I am only interested in the data who have given a definite answer to the survey questions.

IF H1FS1 LE 4; IF H1FS2 LE 4; IF H1FS3 LE 4; IF H1FS5 LE 4; IF H1FS6 LE 4; IF H1FS7 LE 4; IF H1FS9 LE 4; IF H1FS10 LE 4; IF H1FS13 LE 4; IF H1FS16 LE 4; IF H1FS17 LE 4; IF H1FS19 LE 4;

PA = (H1DA1 + H1DA4 + H1DA5 + H1DA6)/4; SRMH = (H1FS1 + H1FS2 + H1FS3 + H1FS5 + H1FS6 + H1FS7 + H1FS9 + H1FS10 +        H1FS13 + H1FS16 + H1FS17 + H1FS19)/12;

/* -------------------------------------------------------------------------- */ /*--------------------------------------------------------------------------*/

/* For PHYSICAL ACTIVITIE VARIABLE, I am going to filter out data where the respondent has refused or was unsure about the physical activities.For my research, I am only interested in the data who have given a definite answer to the survey questions related to the physical activities.

In my data set, the feeling section is an indicator of Self Rated Mental Health. For FEELINGS VARIABLE, I am going to filter out data where the respondent has refused or was unsure about on how they feel. For my research, I am only interested in the data who have given a definite answer to the survey questions related to how they feel. FILTERED OUT DATA: 6 refused; 8 don’t know; */

/* For my research, I am only interested in Adolescents who are aged from 13 to 18.  There is no reference as to when the survey was conducted. Therefore I am going to use the grades to filter the adolescent which is from grade 9 to grade 12*/

/* -------------------------------------------------------------------------- */ /* End of Program */ /*--------------------------------------------------------------------------*/

I have filtered the sample to be of only adolescents who are in grade 9 to 12.  I was unable to extrapolate age using date of birth  because the surveyed date was missing, and hence I had use their grade/class level to select the adolescents.

As part of handling the missing data, I have filtered out the observations who have refused to give an answer or were unsure about giving a definite answer to the survey question.   100% of the adolescents have given a definite answer to the frequency of the exercise question.  For the self rated mental health variables (feeling tiered or depressed) an accumulative of  0.5% of 4366 adolescents observation  contributes to the missing data.  

In addition, ~0.11 percent of 4533 contributes to the missing data in identifying the adolescents. For the  self rated mental health variables (feeling tiered or depressed), with the inclusion of missing data in identifying the adolescents yields ~0.68 percent.

According to my frequency chart my sample size is 4357.  However the subjects feeling depressed is ~2.5% and feeling often tired  is ~3.2 percent of the sample size and the adolescents who never exercised is ~17% which is the smallest among the distribution of the frequency of exercises.

STEP 3. Prepare a codebook of your own (i.e., print individual pages or copy screen and paste into a new document) from the larger codebook that includes the questions/items/variables that measure your selected topics.)

Section 1: General Introductory -> H1GI1M (Birth Date) Section 1: General Introductory -> H1GI1Y (Birth Date) Section 1: General Introductory -> H1GI19 {Schooling?} Section 1: General Introductory -> H1GI20  {Grade/Class} Section 1: General Introductory -> H1GI21  {School status} Section 2: Daily Activities -> H1DA1 (House Work/Chores) Section 2: Daily Activities -> H1DA2 {Hobbies} Section 2: Daily Activities -> H1DA3 {TV/Video Games} Section 2: Daily Activities -> H1DA4 {Physical Activity -> biking...roller blading} Section 2: Daily Activities -> H1DA5 {Active Sports -> Soccer, baseball} Section 2: Daily Activities -> H1DA6 {Exercise}

STEP 7. Based on your literature review, develop a hypothesis about what you believe the association might be between these topics. Be sure to integrate the specific variables you selected into the hypothesis.

I would like to explore the physical activities of an adolescent and how they feel about themselves. The domain of the variable physical activity(PA) can be  biking, roller blading, sports, exercise and also the housework (chores). The variable feeling is a measure of how the adolescents would feel about themselves on their life, depression, happiness and etc.

Based on the literature review, I have discovered the health related quality of life (HRQL) indicates how individual perceive their physical, mental and social health[4]. There are also evidenced indications that physical activity is directly related to HRQL while sedentary behaviour is inversely associated with poor mental and physical health[4].

The self rated mental health (SRMH) [2] which is how an adolescent perceive about their mental health is also strong indicator of their overall self rated health. A study indicates physical activities are related to physical self concept which is related to global self esteem; which itself  is an indicator of the  mental health[3].

As per my literature review, there have been numerous studies have been conducted SRMH however nothing was more specifically conducted on SRHM of adolescents and on  physical active lifestyle.

Therefore I hypothesis that adolescents engaged in physical activities would rate themselves with high self rated mental health (SRMH) than the adolescents who are less engaged in physical activity.

3. Schmidt M, Blum M, Valkanover S, Conzelmann A (2014). Motor ability and self-esteem: The mediating role of physical self-concept and perceived social acceptance. Psychology of Sport and Exercise (17) 15-23

4. Guallar-Castillón P, López-García E, Bayán-Bravo A, Gutierrez-Fisac J, León-Muñoz L, Rodríguez-Artalejo F,  et al (2014). The association of major patterns of physical activity, sedentary behavior and sleep with health-related quality of life: A cohort study. Preventive Medicine (67) 248–254